diff --git a/.gitignore b/.gitignore
index 06d10162..3f3874f9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,3 +3,5 @@
 .DS_Store
 .ipynb_checkpoints
 */.ipynb_checkpoints/*
+/.idea
+.idea
diff --git a/Jupyter_Notebooks/Chapter_05_Deep_Neural_Networks/Neural_Networks.ipynb b/Jupyter_Notebooks/Chapter_05_Deep_Neural_Networks/Neural_Networks.ipynb
new file mode 100644
index 00000000..19178349
--- /dev/null
+++ b/Jupyter_Notebooks/Chapter_05_Deep_Neural_Networks/Neural_Networks.ipynb
@@ -0,0 +1,3670 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "489b9bb3",
+   "metadata": {
+    "id": "489b9bb3"
+   },
+   "source": [
+    "<font face=\"XB Zar\" size=5><div dir=rtl align=center>\n",
+    "<font face=\"IranNastaliq\" size=5>\n",
+    "به نام خدا\n",
+    "</font>\n",
+    "<br>\n",
+    "<font size=3>\n",
+    "دانشگاه صنعتی شریف - دانشکده مهندسی کامپیوتر\n",
+    "</font>\n",
+    "<br>\n",
+    "<font color=blue size=5>\n",
+    "مقدمه‌ای بر یادگیری ماشین\n",
+    "</font>\n",
+    "<br>\n",
+    "<hr/>\n",
+    "<font color=red size=6>\n",
+    "فصل پنج\n",
+    "<br>\n",
+    "Neural Networks \n",
+    "</font>\n",
+    "<br>\n",
+    "نویسنده:‌ علی رازقندی\n",
+    "<hr>\n",
+    "\n",
+    "</div></font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8efb6140",
+   "metadata": {
+    "id": "8efb6140"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import pickle as pickle\n",
+    "from torchvision import datasets\n",
+    "from sklearn.datasets import fetch_california_housing\n",
+    "\n",
+    "\n",
+    "%matplotlib inline\n",
+    "plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots\n",
+    "plt.rcParams['image.cmap'] = 'gray'\n",
+    "\n",
+    "def rel_error(x, y):\n",
+    "  \"\"\" returns relative error \"\"\"\n",
+    "  return np.max(np.abs(x - y) / (np.maximum(1e-8, np.abs(x) + np.abs(y))))\n",
+    "\n",
+    "def print_mean_std(x,axis=0):\n",
+    "    print(f\"  means: {x.mean(axis=axis)}\")\n",
+    "    print(f\"  stds:  {x.std(axis=axis)}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57c3af9e",
+   "metadata": {
+    "id": "57c3af9e"
+   },
+   "source": [
+    "# Fully-Connected Neural Nets\n",
+    "In this notebook we will implement fully-connected networks using a modular approach. For each layer we will implement a `forward` and a `backward` function. The `forward` function will receive inputs, weights, and other parameters and will return both an output and a `cache` object storing data needed for the backward pass, like this:\n",
+    "\n",
+    "```python\n",
+    "def layer_forward(x, w):\n",
+    "  \"\"\" Receive inputs x and weights w \"\"\"\n",
+    "  # Do some computations ...\n",
+    "  z = # ... some intermediate value\n",
+    "  # Do some more computations ...\n",
+    "  out = # the output\n",
+    "   \n",
+    "  cache = (x, w, z, out) # Values we need to compute gradients\n",
+    "   \n",
+    "  return out, cache\n",
+    "```\n",
+    "\n",
+    "The backward pass will receive upstream derivatives and the `cache` object, and will return gradients with respect to the inputs and weights, like this:\n",
+    "\n",
+    "```python\n",
+    "def layer_backward(dout, cache):\n",
+    "  \"\"\"\n",
+    "  Receive dout (derivative of loss with respect to outputs) and cache,\n",
+    "  and compute derivative with respect to inputs.\n",
+    "  \"\"\"\n",
+    "  # Unpack cache values\n",
+    "  x, w, z, out = cache\n",
+    "  \n",
+    "  # Use values in cache to compute derivatives\n",
+    "  dx = # Derivative of loss with respect to x\n",
+    "  dw = # Derivative of loss with respect to w\n",
+    "  \n",
+    "  return dx, dw\n",
+    "```\n",
+    "\n",
+    "After implementing a bunch of layers this way, we will be able to easily combine them to build classifiers with different architectures."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "649895ab",
+   "metadata": {
+    "id": "649895ab"
+   },
+   "source": [
+    "# Affine layer: forward"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "03c584b4",
+   "metadata": {
+    "id": "03c584b4"
+   },
+   "outputs": [],
+   "source": [
+    "def affine_forward(x, w, b):\n",
+    "    \"\"\"\n",
+    "    Computes the forward pass for an affine (fully-connected) layer.\n",
+    "\n",
+    "    The input x has shape (N, d_1, ..., d_k) and contains a minibatch of N\n",
+    "    examples, where each example x[i] has shape (d_1, ..., d_k). We will\n",
+    "    reshape each input into a vector of dimension D = d_1 * ... * d_k, and\n",
+    "    then transform it to an output vector of dimension M.\n",
+    "\n",
+    "    Inputs:\n",
+    "    - x: A numpy array containing input data, of shape (N, d_1, ..., d_k)\n",
+    "    - w: A numpy array of weights, of shape (D, M)\n",
+    "    - b: A numpy array of biases, of shape (M,)\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - out: output, of shape (N, M)\n",
+    "    - cache: (x, w, b)\n",
+    "    \"\"\"\n",
+    "\n",
+    "    N = x.shape[0]\n",
+    "    D,M = w.shape\n",
+    "    \n",
+    "    input_vectors = x.reshape(N,D)\n",
+    "    \n",
+    "    out = np.matmul(input_vectors,w) + b\n",
+    "    \n",
+    "    return out, (x, w, b)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e64b312",
+   "metadata": {
+    "id": "8e64b312"
+   },
+   "source": [
+    "# Affine layer: backward"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e61d5b9c",
+   "metadata": {
+    "id": "e61d5b9c"
+   },
+   "outputs": [],
+   "source": [
+    "def affine_backward(dout, cache):\n",
+    "    \"\"\"\n",
+    "    Computes the backward pass for an affine layer.\n",
+    "\n",
+    "    Inputs:\n",
+    "    - dout: Upstream derivative, of shape (N, M)\n",
+    "    - cache: Tuple of:\n",
+    "      - x: Input data, of shape (N, d_1, ... d_k)\n",
+    "      - w: Weights, of shape (D, M)\n",
+    "      - b: Biases, of shape (M,)\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - dx: Gradient with respect to x, of shape (N, d1, ..., d_k)\n",
+    "    - dw: Gradient with respect to w, of shape (D, M)\n",
+    "    - db: Gradient with respect to b, of shape (M,)\n",
+    "    \"\"\"    \n",
+    "    x,w,b = cache\n",
+    "    \n",
+    "    \n",
+    "    N = x.shape[0]\n",
+    "    D,M = w.shape\n",
+    "    \n",
+    "    dx = np.matmul(dout,w.transpose()).reshape(x.shape)\n",
+    "    dw = np.matmul(x.reshape(N,D).transpose(),dout)\n",
+    "    db = np.sum(dout, axis=0)\n",
+    "    \n",
+    "    \n",
+    "    return dx,dw,db"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "af5910d2",
+   "metadata": {
+    "id": "af5910d2"
+   },
+   "source": [
+    "# ReLU activation: forward"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "c537098f",
+   "metadata": {
+    "id": "c537098f"
+   },
+   "outputs": [],
+   "source": [
+    "def relu_forward(x):\n",
+    "    \"\"\"\n",
+    "    Computes the forward pass for a layer of rectified linear units (ReLUs).\n",
+    "\n",
+    "    Input:\n",
+    "    - x: Inputs, of any shape\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - out: Output, of the same shape as x\n",
+    "    - cache: x\n",
+    "    \"\"\"\n",
+    "    return np.maximum(x,0),x"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6171f37c",
+   "metadata": {
+    "id": "6171f37c"
+   },
+   "source": [
+    "# ReLU activation: backward"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3187da88",
+   "metadata": {
+    "id": "3187da88"
+   },
+   "outputs": [],
+   "source": [
+    "def relu_backward(dout, cache):\n",
+    "    \"\"\"\n",
+    "    Computes the backward pass for a layer of rectified linear units (ReLUs).\n",
+    "\n",
+    "    Input:\n",
+    "    - dout: Upstream derivatives, of any shape\n",
+    "    - cache: Input x, of same shape as dout\n",
+    "\n",
+    "    Returns:\n",
+    "    - dx: Gradient with respect to x\n",
+    "    \"\"\"\n",
+    "    dr = cache\n",
+    "    dr[dr<=0] = 0\n",
+    "    dr[dr>0] = 1\n",
+    "    \n",
+    "    return np.multiply(dr,dout)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b0f2e4d2",
+   "metadata": {
+    "id": "b0f2e4d2"
+   },
+   "source": [
+    "# Sigmoid activation: forward"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "872854b0",
+   "metadata": {
+    "id": "872854b0"
+   },
+   "outputs": [],
+   "source": [
+    "def sigmoid_forward(x):\n",
+    "    \"\"\"\n",
+    "    Computes the forward pass for a layer of Sigmoid.\n",
+    "\n",
+    "    Input:\n",
+    "    - x: Inputs, of any shape\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - out: Output, of the same shape as x\n",
+    "    - cache: x\n",
+    "    \"\"\"\n",
+    "\n",
+    "    out = np.divide(np.exp(x), np.exp(x) + 1)\n",
+    "    return out, x"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9aa4e6a8",
+   "metadata": {
+    "id": "9aa4e6a8"
+   },
+   "source": [
+    "# Sigmoid activation: backward"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "fe527984",
+   "metadata": {
+    "id": "fe527984"
+   },
+   "outputs": [],
+   "source": [
+    "def sigmoid_backward(dout, cache):\n",
+    "    \"\"\"\n",
+    "    Computes the backward pass for a layer of Sigmoid.\n",
+    "\n",
+    "    Input:\n",
+    "    - dout: Upstream derivatives, of any shape\n",
+    "    - cache: Input x, of same shape as dout\n",
+    "\n",
+    "    Returns:\n",
+    "    - dx: Gradient with respect to x\n",
+    "    \"\"\"\n",
+    "    out,_ = sigmoid_forward(cache)\n",
+    "    ds = out * (1-out)\n",
+    "    \n",
+    "    return np.multiply(ds,dout)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1eb8d7a7",
+   "metadata": {
+    "id": "1eb8d7a7",
+    "tags": []
+   },
+   "source": [
+    "# \"Sandwich\" layers\n",
+    "There are some common patterns of layers that are frequently used in neural nets. For example, affine layers are frequently followed by a ReLU nonlinearity.here is the Implementation of the forward and backward pass for the affine layer followed by a ReLU nonlinearity in the `affine_relu_forward` and `affine_relu_backward` functions. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7283bd3d",
+   "metadata": {
+    "id": "7283bd3d"
+   },
+   "outputs": [],
+   "source": [
+    "def affine_relu_forward(x, w, b):\n",
+    "    \"\"\"\n",
+    "    Convenience layer that performs an affine transform followed by a ReLU\n",
+    "\n",
+    "    Inputs:\n",
+    "    - x: Input to the affine layer\n",
+    "    - w, b: Weights for the affine layer\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - out: Output from the ReLU\n",
+    "    - cache: Object to give to the backward pass\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    affine_out, affine_cache = affine_forward(x, w, b)\n",
+    "    \n",
+    "    relu_out, relu_cache = relu_forward(affine_out)\n",
+    "    \n",
+    "    return relu_out, (*affine_cache,relu_cache)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "00e27852",
+   "metadata": {
+    "id": "00e27852"
+   },
+   "outputs": [],
+   "source": [
+    "def affine_relu_backward(dout, cache):\n",
+    "    \"\"\"\n",
+    "    Backward pass for the affine-relu convenience layer\n",
+    "    \n",
+    "    Inputs:\n",
+    "    - dout: Upstream derivatives, of any shape\n",
+    "    - cache: (fc_cache, relu_cache)\n",
+    "      \n",
+    "    Returns a tuple of:\n",
+    "    - dx: Gradient with respect to x\n",
+    "    - dw: Gradient with respect to w\n",
+    "    - db: Gradient with respect to b\n",
+    "    \"\"\"\n",
+    "    x, w, b, relu_input = cache\n",
+    "    \n",
+    "    relu_backward_out = relu_backward(dout, relu_input)\n",
+    "    dx, dw, db = affine_backward(relu_backward_out, (x, w, b))\n",
+    "    \n",
+    "    return dx, dw, db"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0bd6b07f",
+   "metadata": {
+    "id": "0bd6b07f"
+   },
+   "source": [
+    "# Batch Normalization: Forward Pass\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7ae14e5d",
+   "metadata": {
+    "id": "7ae14e5d"
+   },
+   "outputs": [],
+   "source": [
+    "def batchnorm_forward(x, gamma, beta, bn_param):\n",
+    "    \"\"\"Forward pass for batch normalization.\n",
+    "\n",
+    "    During training the sample mean and (uncorrected) sample variance are\n",
+    "    computed from minibatch statistics and used to normalize the incoming data.\n",
+    "    During training we also keep an exponentially decaying running mean of the\n",
+    "    mean and variance of each feature, and these averages are used to normalize\n",
+    "    data at test-time.\n",
+    "\n",
+    "    At each timestep we update the running averages for mean and variance using\n",
+    "    an exponential decay based on the momentum parameter:\n",
+    "\n",
+    "    running_mean = momentum * running_mean + (1 - momentum) * sample_mean\n",
+    "    running_var = momentum * running_var + (1 - momentum) * sample_var\n",
+    "\n",
+    "    Input:\n",
+    "    - x: Data of shape (N, D)\n",
+    "    - gamma: Scale parameter of shape (D,)\n",
+    "    - beta: Shift paremeter of shape (D,)\n",
+    "    - bn_param: Dictionary with the following keys:\n",
+    "      - mode: 'train' or 'test'; required\n",
+    "      - eps: Constant for numeric stability\n",
+    "      - momentum: Constant for running mean / variance.\n",
+    "      - running_mean: Array of shape (D,) giving running mean of features\n",
+    "      - running_var Array of shape (D,) giving running variance of features\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - out: of shape (N, D)\n",
+    "    - cache: A tuple of values needed in the backward pass\n",
+    "    \"\"\"\n",
+    "    mode = bn_param[\"mode\"]\n",
+    "    eps = bn_param.get(\"eps\", 1e-5)\n",
+    "    momentum = bn_param.get(\"momentum\", 0.9)\n",
+    "\n",
+    "    N, D = x.shape\n",
+    "    running_mean = bn_param.get(\"running_mean\", np.zeros(D, dtype=x.dtype))\n",
+    "    running_var = bn_param.get(\"running_var\", np.zeros(D, dtype=x.dtype))\n",
+    "\n",
+    "    out, cache = None, None\n",
+    "    if mode == \"train\":\n",
+    "        data_mean = np.mean(x, axis=0)\n",
+    "        data_var = np.var(x, axis=0)\n",
+    "        \n",
+    "        running_mean = momentum * running_mean + (1 - momentum) * data_mean\n",
+    "        running_var = momentum * running_var + (1 - momentum) * data_var\n",
+    "        \n",
+    "        normilized_data = (x - data_mean) / np.sqrt(data_var + eps)\n",
+    "        out = normilized_data * gamma + beta\n",
+    "        cache = (x, gamma, beta, bn_param, normilized_data)\n",
+    "\n",
+    "    elif mode == \"test\":\n",
+    "\n",
+    "        normilized_data = (x - running_mean) / np.sqrt(running_var + eps)\n",
+    "        out = normilized_data * gamma + beta\n",
+    "        cache = (x, gamma, beta, bn_param, normilized_data)\n",
+    "\n",
+    "    else:\n",
+    "        raise ValueError('Invalid forward batchnorm mode \"%s\"' % mode)\n",
+    "\n",
+    "    bn_param[\"running_mean\"] = running_mean\n",
+    "    bn_param[\"running_var\"] = running_var\n",
+    "\n",
+    "    return out, cache"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "07719acb",
+   "metadata": {
+    "id": "07719acb"
+   },
+   "source": [
+    "# Batch Normalization: Backward Pass\n",
+    "Now here is the implementation of the backward pass for batch normalization in the function `batchnorm_backward`.\n",
+    "\n",
+    "In the forward pass, given a set of inputs $X=\\begin{bmatrix}x_1\\\\x_2\\\\...\\\\x_N\\end{bmatrix}$, \n",
+    "\n",
+    "we first calculate the mean $\\mu$ and variance $var$.\n",
+    "With $\\mu$ and $var$ calculated, we can calculate the standard deviation $\\sigma$  and normalized data $Y$.\n",
+    "The equations and graph illustration below describe the computation ($y_i$ is the i-th element of the vector $Y$).\n",
+    "\n",
+    "\\begin{align}\n",
+    "& \\mu=\\frac{1}{N}\\sum_{k=1}^N x_k  &  var=\\frac{1}{N}\\sum_{k=1}^N (x_k-\\mu)^2 \\\\\n",
+    "& \\sigma=\\sqrt{v+\\epsilon}         &  y_i=\\frac{x_i-\\mu}{\\sigma}\n",
+    "\\end{align}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "06afd7ac",
+   "metadata": {
+    "id": "06afd7ac"
+   },
+   "source": [
+    "<img src=\"https://kratzert.github.io/images/bn_backpass/bn_algorithm.PNG\">\n",
+    "\n",
+    "---\n",
+    "\n",
+    "\n",
+    "<img src=\"https://kratzert.github.io/images/bn_backpass/BNcircuit.png\">\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "07b2bf8c",
+   "metadata": {
+    "id": "07b2bf8c"
+   },
+   "outputs": [],
+   "source": [
+    "def batchnorm_backward(dout, cache):\n",
+    "    \"\"\"Backward pass for batch normalization.\n",
+    "\n",
+    "    For this implementation, you should write out a computation graph for\n",
+    "    batch normalization on paper and propagate gradients backward through\n",
+    "    intermediate nodes.\n",
+    "\n",
+    "    Inputs:\n",
+    "    - dout: Upstream derivatives, of shape (N, D)\n",
+    "    - cache: Variable of intermediates from batchnorm_forward.\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - dx: Gradient with respect to inputs x, of shape (N, D)\n",
+    "    - dgamma: Gradient with respect to scale parameter gamma, of shape (D,)\n",
+    "    - dbeta: Gradient with respect to shift parameter beta, of shape (D,)\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    x, gamma, beta, bn_param, normilized_data = cache\n",
+    "    eps = bn_param.get(\"eps\", 1e-5)\n",
+    "    dbeta = np.sum(dout, axis=0)\n",
+    "    dgamma = np.multiply(normilized_data, dout).sum(axis=0)\n",
+    "    \n",
+    "    mean = np.mean(x, axis=0)\n",
+    "    var = np.var(x, axis=0)\n",
+    "    std = np.sqrt(var+eps)\n",
+    "    \n",
+    "    n,d = dout.shape\n",
+    "    \n",
+    "    coef = gamma * dout    \n",
+    "    \n",
+    "    d_isigma = np.sum(coef * (x-mean), axis=0)\n",
+    "    dxmu1 = coef / std\n",
+    "\n",
+    "  \n",
+    "    dsigma = -1. /(std**2) * d_isigma\n",
+    "\n",
+    "  \n",
+    "    dvar = 0.5 * 1 /std * dsigma\n",
+    "\n",
+    "  \n",
+    "    dsq = 1 /n * np.ones((n,d)) * dvar\n",
+    "\n",
+    "  \n",
+    "    dxmu2 = 2 * (x - mean) * dsq\n",
+    "\n",
+    "    \n",
+    "    dx1 = (dxmu1 + dxmu2)\n",
+    "    dmu = -1 * np.sum(dxmu1+dxmu2, axis=0)\n",
+    "\n",
+    "    \n",
+    "    dx2 = 1. /n * np.ones((n,d)) * dmu\n",
+    "\n",
+    "    \n",
+    "    dx = dx1 + dx2\n",
+    "    \n",
+    "    \n",
+    "    return dx,dgamma,dbeta"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a9227f7e",
+   "metadata": {
+    "id": "a9227f7e"
+   },
+   "source": [
+    "# Loss layer: Softmax"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "e99a83c5",
+   "metadata": {
+    "id": "e99a83c5"
+   },
+   "outputs": [],
+   "source": [
+    "def softmax_loss(x, y):\n",
+    "    \"\"\"\n",
+    "    Computes the loss and gradient for softmax classification.\n",
+    "\n",
+    "    Inputs:\n",
+    "    - x: Input data, of shape (N, C) where x[i, j] is the score for the jth\n",
+    "      class for the ith input.\n",
+    "    - y: Vector of labels, of shape (N,) where y[i] is the label for x[i] and\n",
+    "      0 <= y[i] < C\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - loss: Scalar giving the loss\n",
+    "    - dx: Gradient of the loss with respect to x\n",
+    "    \"\"\"\n",
+    "\n",
+    "    n = y.shape[0]\n",
+    "    p = (np.exp(x).T / np.sum(np.exp(x),axis=1)).T\n",
+    "    log_likelihood = -np.log(p[range(n),y])\n",
+    "    loss = np.sum(log_likelihood) / n\n",
+    "    \n",
+    "    p[range(n),y] -= 1\n",
+    "    dx = p/n\n",
+    "    \n",
+    "    return loss,dx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "31d4492a",
+   "metadata": {
+    "id": "31d4492a"
+   },
+   "source": [
+    "# Loss layer: MSE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "92f5cdd9",
+   "metadata": {
+    "id": "92f5cdd9"
+   },
+   "outputs": [],
+   "source": [
+    "def mse_loss(x, y):\n",
+    "    \"\"\"\n",
+    "    Computes the loss and gradient for MSE loss.\n",
+    "\n",
+    "    Inputs:\n",
+    "    - x: Input data, of shape (N,) where x[i] is the predicted vector for \n",
+    "        the ith input.\n",
+    "    - y: Vector of target values, of shape (N,) where y[i] is the target value\n",
+    "        for the ith input.\n",
+    "\n",
+    "    Returns a tuple of:\n",
+    "    - loss: Scalar giving the loss\n",
+    "    - dx: Gradient of the loss with respect to x\n",
+    "    \"\"\"\n",
+    "    n = x.shape[0]\n",
+    "    \n",
+    "    x = x.flatten()\n",
+    "    y = y.flatten()\n",
+    "    \n",
+    "    MSE = ((y - x)**2).sum() / n\n",
+    "    \n",
+    "    dx = 2 * (x-y) / n\n",
+    "    \n",
+    "    return MSE,dx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71a7bb75",
+   "metadata": {
+    "id": "71a7bb75"
+   },
+   "source": [
+    "# Multi-Layer Fully Connected Network"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ffd460d2",
+   "metadata": {
+    "id": "ffd460d2"
+   },
+   "outputs": [],
+   "source": [
+    "class FullyConnectedNet(object):\n",
+    "    \"\"\"Class for a multi-layer fully connected neural network.\n",
+    "\n",
+    "    Network contains an arbitrary number of hidden layers, ReLU nonlinearities,\n",
+    "    and a softmax loss function for a classification problem or the MSE loss function for \n",
+    "    a regression problem. This will also implement batch normalization as an option. \n",
+    "    For a network with L layers, the architecture will be\n",
+    "\n",
+    "    {affine - [batchnorm] - relu} x (L - 1) - affine - softmax/mse\n",
+    "\n",
+    "    where batch normalization is optional in each layer and the {...} block is\n",
+    "    repeated L - 1 times.\n",
+    "\n",
+    "    Learnable parameters are stored in the self.params dictionary and will be learned\n",
+    "    using the Solver class.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        category,\n",
+    "        hidden_dims,\n",
+    "        normalization,\n",
+    "        input_dim=784,\n",
+    "        output_dim=10,\n",
+    "        reg=0.0,\n",
+    "        weight_scale=1e-2,\n",
+    "        dtype=np.float32,\n",
+    "    ):\n",
+    "        \"\"\"Initialize a new FullyConnectedNet.\n",
+    "\n",
+    "        Inputs:\n",
+    "        - category: The type of the problem. Valid values are \"classification\",\n",
+    "            \"regression\".\n",
+    "        - hidden_dims: A list of integers giving the size of each hidden layer.\n",
+    "        - normalization: A list of booleans which shows that we have batch \n",
+    "            normalization after the affine layer.\n",
+    "        - input_dim: An integer giving the size of the input.\n",
+    "        - output_dim: An integer giving the number of classes to classify. It\n",
+    "            is 1 for a regression problem.\n",
+    "        - reg: Scalar giving L2 regularization strength.\n",
+    "        - weight_scale: Scalar giving the standard deviation for random\n",
+    "            initialization of the weights.\n",
+    "        - dtype: A numpy datatype object; all computations will be performed using\n",
+    "            this datatype. float32 is faster but less accurate, so you should use\n",
+    "            float64 for numeric gradient checking.\n",
+    "        \"\"\"\n",
+    "        self.category = category\n",
+    "        self.normalization = normalization\n",
+    "        self.reg = reg\n",
+    "        self.num_layers = 1 + len(hidden_dims)\n",
+    "        self.dtype = dtype\n",
+    "        self.params = {}\n",
+    "        \n",
+    "        last_no_number = input_dim\n",
+    "        \n",
+    "        for i in range(len(hidden_dims)):\n",
+    "            weight_key = 'w' + str(i+1)\n",
+    "            bias_key = 'b' + str(i+1)\n",
+    "            no_node = hidden_dims[i]\n",
+    "            \n",
+    "            weights = np.random.normal(0, weight_scale, size=(last_no_number, no_node))\n",
+    "            biases = np.zeros(no_node)\n",
+    "            \n",
+    "            last_no_number = no_node\n",
+    "            \n",
+    "            self.params[weight_key] = weights\n",
+    "            self.params[bias_key] = biases\n",
+    "            \n",
+    "            if normalization[i]:\n",
+    "                gamma_key = 'gamma' + str(i+1)\n",
+    "                beta_key = 'beta' + str(i+1)\n",
+    "                \n",
+    "                self.params[gamma_key] = np.ones(no_node)\n",
+    "                self.params[beta_key] = np.zeros(no_node)\n",
+    "        \n",
+    "        weight_key = 'w' + str(self.num_layers)\n",
+    "        bias_key = 'b' + str(self.num_layers)\n",
+    "        \n",
+    "        weights = np.random.normal(0, weight_scale, size=(last_no_number, output_dim))\n",
+    "        biases = np.zeros(output_dim)\n",
+    "            \n",
+    "        self.params[weight_key] = weights\n",
+    "        self.params[bias_key] = biases\n",
+    "\n",
+    "        # With batch normalization we need to keep track of running means and\n",
+    "        # variances, so we need to pass a special bn_param object to each batch\n",
+    "        # normalization layer. You should pass self.bn_params[0] to the forward pass\n",
+    "        # of the first batch normalization layer, self.bn_params[1] to the forward\n",
+    "        # pass of the second batch normalization layer, etc.\n",
+    "\n",
+    "        self.bn_params = [{\"mode\": \"train\"} for i in range(self.num_layers - 1)]\n",
+    "\n",
+    "        # Cast all parameters to the correct datatype.\n",
+    "        for k, v in self.params.items():\n",
+    "            self.params[k] = v.astype(dtype)\n",
+    "\n",
+    "    def loss(self, X, y=None):\n",
+    "        \"\"\"Compute loss and gradient for the fully connected net.\n",
+    "        \n",
+    "        Inputs:\n",
+    "        - X: Array of input data of shape (N, d_1, ..., d_k)\n",
+    "        - y: Array of labels / target values, of shape (N,). y[i] gives the \n",
+    "            label / target value for X[i].\n",
+    "\n",
+    "        Returns:\n",
+    "        If y is None, then run a test-time forward pass of the model and return\n",
+    "        scores for a classification problem or the predicted_values for \n",
+    "        a regression problem:\n",
+    "        - out: Array of shape (N, C) / (N, ) giving classification scores / predicted values, where \n",
+    "        scores[i, c] is the classification score for X[i] and class c / predicted_values[i]\n",
+    "        is the predicted value for X[i].\n",
+    "            \n",
+    "\n",
+    "        If y is not None, then run a training-time forward and backward pass and\n",
+    "        return a tuple of:\n",
+    "        - loss: Scalar value giving the loss\n",
+    "        - grads: Dictionary with the same keys as self.params, mapping parameter\n",
+    "            names to gradients of the loss with respect to those parameters.\n",
+    "        \"\"\"\n",
+    "        X = X.astype(self.dtype)\n",
+    "        mode = \"test\" if y is None else \"train\"\n",
+    "\n",
+    "        # Set train/test mode for batchnorm params since they\n",
+    "        # behave differently during training and testing.\n",
+    "        for bn_param in self.bn_params:\n",
+    "            bn_param[\"mode\"] = mode\n",
+    "\n",
+    "        cache_list = list()\n",
+    "        data = X\n",
+    "        for i in range(self.num_layers - 1):\n",
+    "            \n",
+    "            cache_list.append(dict())\n",
+    "            \n",
+    "            weights = self.params['w'+str(i+1)]\n",
+    "            biases = self.params['b'+str(i+1)]\n",
+    "            \n",
+    "            data, affine_cache = affine_forward(data, weights, biases)\n",
+    "            \n",
+    "            cache_list[i][\"affine_cache\"] = affine_cache\n",
+    "            \n",
+    "            if self.normalization[i]:\n",
+    "                gamma = self.params['gamma' + str(i+1)]\n",
+    "                beta = self.params['beta' + str(i+1)]\n",
+    "                data, batch_cache = batchnorm_forward(data, gamma, beta, self.bn_params[i])\n",
+    "                \n",
+    "                cache_list[i][\"batch_cache\"] = batch_cache\n",
+    "                \n",
+    "            data, relu_cache = relu_forward(data)\n",
+    "            cache_list[i][\"relu_cache\"] = relu_cache\n",
+    "        \n",
+    "        \n",
+    "        weight_key = 'w' + str(self.num_layers)\n",
+    "        bias_key = 'b' + str(self.num_layers)\n",
+    "            \n",
+    "        weights = self.params[weight_key] \n",
+    "        biases = self.params[bias_key]\n",
+    "        \n",
+    "        out, affine_cache = affine_forward(data, weights, biases)\n",
+    "        cache_list.append(dict())\n",
+    "        \n",
+    "        cache_list[-1][\"affine_cache\"] = affine_cache   \n",
+    "\n",
+    "        # If test mode return early.\n",
+    "        if mode == \"test\":\n",
+    "            return out\n",
+    "            \n",
+    "        loss, grads = 0.0, {}\n",
+    "      \n",
+    "        if self.category == 'classification':\n",
+    "            loss, loss_grad = softmax_loss(out, y)\n",
+    "        else:\n",
+    "            loss, loss_grad = mse_loss(out, y)\n",
+    "            loss_grad = np.reshape(loss_grad, (-1, 1))\n",
+    "            \n",
+    "        \n",
+    "        for i in range(self.num_layers):\n",
+    "            w = self.params['w'+str(i+1)]\n",
+    "            loss += 0.5 * self.reg * np.sum(w * w) \n",
+    "\n",
+    "        # calculate gradients\n",
+    "        dout = loss_grad\n",
+    "        affine_cache = cache_list[-1][\"affine_cache\"]\n",
+    "        \n",
+    "        dout, dw, db = affine_backward(dout, affine_cache)\n",
+    "        grads['w' + str(self.num_layers)] = dw + self.reg * self.params['w' + str(self.num_layers)]\n",
+    "        grads['b' + str(self.num_layers)] = db\n",
+    "        \n",
+    "        \n",
+    "        for i in range(self.num_layers - 2, -1, -1):\n",
+    "            relu_cache = cache_list[i][\"relu_cache\"]\n",
+    "            dx = relu_backward(dout, relu_cache)\n",
+    "            \n",
+    "            if self.normalization[i]:\n",
+    "                batch_cache = cache_list[i][\"batch_cache\"]\n",
+    "                dx,dgamma,dbeta = batchnorm_backward(dx, batch_cache)\n",
+    "                grads['gamma'+str(i+1)] = dgamma\n",
+    "                grads['beta' +str(i+1)] = dbeta\n",
+    "            \n",
+    "            affine_cache = cache_list[i][\"affine_cache\"]\n",
+    "            dx, dw, db = affine_backward(dx, affine_cache)\n",
+    "                \n",
+    "            grads['w' + str(i + 1)] = dw + self.reg * self.params['w' + str(i + 1)]\n",
+    "            grads['b' + str(i + 1)] = db\n",
+    "            dout = dx\n",
+    "            \n",
+    "        return loss, grads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6042ddcf",
+   "metadata": {
+    "id": "6042ddcf"
+   },
+   "source": [
+    "## SGD+Momentum\n",
+    "Stochastic gradient descent with momentum is a widely used update rule that tends to make deep networks converge faster than vanilla stochastic gradient descent.\n",
+    "\n",
+    "Here is the implementation of the SGD+momentum update rule in the function `sgd_momentum`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "2e678506",
+   "metadata": {
+    "id": "2e678506"
+   },
+   "outputs": [],
+   "source": [
+    "def sgd_momentum(w, dw, config=None):\n",
+    "    \"\"\"\n",
+    "    Performs stochastic gradient descent with momentum.\n",
+    "    Inputs:\n",
+    "    - w: A numpy array giving the current weights.\n",
+    "    - dw: A numpy array of the same shape as w giving the gradient of the\n",
+    "    loss with respect to w.\n",
+    "    - config: A dictionary containing hyperparameter values such as learning\n",
+    "    rate, momentum.\n",
+    "\n",
+    "    Returns:\n",
+    "      - next_w: The next point after the update.\n",
+    "      - config: The config dictionary to be passed to the next iteration of the\n",
+    "        update rule.\n",
+    "\n",
+    "    config format:\n",
+    "    - learning_rate: Scalar learning rate.\n",
+    "    - momentum: Scalar between 0 and 1 giving the momentum value.\n",
+    "      Setting momentum = 0 reduces sgd_momentum to stochastic gradient descent.\n",
+    "    - velocity: A numpy array of the same shape as w and dw used to store a\n",
+    "      moving average of the gradients.\n",
+    "    \"\"\"\n",
+    "    if config is None:\n",
+    "        config = {}\n",
+    "    config.setdefault(\"learning_rate\", 1e-2)\n",
+    "    config.setdefault(\"momentum\", 0.9)\n",
+    "    v = config.get(\"velocity\", np.zeros_like(w))\n",
+    "\n",
+    "    next_w = None\n",
+    "\n",
+    "    v = config['momentum'] * v - config['learning_rate'] * dw\n",
+    "    next_w = w + v\n",
+    "\n",
+    "    config[\"velocity\"] = v\n",
+    "\n",
+    "    return next_w, config"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Solver"
+   ],
+   "metadata": {
+    "id": "7ztCBKvZLtro"
+   },
+   "id": "7ztCBKvZLtro"
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "class Solver(object):\n",
+    "    \"\"\"\n",
+    "    A Solver encapsulates all the logic necessary for training classification\n",
+    "    and regression models. The Solver performs stochastic gradient descent \n",
+    "    with momentum.\n",
+    "\n",
+    "    The solver accepts both training and validation data and labels or\n",
+    "    target values, so it can periodically check accuracy on both training\n",
+    "    and validation data to watch out for overfitting.\n",
+    "\n",
+    "    To train a model, you will first construct a Solver instance, passing the\n",
+    "    model, dataset, and various options (learning rate, batch size, etc.) to the\n",
+    "    constructor. You will then call the train() method to run the optimization\n",
+    "    procedure and train the model.\n",
+    "\n",
+    "    After the train() method returns, model.params will contain the parameters\n",
+    "    that performed best on the validation set over the course of training.\n",
+    "    In addition, the instance variable solver.loss_history will contain a list\n",
+    "    of all losses encountered during training and the instance variables\n",
+    "    solver.train_acc_history and solver.val_acc_history will be lists of the\n",
+    "    accuracies of the model on the training and validation set at each epoch.\n",
+    "\n",
+    "    Example usage might look something like this:\n",
+    "\n",
+    "    data = {\n",
+    "      'X_train': # training data\n",
+    "      'y_train': # training labels\n",
+    "      'X_val': # validation data\n",
+    "      'y_val': # validation labels\n",
+    "    }\n",
+    "    model = MyAwesomeModel(hidden_size=100, reg=10)\n",
+    "    solver = Solver(model, data,\n",
+    "                    update_rule=sgd_momentum,\n",
+    "                    optim_config={\n",
+    "                      'learning_rate': 1e-4,\n",
+    "                    },\n",
+    "                    lr_decay=0.95,\n",
+    "                    num_epochs=5, batch_size=200,\n",
+    "                    print_every=100)\n",
+    "    solver.train()\n",
+    "\n",
+    "\n",
+    "    A Solver works on a model object that must conform to the following API:\n",
+    "\n",
+    "    - model.params must be a dictionary mapping string parameter names to numpy\n",
+    "      arrays containing parameter values.\n",
+    "\n",
+    "    - model.loss(X, y) must be a function that computes training-time loss and\n",
+    "      gradients, and test-time classification scores / target values, with the\n",
+    "      following inputs and outputs:\n",
+    "\n",
+    "      Inputs:\n",
+    "      - X: Array giving a minibatch of input data of shape (N, d_1, ..., d_k)\n",
+    "      - y: Array of labels, of shape (N,) giving labels for X where y[i] is the\n",
+    "        label for X[i].\n",
+    "\n",
+    "      Returns:\n",
+    "      If y is None, run a test-time forward pass and return:\n",
+    "      - out: Array of shape (N, C) / (N, ) giving classification scores / predicted values, where \n",
+    "        scores[i, c] is the classification score for X[i] and class c / predicted_values[i]\n",
+    "        is the predicted value for X[i].\n",
+    "\n",
+    "      If y is not None, run a training time forward and backward pass and\n",
+    "      return a tuple of:\n",
+    "      - loss: Scalar giving the loss\n",
+    "      - grads: Dictionary with the same keys as self.params mapping parameter\n",
+    "        names to gradients of the loss with respect to those parameters.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    def __init__(self, model, data, update_rule, **kwargs):\n",
+    "        \"\"\"\n",
+    "        Construct a new Solver instance.\n",
+    "\n",
+    "        Required arguments:\n",
+    "        - model: A model object conforming to the API described above\n",
+    "        - data: A dictionary of training and validation data containing:\n",
+    "          'X_train': Array, shape (N_train, d_1, ..., d_k) of training images\n",
+    "          'X_val': Array, shape (N_val, d_1, ..., d_k) of validation images\n",
+    "          'y_train': Array, shape (N_train,) of labels/target values for training images\n",
+    "          'y_val': Array, shape (N_val,) of labels/target values for validation images\n",
+    "        - update_rule: A update rule function.\n",
+    "          Default is 'sgd_momentum'.\n",
+    "\n",
+    "        Optional arguments:\n",
+    "        - optim_config: A dictionary containing hyperparameters that will be\n",
+    "          passed to the chosen update rule. Each update rule requires different\n",
+    "          hyperparameters but all update rules require a\n",
+    "          'learning_rate' parameter so that should always be present.\n",
+    "        - lr_decay: A scalar for learning rate decay; after each epoch the\n",
+    "          learning rate is multiplied by this value.\n",
+    "        - batch_size: Size of minibatches used to compute loss and gradient\n",
+    "          during training.\n",
+    "        - num_epochs: The number of epochs to run for during training.\n",
+    "        - print_every: Integer; training losses will be printed every\n",
+    "          print_every iteration.\n",
+    "        - verbose: Boolean; if set to false then no output will be printed\n",
+    "          during training.\n",
+    "        - num_train_samples: Number of training samples used to check training\n",
+    "          accuracy; default is 1000; set to None to use entire training set.\n",
+    "        - num_val_samples: Number of validation samples to use to check val\n",
+    "          accuracy; default is None, which uses the entire validation set.\n",
+    "        - checkpoint_name: If not None, then save model checkpoints here every\n",
+    "          epoch.\n",
+    "        \"\"\"\n",
+    "        self.model = model\n",
+    "        self.X_train = data[\"X_train\"]\n",
+    "        self.y_train = data[\"y_train\"]\n",
+    "        self.X_val = data[\"X_val\"]\n",
+    "        self.y_val = data[\"y_val\"]\n",
+    "        self.update_rule = update_rule\n",
+    "\n",
+    "        # Unpack keyword arguments\n",
+    "\n",
+    "        self.optim_config = kwargs.pop(\"optim_config\", {})\n",
+    "        self.lr_decay = kwargs.pop(\"lr_decay\", 1.0)\n",
+    "        self.batch_size = kwargs.pop(\"batch_size\", 100)\n",
+    "        self.num_epochs = kwargs.pop(\"num_epochs\", 10)\n",
+    "        self.num_train_samples = kwargs.pop(\"num_train_samples\", 1000)\n",
+    "        self.num_val_samples = kwargs.pop(\"num_val_samples\", None)\n",
+    "\n",
+    "        self.checkpoint_name = kwargs.pop(\"checkpoint_name\", None)\n",
+    "        self.print_every = kwargs.pop(\"print_every\", 10)\n",
+    "        self.verbose = kwargs.pop(\"verbose\", True)\n",
+    "\n",
+    "        # Throw an error if there are extra keyword arguments\n",
+    "        if len(kwargs) > 0:\n",
+    "            extra = \", \".join('\"%s\"' % k for k in list(kwargs.keys()))\n",
+    "            raise ValueError(\"Unrecognized arguments %s\" % extra)\n",
+    "\n",
+    "        self._reset()\n",
+    "\n",
+    "    def _reset(self):\n",
+    "        \"\"\"\n",
+    "        Set up some bookkeeping variables for optimization. Don't call this\n",
+    "        manually.\n",
+    "        \"\"\"\n",
+    "        # Set up some variables for bookkeeping\n",
+    "        self.epoch = 0\n",
+    "        self.best_val_acc = 0\n",
+    "        self.best_params = {}\n",
+    "        self.loss_history = []\n",
+    "        self.train_acc_history = []\n",
+    "        self.val_acc_history = []\n",
+    "\n",
+    "        # Make a deep copy of the optim_config for each parameter\n",
+    "        self.optim_configs = {}\n",
+    "        for p in self.model.params:\n",
+    "            d = {k: v for k, v in self.optim_config.items()}\n",
+    "            self.optim_configs[p] = d\n",
+    "\n",
+    "    def _step(self):\n",
+    "        \"\"\"\n",
+    "        Make a single gradient update. This is called by train() and should not\n",
+    "        be called manually.\n",
+    "        \"\"\"\n",
+    "        # Make a minibatch of training data\n",
+    "        num_train = self.X_train.shape[0]\n",
+    "        batch_mask = np.random.choice(num_train, self.batch_size)\n",
+    "        X_batch = self.X_train[batch_mask]\n",
+    "        y_batch = self.y_train[batch_mask]\n",
+    "\n",
+    "        # Compute loss and gradient\n",
+    "        loss, grads = self.model.loss(X_batch, y_batch)\n",
+    "        self.loss_history.append(loss)\n",
+    "\n",
+    "        # Perform a parameter update\n",
+    "        for p, w in self.model.params.items():\n",
+    "            dw = grads[p]\n",
+    "            config = self.optim_configs[p]\n",
+    "            next_w, next_config = self.update_rule(w, dw, config)\n",
+    "            self.model.params[p] = next_w\n",
+    "            self.optim_configs[p] = next_config\n",
+    "\n",
+    "    def _save_checkpoint(self):\n",
+    "        if self.checkpoint_name is None:\n",
+    "            return\n",
+    "        checkpoint = {\n",
+    "            \"model\": self.model,\n",
+    "            \"update_rule\": self.update_rule,\n",
+    "            \"lr_decay\": self.lr_decay,\n",
+    "            \"optim_config\": self.optim_config,\n",
+    "            \"batch_size\": self.batch_size,\n",
+    "            \"num_train_samples\": self.num_train_samples,\n",
+    "            \"num_val_samples\": self.num_val_samples,\n",
+    "            \"epoch\": self.epoch,\n",
+    "            \"loss_history\": self.loss_history,\n",
+    "            \"train_acc_history\": self.train_acc_history,\n",
+    "            \"val_acc_history\": self.val_acc_history,\n",
+    "        }\n",
+    "        filename = \"%s_epoch_%d.pkl\" % (self.checkpoint_name, self.epoch)\n",
+    "        if self.verbose:\n",
+    "            print('Saving checkpoint to \"%s\"' % filename)\n",
+    "        with open(filename, \"wb\") as f:\n",
+    "            pickle.dump(checkpoint, f)\n",
+    "\n",
+    "    def check_accuracy(self, X, y, num_samples=None, batch_size=100):\n",
+    "        \"\"\"\n",
+    "        Check accuracy of the model on the provided data.\n",
+    "\n",
+    "        Inputs:\n",
+    "        - X: Array of data, of shape (N, d_1, ..., d_k)\n",
+    "        - y: Array of labels / target values, of shape (N,)\n",
+    "        - num_samples: If not None, subsample the data and only test the model\n",
+    "          on num_samples datapoints.\n",
+    "        - batch_size: Split X and y into batches of this size to avoid using\n",
+    "          too much memory.\n",
+    "\n",
+    "        Returns:\n",
+    "        For a classification problem:\n",
+    "        - acc: Scalar giving the fraction of instances that were correctly\n",
+    "          classified by the model.\n",
+    "\n",
+    "        For a regression problem:\n",
+    "        - acc: Scalar giving the root-mean-square(RMS) error.\n",
+    "        \"\"\"\n",
+    "\n",
+    "        # Maybe subsample the data\n",
+    "        N = X.shape[0]\n",
+    "        if num_samples is not None and N > num_samples:\n",
+    "            mask = np.random.choice(N, num_samples)\n",
+    "            N = num_samples\n",
+    "            X = X[mask]\n",
+    "            y = y[mask]\n",
+    "\n",
+    "        # Compute predictions in batches\n",
+    "        num_batches = N // batch_size\n",
+    "        if N % batch_size != 0:\n",
+    "            num_batches += 1\n",
+    "        y_pred = []\n",
+    "        loss = 10\n",
+    "        for i in range(num_batches):\n",
+    "            start = i * batch_size\n",
+    "            end = (i + 1) * batch_size\n",
+    "            if self.model.category == \"classification\":\n",
+    "                scores = self.model.loss(X[start:end])\n",
+    "                y_pred.append(np.argmax(scores, axis=1))\n",
+    "            elif self.model.category == \"regression\":\n",
+    "                loss += batch_size * \\\n",
+    "                        self.model.loss(X[start:end], y[start:end])[0]\n",
+    "        acc = None\n",
+    "\n",
+    "        if self.model.category == \"classification\":\n",
+    "            y_pred = np.hstack(y_pred)\n",
+    "            acc = np.mean(y_pred == y)\n",
+    "        elif self.model.category == \"regression\":\n",
+    "            acc = np.sqrt(loss / N)\n",
+    "\n",
+    "        return acc\n",
+    "\n",
+    "    def train(self):\n",
+    "        \"\"\"\n",
+    "        Run optimization to train the model.\n",
+    "        \"\"\"\n",
+    "        num_train = self.X_train.shape[0]\n",
+    "        iterations_per_epoch = max(num_train // self.batch_size, 1)\n",
+    "        num_iterations = self.num_epochs * iterations_per_epoch\n",
+    "\n",
+    "        for t in range(num_iterations):\n",
+    "            self._step()\n",
+    "\n",
+    "            # Maybe print training loss\n",
+    "            if self.verbose and t % self.print_every == 0:\n",
+    "                print(\n",
+    "                    \"(Iteration %d / %d) loss: %f\"\n",
+    "                    % (t + 1, num_iterations, self.loss_history[-1])\n",
+    "                )\n",
+    "\n",
+    "            # At the end of every epoch, increment the epoch counter and decay\n",
+    "            # the learning rate.\n",
+    "            epoch_end = (t + 1) % iterations_per_epoch == 0\n",
+    "            if epoch_end:\n",
+    "                self.epoch += 1\n",
+    "                for k in self.optim_configs:\n",
+    "                    self.optim_configs[k][\"learning_rate\"] *= self.lr_decay\n",
+    "\n",
+    "            # Check train and val accuracy on the first iteration, the last\n",
+    "            # iteration, and at the end of each epoch.\n",
+    "            first_it = t == 0\n",
+    "            last_it = t == num_iterations - 1\n",
+    "            if first_it or last_it or epoch_end:\n",
+    "                train_acc = self.check_accuracy(\n",
+    "                    self.X_train, self.y_train, num_samples=self.num_train_samples\n",
+    "                )\n",
+    "                val_acc = self.check_accuracy(\n",
+    "                    self.X_val, self.y_val, num_samples=self.num_val_samples\n",
+    "                )\n",
+    "                self.train_acc_history.append(train_acc)\n",
+    "                self.val_acc_history.append(val_acc)\n",
+    "                self._save_checkpoint()\n",
+    "\n",
+    "                if self.verbose:\n",
+    "                    if self.model.category == \"classification\":\n",
+    "                        print(\n",
+    "                            \"(Epoch %d / %d) train acc: %f; val_acc: %f\"\n",
+    "                            % (self.epoch, self.num_epochs, train_acc, val_acc)\n",
+    "                        )\n",
+    "                    elif self.model.category == \"regression\":\n",
+    "                        print(\n",
+    "                            \"(Epoch %d / %d) train RMS error: %f; val RMS error: %f\"\n",
+    "                            % (self.epoch, self.num_epochs, train_acc, val_acc)\n",
+    "                        )\n",
+    "\n",
+    "                # Keep track of the best model\n",
+    "                if (self.model.category == \"classification\" and val_acc > self.best_val_acc) or (\n",
+    "                        self.model.category == \"regression\" and val_acc < self.best_val_acc):\n",
+    "                    self.best_val_acc = val_acc\n",
+    "                    self.best_params = {}\n",
+    "                    for k, v in self.model.params.items():\n",
+    "                        self.best_params[k] = v.copy()\n",
+    "\n",
+    "        # At the end of training swap the best params into the model\n",
+    "        self.model.params = self.best_params\n"
+   ],
+   "metadata": {
+    "id": "RExJ8OcdLp_I"
+   },
+   "id": "RExJ8OcdLp_I",
+   "execution_count": 17,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc30c93e",
+   "metadata": {
+    "id": "cc30c93e"
+   },
+   "source": [
+    "# MNIST\n",
+    "MNIST is a widely used dataset of handwritten digits that contains 60,000 handwritten digits for training a machine learning model and 10,000 handwritten digits for testing the model."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Load Data"
+   ],
+   "metadata": {
+    "id": "hWQwXBJTL6JZ"
+   },
+   "id": "hWQwXBJTL6JZ"
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "def get_MNIST_data(num_training=50000, num_validation=10000, num_test=10000):\n",
+    "    \"\"\"\n",
+    "    Load the MNIST dataset from disk and perform preprocessing to prepare\n",
+    "    it for the classification. \n",
+    "    \"\"\"\n",
+    "    # Load the raw MNIST data\n",
+    "    train_data = datasets.MNIST('./data', train=True, download=True)\n",
+    "    test_data = datasets.MNIST('./data', train=False, download=True)\n",
+    "\n",
+    "    X_train, y_train = np.array(train_data.data, dtype=float), np.array(\n",
+    "        train_data.targets, dtype=float)\n",
+    "    X_test, y_test = np.array(test_data.data, dtype=float), np.array(\n",
+    "        test_data.targets, dtype=float)\n",
+    "\n",
+    "    # subsample the data\n",
+    "    mask = list(range(num_training, num_training + num_validation))\n",
+    "    X_val = X_train[mask]\n",
+    "    y_val = y_train[mask]\n",
+    "    mask = list(range(num_training))\n",
+    "    X_train = X_train[mask]\n",
+    "    y_train = y_train[mask]\n",
+    "    mask = list(range(num_test))\n",
+    "    X_test = X_test[mask]\n",
+    "    y_test = y_test[mask]\n",
+    "\n",
+    "    # Preprocessing: reshape the image data into rows\n",
+    "    X_train = np.reshape(X_train, (X_train.shape[0], -1))\n",
+    "    X_val = np.reshape(X_val, (X_val.shape[0], -1))\n",
+    "    X_test = np.reshape(X_test, (X_test.shape[0], -1))\n",
+    "\n",
+    "    return X_train, y_train, X_val, y_val, X_test, y_test\n",
+    "\n",
+    "\n",
+    "def get_normalized_MNIST_data(X_train, X_val, X_test):\n",
+    "    # Normalize the data: subtract the mean image\n",
+    "    epsilon = 10 ** -6\n",
+    "    mean_image = np.mean(X_train, axis=0)\n",
+    "    std = np.std(X_train, axis=0) + epsilon\n",
+    "\n",
+    "    X_train -= mean_image\n",
+    "    X_val -= mean_image\n",
+    "    X_test -= mean_image\n",
+    "    return X_train / std , X_val / std , X_test / std\n"
+   ],
+   "metadata": {
+    "id": "29NgPfNaL-bD"
+   },
+   "id": "29NgPfNaL-bD",
+   "execution_count": 18,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "e3fa8400",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 527,
+     "referenced_widgets": [
+      "2d67ea1c85514b20a449bde440a6c08c",
+      "02fde3a6623b40c18456121c8db32679",
+      "d8f8cf98cb5c4bf091ddb96a89fd3c08",
+      "2df61380b2cb4a4aab14a2be10b40b65",
+      "8b5b19e7914d4e1cb4c90aa7a1dc9de6",
+      "2a483f0e5d6341ea9f416f9c8137c617",
+      "fdb6ed9208b84745aaf019d53476e525",
+      "11fdd7100d7b4c8cbf504baaeaf5c51e",
+      "1193bc936c494b8d8109bf86782dd3b0",
+      "1e5b0f36eea64a4da35af00e988b9e49",
+      "dcb7c33f7bd14077b4dfff6dfdd5127c",
+      "a141e34baf0145569026127549e12af2",
+      "e45f65c8a003410cba3c6ed3208265c5",
+      "fcc12dc7d49643069c024300329ffa3f",
+      "d4e61b124e094ea59b255a6eb890f765",
+      "f1d9c15b33824051afb387a15036ee54",
+      "76490141f1f8414480e072dad27ab735",
+      "aa80b7dbbcc344e5919f782119759987",
+      "af102305ab89423b99fff9f12de56be1",
+      "231b5c1465294e8ca7d92bbb8a1c35b3",
+      "366317e704dc4c5d85ebd86e1cb5e605",
+      "39aea92910fe4560b97bf7bcf40005d9",
+      "ce0c95134cc84d568c77519b33abbad4",
+      "24aad3dd0c254e65af983ef274644af9",
+      "c2f87b094ece4a9ab578d9c3a9a64261",
+      "2fb93bb1dc7b45fa81d977d417735986",
+      "2564d791dac44e00ad58bd3c22eaffd7",
+      "423464c848074c5f82af56686e0ed7a6",
+      "0c2b8d0da2ee47adabc870c2e20d2589",
+      "2f782d6343404904a7be6ae767ddc045",
+      "221cb124249b442e8562e7474867da4c",
+      "fc851dfec63748cd8b2f99bfdf0b5895",
+      "0e622b2f01e14ddf889a94830ba09411",
+      "967a0b6c4f3d49fdbba513957c2e3ef3",
+      "b2bae96fef44467c8bfe67bdd32da940",
+      "c308d86c6ec242fbb28785a5ca9aeec6",
+      "d506aea1cf9547dc8e063f97b96bd07c",
+      "2d8a041617fa438b9f3f614a02b54f42",
+      "4d473d2ad3fb495594bd880eabe7c1e5",
+      "27eab7d037f64833be94878e33e9eb14",
+      "b737736bdcba48ffb80f83a939b9c992",
+      "2710d61d180b49dfa2ac072efab2c8d1",
+      "170c9c6ae03741dea252dae56da56ec6",
+      "0b2d109241424cd79a55014fd618791d"
+     ]
+    },
+    "id": "e3fa8400",
+    "outputId": "043788c3-8e2c-4b0d-e560-f6aba8e7af0c"
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to ./data/MNIST/raw/train-images-idx3-ubyte.gz\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "  0%|          | 0/9912422 [00:00<?, ?it/s]"
+      ],
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "2d67ea1c85514b20a449bde440a6c08c"
+      }
+     },
+     "metadata": {}
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Extracting ./data/MNIST/raw/train-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
+      "\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to ./data/MNIST/raw/train-labels-idx1-ubyte.gz\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "  0%|          | 0/28881 [00:00<?, ?it/s]"
+      ],
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "a141e34baf0145569026127549e12af2"
+      }
+     },
+     "metadata": {}
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Extracting ./data/MNIST/raw/train-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
+      "\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw/t10k-images-idx3-ubyte.gz\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "  0%|          | 0/1648877 [00:00<?, ?it/s]"
+      ],
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "ce0c95134cc84d568c77519b33abbad4"
+      }
+     },
+     "metadata": {}
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Extracting ./data/MNIST/raw/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
+      "\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz\n",
+      "Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "  0%|          | 0/4542 [00:00<?, ?it/s]"
+      ],
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "967a0b6c4f3d49fdbba513957c2e3ef3"
+      }
+     },
+     "metadata": {}
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Extracting ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
+      "\n",
+      "Train data shape:  (50000, 784)\n",
+      "Train labels shape:  (50000,)\n",
+      "Validation data shape:  (10000, 784)\n",
+      "Validation labels shape:  (10000,)\n",
+      "Test data shape:  (10000, 784)\n",
+      "Test labels shape:  (10000,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "X_train, y_train, X_val, y_val, X_test, y_test = get_MNIST_data()\n",
+    "print('Train data shape: ', X_train.shape)\n",
+    "print('Train labels shape: ', y_train.shape)\n",
+    "print('Validation data shape: ', X_val.shape)\n",
+    "print('Validation labels shape: ', y_val.shape)\n",
+    "print('Test data shape: ', X_test.shape)\n",
+    "print('Test labels shape: ', y_test.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "1e15a728",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 476
+    },
+    "id": "1e15a728",
+    "outputId": "97ca6a99-f567-4fb0-b0da-030f92d3ebe3"
+   },
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 720x576 with 70 Axes>"
+      ],
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "source": [
+    "# Visualize some examples from the dataset.\n",
+    "# We show a few examples of training images from each class.\n",
+    "classes = list(range(10))\n",
+    "num_classes = len(classes)\n",
+    "samples_per_class = 7\n",
+    "for y, cls in enumerate(classes):\n",
+    "    idxs = np.flatnonzero(y_train == y)\n",
+    "    idxs = np.random.choice(idxs, samples_per_class, replace=False)\n",
+    "    for i, idx in enumerate(idxs):\n",
+    "        plt_idx = i * num_classes + y + 1\n",
+    "        plt.subplot(samples_per_class, num_classes, plt_idx)\n",
+    "        plt.imshow(X_train[idx].reshape((28, 28)))\n",
+    "        plt.axis('off')\n",
+    "        if i == 0:\n",
+    "            plt.title(cls)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ca6ad76a",
+   "metadata": {
+    "id": "ca6ad76a"
+   },
+   "source": [
+    "Data normalization is an important step which ensures that each input parameter has a similar data distribution. This makes convergence faster while training the network."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "ea87dfbb",
+   "metadata": {
+    "id": "ea87dfbb"
+   },
+   "outputs": [],
+   "source": [
+    "X_train, X_val, X_test = get_normalized_MNIST_data(X_train, X_val, X_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3ed0af35",
+   "metadata": {
+    "id": "3ed0af35"
+   },
+   "source": [
+    "# Train a Model!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "5d59d748",
+   "metadata": {
+    "id": "5d59d748",
+    "outputId": "0baa1b38-4f10-4066-9d0c-201432f7ff54",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "(Iteration 1 / 1250) loss: 2.306774\n",
+      "(Epoch 0 / 5) train acc: 0.084000; val_acc: 0.096800\n",
+      "(Iteration 101 / 1250) loss: 1.311712\n",
+      "(Iteration 201 / 1250) loss: 0.561714\n",
+      "(Epoch 1 / 5) train acc: 0.914000; val_acc: 0.937100\n",
+      "(Iteration 301 / 1250) loss: 0.320414\n",
+      "(Iteration 401 / 1250) loss: 0.206991\n",
+      "(Epoch 2 / 5) train acc: 0.976000; val_acc: 0.957500\n",
+      "(Iteration 501 / 1250) loss: 0.208070\n",
+      "(Iteration 601 / 1250) loss: 0.169237\n",
+      "(Iteration 701 / 1250) loss: 0.128945\n",
+      "(Epoch 3 / 5) train acc: 0.983000; val_acc: 0.963500\n",
+      "(Iteration 801 / 1250) loss: 0.125127\n",
+      "(Iteration 901 / 1250) loss: 0.100621\n",
+      "(Epoch 4 / 5) train acc: 0.984000; val_acc: 0.966200\n",
+      "(Iteration 1001 / 1250) loss: 0.098808\n",
+      "(Iteration 1101 / 1250) loss: 0.088913\n",
+      "(Iteration 1201 / 1250) loss: 0.088881\n",
+      "(Epoch 5 / 5) train acc: 0.983000; val_acc: 0.971400\n"
+     ]
+    }
+   ],
+   "source": [
+    "MNIST_best_model = None\n",
+    "\n",
+    "data = {\n",
+    "    'X_train': X_train,\n",
+    "    'y_train': y_train.astype(int),\n",
+    "    'X_val': X_val,\n",
+    "    'y_val': y_val.astype(int),\n",
+    "    'X_test': X_test,\n",
+    "    'y_test': y_test.astype(int)\n",
+    "    }\n",
+    "\n",
+    "model = FullyConnectedNet(\n",
+    "    'classification', \n",
+    "    [120, 100, 80],\n",
+    "    [False, True, True],\n",
+    "    dtype=np.float64\n",
+    ")\n",
+    "solver = Solver(model, data,\n",
+    "                update_rule=sgd_momentum,\n",
+    "                optim_config={\n",
+    "                  'learning_rate': 1e-3,\n",
+    "                },\n",
+    "                lr_decay=0.95,\n",
+    "                num_epochs=5, batch_size=200,\n",
+    "                print_every=100)\n",
+    "solver.train()\n",
+    "\n",
+    "MNIST_solver = solver\n",
+    "MNIST_best_model = model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "25f8a45b",
+   "metadata": {
+    "id": "25f8a45b",
+    "outputId": "a84fb9d0-eb6e-4e0b-c92d-386766e78392",
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 730
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 1080x864 with 2 Axes>"
+      ],
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "source": [
+    "# Visualize training loss and train / val accuracy\n",
+    "\n",
+    "plt.subplot(2, 1, 1)\n",
+    "plt.title('Training loss')\n",
+    "plt.plot(MNIST_solver.loss_history, 'o')\n",
+    "plt.xlabel('Iteration')\n",
+    "\n",
+    "plt.subplot(2, 1, 2)\n",
+    "plt.title('Accuracy')\n",
+    "plt.plot(MNIST_solver.train_acc_history, '-o', label='train')\n",
+    "plt.plot(MNIST_solver.val_acc_history, '-o', label='val')\n",
+    "plt.plot([0.9] * len(MNIST_solver.val_acc_history), 'k--')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(loc='lower right')\n",
+    "plt.gcf().set_size_inches(15, 12)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19ff7e18",
+   "metadata": {
+    "id": "19ff7e18"
+   },
+   "source": [
+    "# Test The Model!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "3df244fa",
+   "metadata": {
+    "id": "3df244fa",
+    "outputId": "2bbe2e3a-7ab5-4325-f215-7e6bc909b821",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Validation set accuracy:  0.9714\n",
+      "Test set accuracy:  0.9695\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_test_pred = np.argmax(MNIST_best_model.loss(data['X_test']), axis=1)\n",
+    "y_val_pred = np.argmax(MNIST_best_model.loss(data['X_val']), axis=1)\n",
+    "print('Validation set accuracy: ', (y_val_pred == data['y_val']).mean())\n",
+    "print('Test set accuracy: ', (y_test_pred == data['y_test']).mean())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5e9b7aa1",
+   "metadata": {
+    "id": "5e9b7aa1"
+   },
+   "source": [
+    "# California housing dataset\n",
+    "This is a dataset obtained from the [StatLib repository](https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html). The data pertains to the houses found in a given California district and some summary stats about them based on the 1990 census data."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Load Data"
+   ],
+   "metadata": {
+    "id": "7kpleK6EMUUm"
+   },
+   "id": "7kpleK6EMUUm"
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "def get_california_housing_data(num_training=15640, num_validation=2500, num_test=2500):\n",
+    "    \"\"\"\n",
+    "    Load the california housing dataset from disk and perform preprocessing to prepare\n",
+    "    it for the price prediction. \n",
+    "    \"\"\"\n",
+    "\n",
+    "    # Load the raw california_housing data\n",
+    "    X_train, y_train = fetch_california_housing(return_X_y=True)\n",
+    "\n",
+    "    # subsample the data\n",
+    "    mask = list(range(num_training + num_validation,\n",
+    "                      num_training + num_validation + num_test))\n",
+    "    X_test = X_train[mask]\n",
+    "    y_test = y_train[mask]\n",
+    "    mask = list(range(num_training, num_training + num_validation))\n",
+    "    X_val = X_train[mask]\n",
+    "    y_val = y_train[mask]\n",
+    "    mask = list(range(num_training))\n",
+    "    X_train = X_train[mask]\n",
+    "    y_train = y_train[mask]\n",
+    "\n",
+    "    # Preprocessing: reshape the image data into rows\n",
+    "    X_train = np.reshape(X_train, (X_train.shape[0], -1))\n",
+    "    X_val = np.reshape(X_val, (X_val.shape[0], -1))\n",
+    "    X_test = np.reshape(X_test, (X_test.shape[0], -1))\n",
+    "\n",
+    "    return X_train, y_train, X_val, y_val, X_test, y_test\n",
+    "\n",
+    "\n",
+    "def get_california_housing_normalized__data(X_train, X_val, X_test):\n",
+    "    # Normalize the data: subtract the mean array\n",
+    "    epsilon = 10 ** -6\n",
+    "    mean_array = np.mean(X_train, axis=0)\n",
+    "    std = np.std(X_train, axis=0) + epsilon\n",
+    "\n",
+    "    X_train -= mean_array\n",
+    "    X_val -= mean_array\n",
+    "    X_test -= mean_array\n",
+    "    return X_train / std, X_val / std, X_test / std\n"
+   ],
+   "metadata": {
+    "id": "_IDZSKBYMWpo"
+   },
+   "id": "_IDZSKBYMWpo",
+   "execution_count": 25,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "b1ee041f",
+   "metadata": {
+    "id": "b1ee041f",
+    "outputId": "efeceb5b-c3bb-4707-d3f3-1e32a89e2dda",
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "   MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude  \\\n",
+       "0  8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88   \n",
+       "1  8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   \n",
+       "2  7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   \n",
+       "3  5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   \n",
+       "4  3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   \n",
+       "\n",
+       "   Longitude  MedHouseVal  \n",
+       "0    -122.23        4.526  \n",
+       "1    -122.22        3.585  \n",
+       "2    -122.24        3.521  \n",
+       "3    -122.25        3.413  \n",
+       "4    -122.25        3.422  "
+      ],
+      "text/html": [
+       "\n",
+       "  <div id=\"df-0e790a20-449d-4dfd-848c-f492f3c91654\">\n",
+       "    <div class=\"colab-df-container\">\n",
+       "      <div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MedInc</th>\n",
+       "      <th>HouseAge</th>\n",
+       "      <th>AveRooms</th>\n",
+       "      <th>AveBedrms</th>\n",
+       "      <th>Population</th>\n",
+       "      <th>AveOccup</th>\n",
+       "      <th>Latitude</th>\n",
+       "      <th>Longitude</th>\n",
+       "      <th>MedHouseVal</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8.3252</td>\n",
+       "      <td>41.0</td>\n",
+       "      <td>6.984127</td>\n",
+       "      <td>1.023810</td>\n",
+       "      <td>322.0</td>\n",
+       "      <td>2.555556</td>\n",
+       "      <td>37.88</td>\n",
+       "      <td>-122.23</td>\n",
+       "      <td>4.526</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>8.3014</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>6.238137</td>\n",
+       "      <td>0.971880</td>\n",
+       "      <td>2401.0</td>\n",
+       "      <td>2.109842</td>\n",
+       "      <td>37.86</td>\n",
+       "      <td>-122.22</td>\n",
+       "      <td>3.585</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.2574</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>8.288136</td>\n",
+       "      <td>1.073446</td>\n",
+       "      <td>496.0</td>\n",
+       "      <td>2.802260</td>\n",
+       "      <td>37.85</td>\n",
+       "      <td>-122.24</td>\n",
+       "      <td>3.521</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>5.6431</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>5.817352</td>\n",
+       "      <td>1.073059</td>\n",
+       "      <td>558.0</td>\n",
+       "      <td>2.547945</td>\n",
+       "      <td>37.85</td>\n",
+       "      <td>-122.25</td>\n",
+       "      <td>3.413</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3.8462</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>6.281853</td>\n",
+       "      <td>1.081081</td>\n",
+       "      <td>565.0</td>\n",
+       "      <td>2.181467</td>\n",
+       "      <td>37.85</td>\n",
+       "      <td>-122.25</td>\n",
+       "      <td>3.422</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>\n",
+       "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0e790a20-449d-4dfd-848c-f492f3c91654')\"\n",
+       "              title=\"Convert this dataframe to an interactive table.\"\n",
+       "              style=\"display:none;\">\n",
+       "        \n",
+       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+       "       width=\"24px\">\n",
+       "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
+       "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
+       "  </svg>\n",
+       "      </button>\n",
+       "      \n",
+       "  <style>\n",
+       "    .colab-df-container {\n",
+       "      display:flex;\n",
+       "      flex-wrap:wrap;\n",
+       "      gap: 12px;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-convert {\n",
+       "      background-color: #E8F0FE;\n",
+       "      border: none;\n",
+       "      border-radius: 50%;\n",
+       "      cursor: pointer;\n",
+       "      display: none;\n",
+       "      fill: #1967D2;\n",
+       "      height: 32px;\n",
+       "      padding: 0 0 0 0;\n",
+       "      width: 32px;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-convert:hover {\n",
+       "      background-color: #E2EBFA;\n",
+       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+       "      fill: #174EA6;\n",
+       "    }\n",
+       "\n",
+       "    [theme=dark] .colab-df-convert {\n",
+       "      background-color: #3B4455;\n",
+       "      fill: #D2E3FC;\n",
+       "    }\n",
+       "\n",
+       "    [theme=dark] .colab-df-convert:hover {\n",
+       "      background-color: #434B5C;\n",
+       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+       "      fill: #FFFFFF;\n",
+       "    }\n",
+       "  </style>\n",
+       "\n",
+       "      <script>\n",
+       "        const buttonEl =\n",
+       "          document.querySelector('#df-0e790a20-449d-4dfd-848c-f492f3c91654 button.colab-df-convert');\n",
+       "        buttonEl.style.display =\n",
+       "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+       "\n",
+       "        async function convertToInteractive(key) {\n",
+       "          const element = document.querySelector('#df-0e790a20-449d-4dfd-848c-f492f3c91654');\n",
+       "          const dataTable =\n",
+       "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+       "                                                     [key], {});\n",
+       "          if (!dataTable) return;\n",
+       "\n",
+       "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
+       "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+       "            + ' to learn more about interactive tables.';\n",
+       "          element.innerHTML = '';\n",
+       "          dataTable['output_type'] = 'display_data';\n",
+       "          await google.colab.output.renderOutput(dataTable, element);\n",
+       "          const docLink = document.createElement('div');\n",
+       "          docLink.innerHTML = docLinkHtml;\n",
+       "          element.appendChild(docLink);\n",
+       "        }\n",
+       "      </script>\n",
+       "    </div>\n",
+       "  </div>\n",
+       "  "
+      ]
+     },
+     "metadata": {},
+     "execution_count": 26
+    }
+   ],
+   "source": [
+    "california_housing = fetch_california_housing(as_frame=True)\n",
+    "california_housing.frame.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "bbc5ad10",
+   "metadata": {
+    "id": "bbc5ad10",
+    "outputId": "8b2b1a40-96ae-4496-82dc-648d320fef3a",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Train data shape:  (15640, 8)\n",
+      "Train target values shape:  (15640,)\n",
+      "Validation data shape:  (2500, 8)\n",
+      "Validation target values shape:  (2500,)\n",
+      "Test data shape:  (2500, 8)\n",
+      "Test target values shape:  (2500,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "X_train, y_train, X_val, y_val, X_test, y_test = get_california_housing_data()\n",
+    "print('Train data shape: ', X_train.shape)\n",
+    "print('Train target values shape: ', y_train.shape)\n",
+    "print('Validation data shape: ', X_val.shape)\n",
+    "print('Validation target values shape: ', y_val.shape)\n",
+    "print('Test data shape: ', X_test.shape)\n",
+    "print('Test target values shape: ', y_test.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "30a1eeb3",
+   "metadata": {
+    "id": "30a1eeb3"
+   },
+   "outputs": [],
+   "source": [
+    "X_train, X_val, X_test = get_california_housing_normalized__data(X_train, X_val, X_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a1179b5c",
+   "metadata": {
+    "id": "a1179b5c"
+   },
+   "source": [
+    "# Train a Model!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "2fae7eca",
+   "metadata": {
+    "id": "2fae7eca",
+    "outputId": "4ef87e74-168e-4994-cf4e-4b7d2eb3dd76",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "(Iteration 1 / 390) loss: 3.782765\n",
+      "(Epoch 0 / 5) train RMS error: 1.842930; val RMS error: 2.612607\n",
+      "(Epoch 1 / 5) train RMS error: 0.823995; val RMS error: 1.533379\n",
+      "(Iteration 101 / 390) loss: 0.516311\n",
+      "(Epoch 2 / 5) train RMS error: 0.737113; val RMS error: 1.567512\n",
+      "(Iteration 201 / 390) loss: 0.574447\n",
+      "(Epoch 3 / 5) train RMS error: 0.754334; val RMS error: 1.602909\n",
+      "(Iteration 301 / 390) loss: 0.634667\n",
+      "(Epoch 4 / 5) train RMS error: 0.657686; val RMS error: 1.587526\n",
+      "(Epoch 5 / 5) train RMS error: 0.680126; val RMS error: 1.628638\n"
+     ]
+    }
+   ],
+   "source": [
+    "california_housing_best_model = None\n",
+    "\n",
+    "data = {\n",
+    "    'X_train': X_train,\n",
+    "    'y_train': y_train.astype(int),\n",
+    "    'X_val': X_val,\n",
+    "    'y_val': y_val.astype(int),\n",
+    "    'X_test': X_test,\n",
+    "    'y_test': y_test.astype(int)\n",
+    "    }\n",
+    "\n",
+    "model = FullyConnectedNet(\n",
+    "    'regression', \n",
+    "    [12, 10, 8],\n",
+    "    [False, True,True],\n",
+    "    input_dim=8,\n",
+    "    output_dim=1,\n",
+    "    dtype=np.float64\n",
+    ")\n",
+    "solver = Solver(model, data,\n",
+    "                update_rule=sgd_momentum,\n",
+    "                optim_config={\n",
+    "                  'learning_rate': 1e-3,\n",
+    "                },\n",
+    "                lr_decay=0.95,\n",
+    "                num_epochs=5, batch_size=200,\n",
+    "                print_every=100)\n",
+    "solver.train()\n",
+    "\n",
+    "california_housing_solver = solver\n",
+    "california_housing_best_model = model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "43e51742",
+   "metadata": {
+    "id": "43e51742",
+    "outputId": "b674b578-7252-4972-a4b5-513e6a80981a",
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 730
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 1080x864 with 2 Axes>"
+      ],
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "source": [
+    "# visualize training loss and train / val RMS error\n",
+    "\n",
+    "plt.subplot(2, 1, 1)\n",
+    "plt.title('Training loss')\n",
+    "plt.plot(california_housing_solver.loss_history, 'o')\n",
+    "plt.xlabel('Iteration')\n",
+    "\n",
+    "plt.subplot(2, 1, 2)\n",
+    "plt.title('RMS Error')\n",
+    "plt.plot(california_housing_solver.train_acc_history, '-o', label='train')\n",
+    "plt.plot(california_housing_solver.val_acc_history, '-o', label='val')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(loc='lower right')\n",
+    "plt.gcf().set_size_inches(15, 12)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Resources\n",
+    "\n",
+    "\n",
+    "*   Stanford University CS231n: Deep Learning for Computer Vision (Spring 2017)\n",
+    "*   Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems Book by Geron Aurelien\n",
+    "*   Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python Book by Sebastian Raschka"
+   ],
+   "metadata": {
+    "id": "zFw3BqubcLhz"
+   },
+   "id": "zFw3BqubcLhz"
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [
+    "57c3af9e"
+   ],
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "2d67ea1c85514b20a449bde440a6c08c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_02fde3a6623b40c18456121c8db32679",
+       "IPY_MODEL_d8f8cf98cb5c4bf091ddb96a89fd3c08",
+       "IPY_MODEL_2df61380b2cb4a4aab14a2be10b40b65"
+      ],
+      "layout": "IPY_MODEL_8b5b19e7914d4e1cb4c90aa7a1dc9de6"
+     }
+    },
+    "02fde3a6623b40c18456121c8db32679": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_2a483f0e5d6341ea9f416f9c8137c617",
+      "placeholder": "​",
+      "style": "IPY_MODEL_fdb6ed9208b84745aaf019d53476e525",
+      "value": "100%"
+     }
+    },
+    "d8f8cf98cb5c4bf091ddb96a89fd3c08": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_11fdd7100d7b4c8cbf504baaeaf5c51e",
+      "max": 9912422,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_1193bc936c494b8d8109bf86782dd3b0",
+      "value": 9912422
+     }
+    },
+    "2df61380b2cb4a4aab14a2be10b40b65": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_1e5b0f36eea64a4da35af00e988b9e49",
+      "placeholder": "​",
+      "style": "IPY_MODEL_dcb7c33f7bd14077b4dfff6dfdd5127c",
+      "value": " 9912422/9912422 [00:00&lt;00:00, 170081372.75it/s]"
+     }
+    },
+    "8b5b19e7914d4e1cb4c90aa7a1dc9de6": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "2a483f0e5d6341ea9f416f9c8137c617": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "fdb6ed9208b84745aaf019d53476e525": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "11fdd7100d7b4c8cbf504baaeaf5c51e": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "1193bc936c494b8d8109bf86782dd3b0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "1e5b0f36eea64a4da35af00e988b9e49": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "dcb7c33f7bd14077b4dfff6dfdd5127c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "a141e34baf0145569026127549e12af2": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_e45f65c8a003410cba3c6ed3208265c5",
+       "IPY_MODEL_fcc12dc7d49643069c024300329ffa3f",
+       "IPY_MODEL_d4e61b124e094ea59b255a6eb890f765"
+      ],
+      "layout": "IPY_MODEL_f1d9c15b33824051afb387a15036ee54"
+     }
+    },
+    "e45f65c8a003410cba3c6ed3208265c5": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_76490141f1f8414480e072dad27ab735",
+      "placeholder": "​",
+      "style": "IPY_MODEL_aa80b7dbbcc344e5919f782119759987",
+      "value": "100%"
+     }
+    },
+    "fcc12dc7d49643069c024300329ffa3f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_af102305ab89423b99fff9f12de56be1",
+      "max": 28881,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_231b5c1465294e8ca7d92bbb8a1c35b3",
+      "value": 28881
+     }
+    },
+    "d4e61b124e094ea59b255a6eb890f765": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_366317e704dc4c5d85ebd86e1cb5e605",
+      "placeholder": "​",
+      "style": "IPY_MODEL_39aea92910fe4560b97bf7bcf40005d9",
+      "value": " 28881/28881 [00:00&lt;00:00, 1217688.92it/s]"
+     }
+    },
+    "f1d9c15b33824051afb387a15036ee54": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "76490141f1f8414480e072dad27ab735": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "aa80b7dbbcc344e5919f782119759987": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "af102305ab89423b99fff9f12de56be1": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "231b5c1465294e8ca7d92bbb8a1c35b3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "366317e704dc4c5d85ebd86e1cb5e605": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "39aea92910fe4560b97bf7bcf40005d9": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "ce0c95134cc84d568c77519b33abbad4": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_24aad3dd0c254e65af983ef274644af9",
+       "IPY_MODEL_c2f87b094ece4a9ab578d9c3a9a64261",
+       "IPY_MODEL_2fb93bb1dc7b45fa81d977d417735986"
+      ],
+      "layout": "IPY_MODEL_2564d791dac44e00ad58bd3c22eaffd7"
+     }
+    },
+    "24aad3dd0c254e65af983ef274644af9": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_423464c848074c5f82af56686e0ed7a6",
+      "placeholder": "​",
+      "style": "IPY_MODEL_0c2b8d0da2ee47adabc870c2e20d2589",
+      "value": "100%"
+     }
+    },
+    "c2f87b094ece4a9ab578d9c3a9a64261": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_2f782d6343404904a7be6ae767ddc045",
+      "max": 1648877,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_221cb124249b442e8562e7474867da4c",
+      "value": 1648877
+     }
+    },
+    "2fb93bb1dc7b45fa81d977d417735986": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_fc851dfec63748cd8b2f99bfdf0b5895",
+      "placeholder": "​",
+      "style": "IPY_MODEL_0e622b2f01e14ddf889a94830ba09411",
+      "value": " 1648877/1648877 [00:00&lt;00:00, 50601368.19it/s]"
+     }
+    },
+    "2564d791dac44e00ad58bd3c22eaffd7": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "423464c848074c5f82af56686e0ed7a6": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0c2b8d0da2ee47adabc870c2e20d2589": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "2f782d6343404904a7be6ae767ddc045": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "221cb124249b442e8562e7474867da4c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "fc851dfec63748cd8b2f99bfdf0b5895": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0e622b2f01e14ddf889a94830ba09411": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "967a0b6c4f3d49fdbba513957c2e3ef3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_b2bae96fef44467c8bfe67bdd32da940",
+       "IPY_MODEL_c308d86c6ec242fbb28785a5ca9aeec6",
+       "IPY_MODEL_d506aea1cf9547dc8e063f97b96bd07c"
+      ],
+      "layout": "IPY_MODEL_2d8a041617fa438b9f3f614a02b54f42"
+     }
+    },
+    "b2bae96fef44467c8bfe67bdd32da940": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_4d473d2ad3fb495594bd880eabe7c1e5",
+      "placeholder": "​",
+      "style": "IPY_MODEL_27eab7d037f64833be94878e33e9eb14",
+      "value": "100%"
+     }
+    },
+    "c308d86c6ec242fbb28785a5ca9aeec6": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b737736bdcba48ffb80f83a939b9c992",
+      "max": 4542,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_2710d61d180b49dfa2ac072efab2c8d1",
+      "value": 4542
+     }
+    },
+    "d506aea1cf9547dc8e063f97b96bd07c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_170c9c6ae03741dea252dae56da56ec6",
+      "placeholder": "​",
+      "style": "IPY_MODEL_0b2d109241424cd79a55014fd618791d",
+      "value": " 4542/4542 [00:00&lt;00:00, 302562.24it/s]"
+     }
+    },
+    "2d8a041617fa438b9f3f614a02b54f42": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "4d473d2ad3fb495594bd880eabe7c1e5": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "27eab7d037f64833be94878e33e9eb14": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "b737736bdcba48ffb80f83a939b9c992": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "2710d61d180b49dfa2ac072efab2c8d1": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "170c9c6ae03741dea252dae56da56ec6": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "model_module_version": "1.2.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0b2d109241424cd79a55014fd618791d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "model_module_version": "1.5.0",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    }
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/.idea/Chapter_06_Convolutional_Neural_Networks.iml b/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/.idea/Chapter_06_Convolutional_Neural_Networks.iml
new file mode 100644
index 00000000..d0876a78
--- /dev/null
+++ b/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/.idea/Chapter_06_Convolutional_Neural_Networks.iml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file
diff --git a/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/.idea/modules.xml b/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/.idea/modules.xml
new file mode 100644
index 00000000..12846049
--- /dev/null
+++ b/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Chapter_06_Convolutional_Neural_Networks.iml" filepath="$PROJECT_DIR$/.idea/Chapter_06_Convolutional_Neural_Networks.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file
diff --git a/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/CNN_Architecture.ipynb b/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/CNN_Architecture.ipynb
index 15d73620..2bd86006 100644
--- a/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/CNN_Architecture.ipynb
+++ b/Jupyter_Notebooks/Chapter_06_Convolutional_Neural_Networks/CNN_Architecture.ipynb
@@ -1,767 +1,777 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "collapsed_sections": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    },
-    "accelerator": "GPU"
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "h1OkOqv428jR"
+   },
+   "source": [
+    "<font face=\"XB Zar\" size=5><div dir=rtl align=center>\n",
+    "<font face=\"IranNastaliq\" size=5>\n",
+    "به نام خدا\n",
+    "</font>\n",
+    "<br>\n",
+    "<font size=3>\n",
+    "دانشگاه صنعتی شریف - دانشکده مهندسی کامپیوتر\n",
+    "</font>\n",
+    "<br>\n",
+    "<font color=blue size=5>\n",
+    "مقدمه‌ای بر یادگیری ماشین\n",
+    "</font>\n",
+    "<br>\n",
+    "<hr/>\n",
+    "<font color=red size=6>\n",
+    "فصل شش\n",
+    "<br>\n",
+    "CNN Architecture \n",
+    "</font>\n",
+    "<br>\n",
+    "نویسندگان:‌ آرین امانی\n",
+    "<hr>\n",
+    "\n",
+    "<br>\n",
+    "  <div align=\"right\">\n",
+    "  <font color=\"red\" size=5>فهرست مطالب</font>\n",
+    "\t<ul>\n",
+    "    <li>\n",
+    "\t\t  <a href=\"#Kernels\">\n",
+    "        آشنایی با لایه کانولوشنی\n",
+    "        <ul>\n",
+    "          <li>\n",
+    "            <a href=\"#recap\">\n",
+    "              یاد آوری شبکه کاملا متصل(Fully Connected)\n",
+    "            </a>\n",
+    "          </li>\n",
+    "          <li>\n",
+    "            <a href=\"#cnn\">\n",
+    "              شبکه پیچشی(Convolutional)\n",
+    "            </a>\n",
+    "          </li>\n",
+    "        </ul>\n",
+    "    </a>\n",
+    "\t\t</li>\n",
+    "</div></font>"
+   ]
   },
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "source": [
-        "<font face=\"XB Zar\" size=5><div dir=rtl align=center>\n",
-        "<font face=\"IranNastaliq\" size=5>\n",
-        "به نام خدا\n",
-        "</font>\n",
-        "<br>\n",
-        "<font size=3>\n",
-        "دانشگاه صنعتی شریف - دانشکده مهندسی کامپیوتر\n",
-        "</font>\n",
-        "<br>\n",
-        "<font color=blue size=5>\n",
-        "مقدمه‌ای بر یادگیری ماشین\n",
-        "</font>\n",
-        "<br>\n",
-        "<hr/>\n",
-        "<font color=red size=6>\n",
-        "فصل شش\n",
-        "<br>\n",
-        "CNN Architecture \n",
-        "</font>\n",
-        "<br>\n",
-        "نویسندگان:‌ آرین امانی\n",
-        "<hr>\n",
-        "\n",
-        "<br>\n",
-        "  <div align=\"right\">\n",
-        "  <font color=\"red\" size=5>فهرست مطالب</font>\n",
-        "\t<ul>\n",
-        "    <li>\n",
-        "\t\t  <a href=\"#Kernels\">\n",
-        "        آشنایی با لایه کانولوشنی\n",
-        "        <ul>\n",
-        "          <li>\n",
-        "            <a href=\"#recap\">\n",
-        "              یاد آوری شبکه کاملا متصل(Fully Connected)\n",
-        "            </a>\n",
-        "          </li>\n",
-        "          <li>\n",
-        "            <a href=\"#cnn\">\n",
-        "              شبکه پیچشی(Convolutional)\n",
-        "            </a>\n",
-        "          </li>\n",
-        "        </ul>\n",
-        "    </a>\n",
-        "\t\t</li>\n",
-        "</div></font>"
-      ],
-      "metadata": {
-        "id": "h1OkOqv428jR"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "from tensorflow import keras\n",
-        "from tensorflow.keras.utils import to_categorical, plot_model\n",
-        "from keras.models import Sequential\n",
-        "from keras.layers import Dense, Conv2D, MaxPool2D, Flatten\n",
-        "import matplotlib.pyplot as plt\n",
-        "import tensorflow as tf\n",
-        "import numpy as np"
-      ],
-      "metadata": {
-        "id": "jLw_7U7RxmBc"
-      },
-      "execution_count": 1,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "  <div dir=rtl id=\"dataset\">\n",
-        "  <font face=\"XB Zar\" size=4>\n",
-        "      <font color=\"red\" size=5>\n",
-        "      آشنایی با لایه کانولوشنی\n",
-        "      </font>\n",
-        "      <hr/>\n",
-        "      یاد آوری شبکه پیچشی کاملا متصل - Fully Connected:\n",
-        "  </font>\n",
-        "  </div>\n",
-        "\n",
-        "![FC](https://drive.google.com/uc?export=view&id=15YcnB-3E2D-pGlssP3JPWrwd1_92xfcW)"
-      ],
-      "metadata": {
-        "id": "Cq14deDU49XT"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "  <div dir=rtl id=\"dataset\">\n",
-        "  <font face=\"XB Zar\" size=4>\n",
-        "      <font color=\"red\" size=5>\n",
-        "      آشنایی با لایه کانولوشنی\n",
-        "      </font>\n",
-        "      <hr/>\n",
-        "      همانطور که در اسلایدهای کلاس هم دیدید، تفاوت زیادی بین یادگیری یک مدل کاملا متصل و یک مدل پیچشی وجود دارد.\n",
-        "      <br>\n",
-        "      در مدل‌های Convolutional، ما با مدل‌هایی با پارامترهای بسیار کمتر، نتایجی بسیار بهتر روی دادگان تصویری می‌گیریم.\n",
-        "      <br><br>\n",
-        "      آزمایش انجام شده در اسلایدهای کلاس را در این قسمت می‌توانید خودتان انجام داده و نتایج را مقایسه کنید.\n",
-        "      </hr>\n",
-        "      \n",
-        "  </font>\n",
-        "  </div>\n"
-      ],
-      "metadata": {
-        "id": "fay0-AqvwD5a"
-      }
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "jLw_7U7RxmBc"
+   },
+   "outputs": [],
+   "source": [
+    "from tensorflow import keras\n",
+    "from tensorflow.keras.utils import to_categorical, plot_model\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Conv2D, MaxPool2D, Flatten\n",
+    "import matplotlib.pyplot as plt\n",
+    "import tensorflow as tf\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Cq14deDU49XT"
+   },
+   "source": [
+    "  <div dir=rtl id=\"dataset\">\n",
+    "  <font face=\"XB Zar\" size=4>\n",
+    "      <font color=\"red\" size=5>\n",
+    "      آشنایی با لایه کانولوشنی\n",
+    "      </font>\n",
+    "      <hr/>\n",
+    "      یاد آوری شبکه پیچشی کاملا متصل - Fully Connected:\n",
+    "  </font>\n",
+    "  </div>\n",
+    "\n",
+    "![FC](https://drive.google.com/uc?export=view&id=15YcnB-3E2D-pGlssP3JPWrwd1_92xfcW)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "fay0-AqvwD5a"
+   },
+   "source": [
+    "  <div dir=rtl id=\"dataset\">\n",
+    "  <font face=\"XB Zar\" size=4>\n",
+    "      <font color=\"red\" size=5>\n",
+    "      آشنایی با لایه کانولوشنی\n",
+    "      </font>\n",
+    "      <hr/>\n",
+    "      همانطور که در اسلایدهای کلاس هم دیدید، تفاوت زیادی بین یادگیری یک مدل کاملا متصل و یک مدل پیچشی وجود دارد.\n",
+    "      <br>\n",
+    "      در مدل‌های Convolutional، ما با مدل‌هایی با پارامترهای بسیار کمتر، نتایجی بسیار بهتر روی دادگان تصویری می‌گیریم.\n",
+    "      <br><br>\n",
+    "      آزمایش انجام شده در اسلایدهای کلاس را در این قسمت می‌توانید خودتان انجام داده و نتایج را مقایسه کنید.\n",
+    "      </hr>\n",
+    "      \n",
+    "  </font>\n",
+    "  </div>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "id": "C9NMKTcixxgk"
+   },
+   "outputs": [],
+   "source": [
+    "# Download the CIFAR10 dataset\n",
+    "(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()\n",
+    "\n",
+    "# Preprocessing the data\n",
+    "trainY = to_categorical(y_train)\n",
+    "testY = to_categorical(y_test)\n",
+    "\n",
+    "x_train = x_train.astype('float32')\n",
+    "x_test = x_test.astype('float32')\n",
+    "x_train = x_train / 255.0\n",
+    "x_test = x_test / 255.0\n",
+    "\n",
+    "# Inputs for the Dense Model\n",
+    "dense_train = x_train.reshape(-1, 32*32*3)\n",
+    "dense_test = x_test.reshape(-1, 32*32*3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "iqmIYOuKyMiI"
+   },
+   "source": [
+    "  <div dir=rtl id=\"dataset\">\n",
+    "  <font face=\"XB Zar\" size=4>\n",
+    "      <hr/>\n",
+    "      مدلی کاملا متصل ساخته و آن را روی دیتای CIFAR10 آموزش می‌دهیم.\n",
+    "      </hr>\n",
+    "      \n",
+    "  </font>\n",
+    "  </div>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 578
     },
+    "id": "LrdT01_p3eDu",
+    "outputId": "5cd58db9-7670-4bd9-bd2d-e9c174a04bdc"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# Download the CIFAR10 dataset\n",
-        "(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()\n",
-        "\n",
-        "# Preprocessing the data\n",
-        "trainY = to_categorical(y_train)\n",
-        "testY = to_categorical(y_test)\n",
-        "\n",
-        "x_train = x_train.astype('float32')\n",
-        "x_test = x_test.astype('float32')\n",
-        "x_train = x_train / 255.0\n",
-        "x_test = x_test / 255.0\n",
-        "\n",
-        "# Inputs for the Dense Model\n",
-        "dense_train = x_train.reshape(-1, 32*32*3)\n",
-        "dense_test = x_test.reshape(-1, 32*32*3)"
-      ],
-      "metadata": {
-        "id": "C9NMKTcixxgk"
-      },
-      "execution_count": 15,
-      "outputs": []
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train: X=(50000, 32, 32, 3), y=(50000, 1)\n",
+      "Test: X=(10000, 32, 32, 3), y=(10000, 1)\n"
+     ]
     },
     {
-      "cell_type": "markdown",
-      "source": [
-        "  <div dir=rtl id=\"dataset\">\n",
-        "  <font face=\"XB Zar\" size=4>\n",
-        "      <hr/>\n",
-        "      مدلی کاملا متصل ساخته و آن را روی دیتای CIFAR10 آموزش می‌دهیم.\n",
-        "      </hr>\n",
-        "      \n",
-        "  </font>\n",
-        "  </div>\n"
-      ],
-      "metadata": {
-        "id": "iqmIYOuKyMiI"
-      }
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 576x576 with 9 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# example of loading the cifar10 dataset\n",
+    "from matplotlib import pyplot\n",
+    "from keras.datasets import cifar10\n",
+    "# load dataset\n",
+    "# (trainX, trainy), (testX, testy) = cifar10.load_data()\n",
+    "# summarize loaded dataset\n",
+    "print('Train: X=%s, y=%s' % (x_train.shape, y_train.shape))\n",
+    "print('Test: X=%s, y=%s' % (x_test.shape, y_test.shape))\n",
+    "# plot first few images\n",
+    "fig , ax = plt.subplots(3, 3)\n",
+    "# plot first few images\n",
+    "for i in range(9):\n",
+    "  # plot raw pixel data\n",
+    "  ax[i//3, i%3]. imshow (x_train[i])\n",
+    "# show the figure\n",
+    "fig.tight_layout()\n",
+    "fig.set_figheight(8)\n",
+    "fig.set_figwidth(8)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 991
     },
+    "id": "-1RuGS8x2pxu",
+    "outputId": "666e35a8-1d5a-434b-8099-fb718449621f"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# example of loading the cifar10 dataset\n",
-        "from matplotlib import pyplot\n",
-        "from keras.datasets import cifar10\n",
-        "# load dataset\n",
-        "# (trainX, trainy), (testX, testy) = cifar10.load_data()\n",
-        "# summarize loaded dataset\n",
-        "print('Train: X=%s, y=%s' % (x_train.shape, y_train.shape))\n",
-        "print('Test: X=%s, y=%s' % (x_test.shape, y_test.shape))\n",
-        "# plot first few images\n",
-        "fig , ax = plt.subplots(3, 3)\n",
-        "# plot first few images\n",
-        "for i in range(9):\n",
-        "  # plot raw pixel data\n",
-        "  ax[i//3, i%3]. imshow (x_train[i])\n",
-        "# show the figure\n",
-        "fig.tight_layout()\n",
-        "fig.set_figheight(8)\n",
-        "fig.set_figwidth(8)\n",
-        "plt.show()"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 578
-        },
-        "id": "LrdT01_p3eDu",
-        "outputId": "5cd58db9-7670-4bd9-bd2d-e9c174a04bdc"
-      },
-      "execution_count": 18,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Train: X=(50000, 32, 32, 3), y=(50000, 1)\n",
-            "Test: X=(10000, 32, 32, 3), y=(10000, 1)\n"
-          ]
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 576x576 with 9 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
-      ]
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"Dense_Model\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " Dense_Layer_1 (Dense)       (None, 2048)              6293504   \n",
+      "                                                                 \n",
+      " Dense_Layer_2 (Dense)       (None, 1024)              2098176   \n",
+      "                                                                 \n",
+      " Dense_Layer_3 (Dense)       (None, 512)               524800    \n",
+      "                                                                 \n",
+      " Dense_Layer_4 (Dense)       (None, 128)               65664     \n",
+      "                                                                 \n",
+      " Softmax_Output_Layer (Dense  (None, 10)               1290      \n",
+      " )                                                               \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 8,983,434\n",
+      "Trainable params: 8,983,434\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "execution_count": 3,
-      "metadata": {
-        "id": "-1RuGS8x2pxu",
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 991
-        },
-        "outputId": "666e35a8-1d5a-434b-8099-fb718449621f"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Model: \"Dense_Model\"\n",
-            "_________________________________________________________________\n",
-            " Layer (type)                Output Shape              Param #   \n",
-            "=================================================================\n",
-            " Dense_Layer_1 (Dense)       (None, 2048)              6293504   \n",
-            "                                                                 \n",
-            " Dense_Layer_2 (Dense)       (None, 1024)              2098176   \n",
-            "                                                                 \n",
-            " Dense_Layer_3 (Dense)       (None, 512)               524800    \n",
-            "                                                                 \n",
-            " Dense_Layer_4 (Dense)       (None, 128)               65664     \n",
-            "                                                                 \n",
-            " Softmax_Output_Layer (Dense  (None, 10)               1290      \n",
-            " )                                                               \n",
-            "                                                                 \n",
-            "=================================================================\n",
-            "Total params: 8,983,434\n",
-            "Trainable params: 8,983,434\n",
-            "Non-trainable params: 0\n",
-            "_________________________________________________________________\n"
-          ]
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "image/png": "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\n",
-            "text/plain": [
-              "<IPython.core.display.Image object>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 3
-        }
-      ],
-      "source": [
-        "from keras.models import Sequential\n",
-        "from keras.layers import Flatten, Dense\n",
-        "\n",
-        "dense_model = Sequential(\n",
-        "    [\n",
-        "        Dense(2048, input_dim=32*32*3, activation='relu', name='Dense_Layer_1'),\n",
-        "        Dense(1024, activation='relu', name='Dense_Layer_2'),\n",
-        "        Dense(512, activation='relu', name='Dense_Layer_3'),\n",
-        "        Dense(128, activation='relu', name='Dense_Layer_4'),\n",
-        "        Dense(10, activation='softmax', name='Softmax_Output_Layer'),\n",
-        "    ],\n",
-        "    name='Dense_Model'\n",
-        ")\n",
-        "\n",
-        "\n",
-        "dense_model.compile(loss='categorical_crossentropy',\n",
-        "              optimizer='adam',\n",
-        "              metrics=['accuracy'])\n",
-        "\n",
-        "\n",
-        "dense_model.summary()\n",
-        "plot_model(dense_model, show_shapes=True)"
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<IPython.core.display.Image object>"
       ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from keras.models import Sequential\n",
+    "from keras.layers import Flatten, Dense\n",
+    "\n",
+    "dense_model = Sequential(\n",
+    "    [\n",
+    "        Dense(2048, input_dim=32*32*3, activation='relu', name='Dense_Layer_1'),\n",
+    "        Dense(1024, activation='relu', name='Dense_Layer_2'),\n",
+    "        Dense(512, activation='relu', name='Dense_Layer_3'),\n",
+    "        Dense(128, activation='relu', name='Dense_Layer_4'),\n",
+    "        Dense(10, activation='softmax', name='Softmax_Output_Layer'),\n",
+    "    ],\n",
+    "    name='Dense_Model'\n",
+    ")\n",
+    "\n",
+    "\n",
+    "dense_model.compile(loss='categorical_crossentropy',\n",
+    "              optimizer='adam',\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "\n",
+    "dense_model.summary()\n",
+    "plot_model(dense_model, show_shapes=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "id": "CB3qTRyvvO5l",
+    "outputId": "1e59f40b-4875-4edc-b888-98d43a126dc6"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "with tf.device('/device:GPU:0'):\n",
-        "  dense_history = dense_model.fit(dense_train, trainY, batch_size=128, epochs=10, verbose=1, validation_split=0.3)"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "CB3qTRyvvO5l",
-        "outputId": "1e59f40b-4875-4edc-b888-98d43a126dc6"
-      },
-      "execution_count": 4,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Epoch 1/10\n",
-            "274/274 [==============================] - 5s 8ms/step - loss: 2.0343 - accuracy: 0.2549 - val_loss: 1.8709 - val_accuracy: 0.3275\n",
-            "Epoch 2/10\n",
-            "274/274 [==============================] - 2s 8ms/step - loss: 1.7589 - accuracy: 0.3616 - val_loss: 1.7097 - val_accuracy: 0.3854\n",
-            "Epoch 3/10\n",
-            "274/274 [==============================] - 2s 6ms/step - loss: 1.6674 - accuracy: 0.4023 - val_loss: 1.7009 - val_accuracy: 0.3878\n",
-            "Epoch 4/10\n",
-            "274/274 [==============================] - 2s 6ms/step - loss: 1.6091 - accuracy: 0.4235 - val_loss: 1.6153 - val_accuracy: 0.4222\n",
-            "Epoch 5/10\n",
-            "274/274 [==============================] - 2s 7ms/step - loss: 1.5534 - accuracy: 0.4434 - val_loss: 1.5622 - val_accuracy: 0.4403\n",
-            "Epoch 6/10\n",
-            "274/274 [==============================] - 2s 9ms/step - loss: 1.5128 - accuracy: 0.4580 - val_loss: 1.5374 - val_accuracy: 0.4515\n",
-            "Epoch 7/10\n",
-            "274/274 [==============================] - 3s 10ms/step - loss: 1.4703 - accuracy: 0.4721 - val_loss: 1.5351 - val_accuracy: 0.4487\n",
-            "Epoch 8/10\n",
-            "274/274 [==============================] - 3s 11ms/step - loss: 1.4294 - accuracy: 0.4893 - val_loss: 1.4810 - val_accuracy: 0.4733\n",
-            "Epoch 9/10\n",
-            "274/274 [==============================] - 3s 10ms/step - loss: 1.3944 - accuracy: 0.5011 - val_loss: 1.4673 - val_accuracy: 0.4819\n",
-            "Epoch 10/10\n",
-            "274/274 [==============================] - 4s 13ms/step - loss: 1.3595 - accuracy: 0.5127 - val_loss: 1.4837 - val_accuracy: 0.4704\n"
-          ]
-        }
-      ]
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "274/274 [==============================] - 5s 8ms/step - loss: 2.0343 - accuracy: 0.2549 - val_loss: 1.8709 - val_accuracy: 0.3275\n",
+      "Epoch 2/10\n",
+      "274/274 [==============================] - 2s 8ms/step - loss: 1.7589 - accuracy: 0.3616 - val_loss: 1.7097 - val_accuracy: 0.3854\n",
+      "Epoch 3/10\n",
+      "274/274 [==============================] - 2s 6ms/step - loss: 1.6674 - accuracy: 0.4023 - val_loss: 1.7009 - val_accuracy: 0.3878\n",
+      "Epoch 4/10\n",
+      "274/274 [==============================] - 2s 6ms/step - loss: 1.6091 - accuracy: 0.4235 - val_loss: 1.6153 - val_accuracy: 0.4222\n",
+      "Epoch 5/10\n",
+      "274/274 [==============================] - 2s 7ms/step - loss: 1.5534 - accuracy: 0.4434 - val_loss: 1.5622 - val_accuracy: 0.4403\n",
+      "Epoch 6/10\n",
+      "274/274 [==============================] - 2s 9ms/step - loss: 1.5128 - accuracy: 0.4580 - val_loss: 1.5374 - val_accuracy: 0.4515\n",
+      "Epoch 7/10\n",
+      "274/274 [==============================] - 3s 10ms/step - loss: 1.4703 - accuracy: 0.4721 - val_loss: 1.5351 - val_accuracy: 0.4487\n",
+      "Epoch 8/10\n",
+      "274/274 [==============================] - 3s 11ms/step - loss: 1.4294 - accuracy: 0.4893 - val_loss: 1.4810 - val_accuracy: 0.4733\n",
+      "Epoch 9/10\n",
+      "274/274 [==============================] - 3s 10ms/step - loss: 1.3944 - accuracy: 0.5011 - val_loss: 1.4673 - val_accuracy: 0.4819\n",
+      "Epoch 10/10\n",
+      "274/274 [==============================] - 4s 13ms/step - loss: 1.3595 - accuracy: 0.5127 - val_loss: 1.4837 - val_accuracy: 0.4704\n"
+     ]
+    }
+   ],
+   "source": [
+    "with tf.device('/device:GPU:0'):\n",
+    "  dense_history = dense_model.fit(dense_train, trainY, batch_size=128, epochs=10, verbose=1, validation_split=0.3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "id": "zfjaG0Mhv8_J",
+    "outputId": "fc572e95-5927-467f-829c-4dbccb395d5c"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "dense_test_accuracy = dense_model.evaluate(dense_test, testY)[1]\n",
-        "print(\"Test Accuracy\",np.round((dense_test_accuracy)*100,2))"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "zfjaG0Mhv8_J",
-        "outputId": "fc572e95-5927-467f-829c-4dbccb395d5c"
-      },
-      "execution_count": 5,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "313/313 [==============================] - 1s 4ms/step - loss: 1.4630 - accuracy: 0.4798\n",
-            "Test Accuracy 47.98\n"
-          ]
-        }
-      ]
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "313/313 [==============================] - 1s 4ms/step - loss: 1.4630 - accuracy: 0.4798\n",
+      "Test Accuracy 47.98\n"
+     ]
+    }
+   ],
+   "source": [
+    "dense_test_accuracy = dense_model.evaluate(dense_test, testY)[1]\n",
+    "print(\"Test Accuracy\",np.round((dense_test_accuracy)*100,2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 295
     },
+    "id": "pTh0nqb2zT3c",
+    "outputId": "b7d288de-55da-4eec-ba6e-7fde0c75fd00"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# Let's plot our results: Accuracy\n",
-        "\n",
-        "plt.plot(dense_history.history['accuracy'])\n",
-        "plt.plot(dense_history.history['val_accuracy'])\n",
-        "plt.title('Dense Model Accuracy')\n",
-        "plt.ylabel('accuracy')\n",
-        "plt.xlabel('epoch')\n",
-        "plt.legend(['train', 'val'], loc='upper left')\n",
-        "plt.show()"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 295
-        },
-        "id": "pTh0nqb2zT3c",
-        "outputId": "b7d288de-55da-4eec-ba6e-7fde0c75fd00"
-      },
-      "execution_count": 6,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
       ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Let's plot our results: Accuracy\n",
+    "\n",
+    "plt.plot(dense_history.history['accuracy'])\n",
+    "plt.plot(dense_history.history['val_accuracy'])\n",
+    "plt.title('Dense Model Accuracy')\n",
+    "plt.ylabel('accuracy')\n",
+    "plt.xlabel('epoch')\n",
+    "plt.legend(['train', 'val'], loc='upper left')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 295
     },
+    "id": "waamXlirzate",
+    "outputId": "bd75b880-4cad-4ce8-919e-fc35c9579793"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# Let's plot our results: Loss\n",
-        "\n",
-        "plt.plot(dense_history.history['loss'])\n",
-        "plt.plot(dense_history.history['val_loss'])\n",
-        "plt.title('Dense Model Loss')\n",
-        "plt.ylabel('loss')\n",
-        "plt.xlabel('epoch')\n",
-        "plt.legend(['train', 'val'], loc='upper left')\n",
-        "plt.show()"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 295
-        },
-        "id": "waamXlirzate",
-        "outputId": "bd75b880-4cad-4ce8-919e-fc35c9579793"
-      },
-      "execution_count": 7,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
       ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Let's plot our results: Loss\n",
+    "\n",
+    "plt.plot(dense_history.history['loss'])\n",
+    "plt.plot(dense_history.history['val_loss'])\n",
+    "plt.title('Dense Model Loss')\n",
+    "plt.ylabel('loss')\n",
+    "plt.xlabel('epoch')\n",
+    "plt.legend(['train', 'val'], loc='upper left')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "BU5gSLrhzmZb"
+   },
+   "source": [
+    "  <div dir=rtl id=\"dataset\">\n",
+    "  <font face=\"XB Zar\" size=4>\n",
+    "      <font color=\"red\" size=5>\n",
+    "      آشنایی با لایه کانولوشنی\n",
+    "      </font>\n",
+    "      <hr/>\n",
+    "      حال، مدلی Convolutional طراحی کرده و تصاویر CIFAR10 را روی آن آموزش می‌دهیم.\n",
+    "      </hr>\n",
+    "      \n",
+    "  </font>\n",
+    "  </div>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000
     },
+    "id": "TePtKRZ2zidO",
+    "outputId": "707bfbbd-eddd-4d04-83d2-45fec7eaa8a9"
+   },
+   "outputs": [
     {
-      "cell_type": "markdown",
-      "source": [
-        "  <div dir=rtl id=\"dataset\">\n",
-        "  <font face=\"XB Zar\" size=4>\n",
-        "      <font color=\"red\" size=5>\n",
-        "      آشنایی با لایه کانولوشنی\n",
-        "      </font>\n",
-        "      <hr/>\n",
-        "      حال، مدلی Convolutional طراحی کرده و تصاویر CIFAR10 را روی آن آموزش می‌دهیم.\n",
-        "      </hr>\n",
-        "      \n",
-        "  </font>\n",
-        "  </div>\n"
-      ],
-      "metadata": {
-        "id": "BU5gSLrhzmZb"
-      }
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"Convolutional_Model\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " Conv_Layer_1 (Conv2D)       (None, 30, 30, 32)        896       \n",
+      "                                                                 \n",
+      " Max_Pool_1 (MaxPooling2D)   (None, 15, 15, 32)        0         \n",
+      "                                                                 \n",
+      " Conv_Layer_2 (Conv2D)       (None, 13, 13, 64)        18496     \n",
+      "                                                                 \n",
+      " Conv_Layer_3 (Conv2D)       (None, 11, 11, 128)       73856     \n",
+      "                                                                 \n",
+      " Flatten (Flatten)           (None, 15488)             0         \n",
+      "                                                                 \n",
+      " Dense_Flat_1 (Dense)        (None, 128)               1982592   \n",
+      "                                                                 \n",
+      " Softmax_Output_Layer (Dense  (None, 10)               1290      \n",
+      " )                                                               \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 2,077,130\n",
+      "Trainable params: 2,077,130\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "# CNN architecture\n",
-        "Convolutional_model = Sequential(\n",
-        "    [\n",
-        "        Conv2D(32, (3, 3), input_shape=(32, 32, 3),activation='relu', name='Conv_Layer_1'),\n",
-        "        MaxPool2D(pool_size=(2, 2), name='Max_Pool_1'),\n",
-        "        Conv2D(64, (3, 3),activation='relu', name='Conv_Layer_2'),\n",
-        "        Conv2D(128, (3, 3),activation='relu', name='Conv_Layer_3'),\n",
-        "        Flatten(name='Flatten'),\n",
-        "        Dense(128, activation='relu', name='Dense_Flat_1'),\n",
-        "        Dense(10, activation='softmax', name='Softmax_Output_Layer')\n",
-        "    ],\n",
-        "    name='Convolutional_Model'\n",
-        ")\n",
-        "\n",
-        "Convolutional_model.compile(loss='categorical_crossentropy',\n",
-        "              optimizer='adam',\n",
-        "              metrics=['accuracy'])\n",
-        "\n",
-        "\n",
-        "Convolutional_model.summary()\n",
-        "plot_model(Convolutional_model, show_shapes=True)"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 1000
-        },
-        "id": "TePtKRZ2zidO",
-        "outputId": "707bfbbd-eddd-4d04-83d2-45fec7eaa8a9"
-      },
-      "execution_count": 8,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Model: \"Convolutional_Model\"\n",
-            "_________________________________________________________________\n",
-            " Layer (type)                Output Shape              Param #   \n",
-            "=================================================================\n",
-            " Conv_Layer_1 (Conv2D)       (None, 30, 30, 32)        896       \n",
-            "                                                                 \n",
-            " Max_Pool_1 (MaxPooling2D)   (None, 15, 15, 32)        0         \n",
-            "                                                                 \n",
-            " Conv_Layer_2 (Conv2D)       (None, 13, 13, 64)        18496     \n",
-            "                                                                 \n",
-            " Conv_Layer_3 (Conv2D)       (None, 11, 11, 128)       73856     \n",
-            "                                                                 \n",
-            " Flatten (Flatten)           (None, 15488)             0         \n",
-            "                                                                 \n",
-            " Dense_Flat_1 (Dense)        (None, 128)               1982592   \n",
-            "                                                                 \n",
-            " Softmax_Output_Layer (Dense  (None, 10)               1290      \n",
-            " )                                                               \n",
-            "                                                                 \n",
-            "=================================================================\n",
-            "Total params: 2,077,130\n",
-            "Trainable params: 2,077,130\n",
-            "Non-trainable params: 0\n",
-            "_________________________________________________________________\n"
-          ]
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "image/png": "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\n",
-            "text/plain": [
-              "<IPython.core.display.Image object>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 8
-        }
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<IPython.core.display.Image object>"
       ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# CNN architecture\n",
+    "Convolutional_model = Sequential(\n",
+    "    [\n",
+    "        Conv2D(32, (3, 3), input_shape=(32, 32, 3),activation='relu', name='Conv_Layer_1'),\n",
+    "        MaxPool2D(pool_size=(2, 2), name='Max_Pool_1'),\n",
+    "        Conv2D(64, (3, 3),activation='relu', name='Conv_Layer_2'),\n",
+    "        Conv2D(128, (3, 3),activation='relu', name='Conv_Layer_3'),\n",
+    "        Flatten(name='Flatten'),\n",
+    "        Dense(128, activation='relu', name='Dense_Flat_1'),\n",
+    "        Dense(10, activation='softmax', name='Softmax_Output_Layer')\n",
+    "    ],\n",
+    "    name='Convolutional_Model'\n",
+    ")\n",
+    "\n",
+    "Convolutional_model.compile(loss='categorical_crossentropy',\n",
+    "              optimizer='adam',\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "\n",
+    "Convolutional_model.summary()\n",
+    "plot_model(Convolutional_model, show_shapes=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "id": "P7jOnf0U0IO9",
+    "outputId": "7b723ba4-cade-4735-83c6-b2f916b0a28d"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "with tf.device('/device:GPU:0'):\n",
-        "  conv_history = Convolutional_model.fit(x_train, trainY, batch_size=128, epochs=10, verbose=1, validation_split=0.3)"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "P7jOnf0U0IO9",
-        "outputId": "7b723ba4-cade-4735-83c6-b2f916b0a28d"
-      },
-      "execution_count": 9,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Epoch 1/10\n",
-            "274/274 [==============================] - 12s 13ms/step - loss: 1.5714 - accuracy: 0.4290 - val_loss: 1.3038 - val_accuracy: 0.5398\n",
-            "Epoch 2/10\n",
-            "274/274 [==============================] - 3s 11ms/step - loss: 1.1907 - accuracy: 0.5764 - val_loss: 1.2918 - val_accuracy: 0.5618\n",
-            "Epoch 3/10\n",
-            "274/274 [==============================] - 3s 10ms/step - loss: 1.0212 - accuracy: 0.6411 - val_loss: 1.0404 - val_accuracy: 0.6334\n",
-            "Epoch 4/10\n",
-            "274/274 [==============================] - 3s 11ms/step - loss: 0.8812 - accuracy: 0.6897 - val_loss: 0.9541 - val_accuracy: 0.6710\n",
-            "Epoch 5/10\n",
-            "274/274 [==============================] - 3s 11ms/step - loss: 0.7914 - accuracy: 0.7231 - val_loss: 0.9199 - val_accuracy: 0.6857\n",
-            "Epoch 6/10\n",
-            "274/274 [==============================] - 3s 10ms/step - loss: 0.6794 - accuracy: 0.7635 - val_loss: 0.8965 - val_accuracy: 0.6967\n",
-            "Epoch 7/10\n",
-            "274/274 [==============================] - 3s 13ms/step - loss: 0.5872 - accuracy: 0.7949 - val_loss: 0.9221 - val_accuracy: 0.6998\n",
-            "Epoch 8/10\n",
-            "274/274 [==============================] - 3s 11ms/step - loss: 0.4965 - accuracy: 0.8267 - val_loss: 0.9193 - val_accuracy: 0.7045\n",
-            "Epoch 9/10\n",
-            "274/274 [==============================] - 3s 10ms/step - loss: 0.4025 - accuracy: 0.8618 - val_loss: 0.9880 - val_accuracy: 0.6975\n",
-            "Epoch 10/10\n",
-            "274/274 [==============================] - 3s 10ms/step - loss: 0.3155 - accuracy: 0.8922 - val_loss: 1.1302 - val_accuracy: 0.6859\n"
-          ]
-        }
-      ]
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "274/274 [==============================] - 12s 13ms/step - loss: 1.5714 - accuracy: 0.4290 - val_loss: 1.3038 - val_accuracy: 0.5398\n",
+      "Epoch 2/10\n",
+      "274/274 [==============================] - 3s 11ms/step - loss: 1.1907 - accuracy: 0.5764 - val_loss: 1.2918 - val_accuracy: 0.5618\n",
+      "Epoch 3/10\n",
+      "274/274 [==============================] - 3s 10ms/step - loss: 1.0212 - accuracy: 0.6411 - val_loss: 1.0404 - val_accuracy: 0.6334\n",
+      "Epoch 4/10\n",
+      "274/274 [==============================] - 3s 11ms/step - loss: 0.8812 - accuracy: 0.6897 - val_loss: 0.9541 - val_accuracy: 0.6710\n",
+      "Epoch 5/10\n",
+      "274/274 [==============================] - 3s 11ms/step - loss: 0.7914 - accuracy: 0.7231 - val_loss: 0.9199 - val_accuracy: 0.6857\n",
+      "Epoch 6/10\n",
+      "274/274 [==============================] - 3s 10ms/step - loss: 0.6794 - accuracy: 0.7635 - val_loss: 0.8965 - val_accuracy: 0.6967\n",
+      "Epoch 7/10\n",
+      "274/274 [==============================] - 3s 13ms/step - loss: 0.5872 - accuracy: 0.7949 - val_loss: 0.9221 - val_accuracy: 0.6998\n",
+      "Epoch 8/10\n",
+      "274/274 [==============================] - 3s 11ms/step - loss: 0.4965 - accuracy: 0.8267 - val_loss: 0.9193 - val_accuracy: 0.7045\n",
+      "Epoch 9/10\n",
+      "274/274 [==============================] - 3s 10ms/step - loss: 0.4025 - accuracy: 0.8618 - val_loss: 0.9880 - val_accuracy: 0.6975\n",
+      "Epoch 10/10\n",
+      "274/274 [==============================] - 3s 10ms/step - loss: 0.3155 - accuracy: 0.8922 - val_loss: 1.1302 - val_accuracy: 0.6859\n"
+     ]
+    }
+   ],
+   "source": [
+    "with tf.device('/device:GPU:0'):\n",
+    "  conv_history = Convolutional_model.fit(x_train, trainY, batch_size=128, epochs=10, verbose=1, validation_split=0.3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "id": "aEqPsy_g0JHt",
+    "outputId": "5c0ac8c3-82af-4498-fdc2-bec4c76d6849"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "conv_test_accuracy = Convolutional_model.evaluate(x_test, testY)[1]\n",
-        "print(\"Test Accuracy\",np.round((conv_test_accuracy)*100,2))"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "aEqPsy_g0JHt",
-        "outputId": "5c0ac8c3-82af-4498-fdc2-bec4c76d6849"
-      },
-      "execution_count": 10,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "313/313 [==============================] - 1s 4ms/step - loss: 1.1774 - accuracy: 0.6735\n",
-            "Test Accuracy 67.35\n"
-          ]
-        }
-      ]
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "313/313 [==============================] - 1s 4ms/step - loss: 1.1774 - accuracy: 0.6735\n",
+      "Test Accuracy 67.35\n"
+     ]
+    }
+   ],
+   "source": [
+    "conv_test_accuracy = Convolutional_model.evaluate(x_test, testY)[1]\n",
+    "print(\"Test Accuracy\",np.round((conv_test_accuracy)*100,2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 295
     },
+    "id": "mzuaDmfa0LXJ",
+    "outputId": "ec300c79-87dc-41e1-87fe-9b9d1822b06b"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# Let's plot our results: Accuracy\n",
-        "\n",
-        "plt.plot(conv_history.history['accuracy'])\n",
-        "plt.plot(conv_history.history['val_accuracy'])\n",
-        "plt.title('Conv Model Accuracy')\n",
-        "plt.ylabel('accuracy')\n",
-        "plt.xlabel('epoch')\n",
-        "plt.legend(['train', 'val'], loc='upper left')\n",
-        "plt.show()"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 295
-        },
-        "id": "mzuaDmfa0LXJ",
-        "outputId": "ec300c79-87dc-41e1-87fe-9b9d1822b06b"
-      },
-      "execution_count": 11,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
       ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Let's plot our results: Accuracy\n",
+    "\n",
+    "plt.plot(conv_history.history['accuracy'])\n",
+    "plt.plot(conv_history.history['val_accuracy'])\n",
+    "plt.title('Conv Model Accuracy')\n",
+    "plt.ylabel('accuracy')\n",
+    "plt.xlabel('epoch')\n",
+    "plt.legend(['train', 'val'], loc='upper left')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 295
     },
+    "id": "pOtWWQtp0Nmf",
+    "outputId": "ec2e0391-339a-468d-ef15-8cdba06f4396"
+   },
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# Let's plot our results: Loss\n",
-        "\n",
-        "plt.plot(conv_history.history['loss'])\n",
-        "plt.plot(conv_history.history['val_loss'])\n",
-        "plt.title('Conv Model Loss')\n",
-        "plt.ylabel('loss')\n",
-        "plt.xlabel('epoch')\n",
-        "plt.legend(['train', 'val'], loc='upper left')\n",
-        "plt.show()"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 295
-        },
-        "id": "pOtWWQtp0Nmf",
-        "outputId": "ec2e0391-339a-468d-ef15-8cdba06f4396"
-      },
-      "execution_count": 12,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
       ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Let's plot our results: Loss\n",
+    "\n",
+    "plt.plot(conv_history.history['loss'])\n",
+    "plt.plot(conv_history.history['val_loss'])\n",
+    "plt.title('Conv Model Loss')\n",
+    "plt.ylabel('loss')\n",
+    "plt.xlabel('epoch')\n",
+    "plt.legend(['train', 'val'], loc='upper left')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "36I1o2BC0eQP"
+   },
+   "source": [
+    "  <div dir=rtl id=\"dataset\">\n",
+    "  <font face=\"XB Zar\" size=4>\n",
+    "      <hr/>\n",
+    "      نتایج دو مدل را با هم مقایسه می‌کنیم.\n",
+    "      <br>\n",
+    "      همانطور که مشخص است مدل Convolutional با وجود داشتن پارامترهای خیلی کمتر، با اختلاف زیادی بهتر عمل می‌کند.\n",
+    "      </hr>\n",
+    "      \n",
+    "  </font>\n",
+    "  </div>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 295
     },
+    "id": "6eFgQIB-0QKh",
+    "outputId": "602dd1cb-da97-47e6-b272-1a8555c5fa60"
+   },
+   "outputs": [
     {
-      "cell_type": "markdown",
-      "source": [
-        "  <div dir=rtl id=\"dataset\">\n",
-        "  <font face=\"XB Zar\" size=4>\n",
-        "      <hr/>\n",
-        "      نتایج دو مدل را با هم مقایسه می‌کنیم.\n",
-        "      <br>\n",
-        "      همانطور که مشخص است مدل Convolutional با وجود داشتن پارامترهای خیلی کمتر، با اختلاف زیادی بهتر عمل می‌کند.\n",
-        "      </hr>\n",
-        "      \n",
-        "  </font>\n",
-        "  </div>\n"
-      ],
-      "metadata": {
-        "id": "36I1o2BC0eQP"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "plt.plot(dense_history.history['val_accuracy'])\n",
-        "plt.plot(conv_history.history['val_accuracy'])\n",
-        "plt.title('Dense vs. Conv Model Accuracy')\n",
-        "plt.ylabel('accuracy')\n",
-        "plt.xlabel('epoch')\n",
-        "plt.legend(['Dense', 'Conv'], loc='upper left')\n",
-        "plt.show()"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 295
-        },
-        "id": "6eFgQIB-0QKh",
-        "outputId": "602dd1cb-da97-47e6-b272-1a8555c5fa60"
-      },
-      "execution_count": 13,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3deXwV5dn4/8+Vk4SsLCFhTcImm6AgBFBRcAVsrbiLuGBbRftIq7a12l/tU0v7tGr9WatSLVXcqKJQtLjigmC1RQirsi8KCVtCwpJA9lzfP2ZCTuIJHCAnc5JzvV+v88qZe5ZzzUky19z3PTO3qCrGGGNMfVFeB2CMMSY8WYIwxhgTkCUIY4wxAVmCMMYYE5AlCGOMMQFZgjDGGBOQJQhjWgAR+UZELgpiue4ioiIS3RRxmebNEkQEcQ8iJSJSJCL7ReQ/InKHiETE34GITBSRbBEpFpFdIvKeiJzTxDG84B6gx9cr/7NbfktTxtMQEVkoIvtEpJXXsRjvRMSBwdTxPVVNBroBDwH3Ac95G1LoichPgceBPwAdgUzgr8D4o60XIhuBm/1iiwauBbZ4EMu3iEh34FxAgcua+LOtZhNGLEFEKFU9oKrzgOuASSIyEEBEWonIoyKyXUT2iMgzIhLvzjtPRHJF5GcikueehX+/Zpsi8h0RWevWUHaIyM/95l0qIiv9ai6nB4pLRJ4WkUfrlf3LPcAjIve52y4SkQ0icuGx9lVE2gBTgTtVda6qHlLVClV9S1Xv9dvvx0Vkp/t6vObs+Wj7LSIjRGS3iPj8Pu8KEVl9lJDeAs4RkXbu9DhgNbDbbxtRIvKAiGxzP/Mldz9q5t/kzisQkV/V298oEblfRLa4818XkZRjfU9+bgYWAy8Ak+ptO0NE5opIvrvtp/zm3SYi69zfzVoRGeKWq4ic4rfcCyLye/d9zXd7n4jsBp4XkXYi8rb7Gfvc9+l+66eIyPPu72mfiLzpln8lIt/zWy5GRPaKyBnHse/GjyWICKeqS4BcnDNGcGoVfYDBwClAV+B//VbpBLRxy38ITPM70D0H3O7WUAYCCwDcf9AZwO1Ae+BvwLwGmi9eBa4TEXHXbQeMAWaJSF9gCjDM/YyxwDdB7OZZQBzwxlGW+RVwprvfg4DhwAPH2m9V/QI4BFzgt+xE4JWjfFYp8C9ggjt9M/BSvWVucV/nAz2BJOApABE5FXgauAnogvOdpvut+2PgcmC0O38fMO0o8dR3M/AP9zVWRDq6n+sD3ga2Ad1xvotZ7rxrgAfddVvj1DwKgvy8TkAKTq12Ms5x6Xl3OhMoqdl318tAAjAA6AD82S1/CbjRb7nvALtUdUWQcZj6VNVeEfLCOZheFKB8Mc4BUnAOdr385p0FfO2+Pw/nnzXab34ecKb7fjtOEmhdb/tPA7+rV7YBGB0gFnG3M8qdvg1Y4L4/xf28i4CY49jvG4Ddx1hmC/Adv+mxwDdB7vfvgRnu+2T3O+zWwOe84C5/DvBfoC2wB4gHPgNucZf7GPgfv/X6AhVANE7CnuU3LxEor/ndAuuAC/3md/ZbtztO01F0A/Gd4y6b6k6vB+7x+1vID7QuMB+4q4FtKnBK/e/A77stB+KO8rsZDOzz25dqoF2A5boARTV/f8Ac4Bde/98155fVIAw4Z4KFQBrOmdkytyloP/C+W16jQFUr/aYP45zdAlyFc9a2TUQWichZbnk34Gc123S3m4HzD12HOv/Zs4Dr3aKJOGeyqOpm4G6cM9U8EZklIt/aRgAFQOox2re74JwZ19hWL76j7fcrwJVujehKYLmq+m/rW1T1M5zv9VfA26paEkQ80Tj9J12AHL9tHaLu2Xo34A2/73odUOWueyyTgA9Uda/fvtU0M2UA2+p9D/jNO9E+lHxVLa2ZEJEEEfmb24R2EPgUaOvWYDKAQlXdV38jqroT+By4SkTaApfg/u2YE2MJIsKJyDCcBPEZsBfnTHmAqrZ1X21UNemoG3Gp6lJVHY9T7X8TeN2dlQP8n98226pqgqq+2sCmXgWuFpFuwAjgn36f8YqqnoNzEFTg4SBC+y9QhtPs0pCd7jZrZLplx6Sqa3EO4Jdw7OYlfzOBn/Ht5qWG4qnEqW3swjlQAs4BFaeZqUYOcEm97ztOVXccLRhx+pquBUa7/Sq7gXuAQSIyyN1uZgOJNgfo1cCmD+OceNToVG9+/UdK/wynxjRCVVsDo2pCdD8nxU0AgbyI08x0DfDfY+2zOTpLEBFKRFqLyKU4Z+szVfVLVa0G/g78WUQ6uMt1FZGxQWwvVkRuEJE2qloBHMRpCsDd5h1uh66ISKKIfFdEkgNtS502473As8B8Vd3vfkZfEbnAPVMvxUlm1YG2UW97B3CaZaaJyOXuGWqMiFwiIo+4i70KPCAiaSKS6i4/81jb9vMKcBfOwWx2kOs8AVyMc4Zc36vAPSLSQ0SScK6+es09e58DXCoi54hILE4HvP//8jPA/7kJFnefgrla63KcmsapOM06g4H+wL9x+haW4CSnh9zfYZyIjHTXfRb4uYgMdX/Hp9R8PrASmCgiPhEZh9M3cjTJOL/b/W7n+m9qZqjqLuA94K9uZ3aMiIzyW/dNYAjO7yJQ4jXHw+s2Lns13QunD6IEp532AM6Z9Z2Az2+ZOJyD0Vacg/w64CfuvPOA3ADbvAiIxWmO2ueutxQ4x2+5cW7ZfpyDzGwg+Six/hrnzPIav7LTcQ5SRThNYm8DXdx5NwBrjrH/NwDZOH0Eu4F3gLP99vsJN7Zd7vu4Y+2333QmTrJ65xgxvIDb/h5gnn8fRBROksrBafefiV+7O06zz3acpqVf+cfjrvtTnH6eIpymnz+487rTQB+E+/v7/wOUX+t+X9Hufr7pfu5e4Am/5e5wP7MY+Ao4wy3PAta4sbyMk/z8+yDqf7ddgIXudjbi9GsdiRmnQ/tFnNrUPmBuvfWfdX/HSV7/zzX3l7hfqDHGtAgi8r9AH1W98ZgLm6Oym1KMMS2G2yT1Q5xLgM1Jsj4IY0yLICK34TTJvaeqgfp1zHGyJiZjjDEBWQ3CGGNMQC2mDyI1NVW7d+/udRjGGNOsLFu2bK+qpgWa12ISRPfu3cnOzvY6DGOMaVZEpMG7/q2JyRhjTECWIIwxxgRkCcIYY0xALaYPIpCKigpyc3MpLS099sItXFxcHOnp6cTExHgdijGmmWjRCSI3N5fk5GS6d++OO/5MRFJVCgoKyM3NpUePHl6HY4xpJlp0E1NpaSnt27eP6OQAICK0b9/ealLGmOPSohMEEPHJoYZ9D8aY4xXSJib32e9/AXzAs6r6UL35f8YZcxecAUU6qGpbd94kascE/r2qvhjKWI0xYaa6Ckr2Q0khHC50fpbsc95XHIakDtC6K7TuAsmdIb4d2IlQowpZgnCHB5yGMyBKLrBUROapM/oWAKp6j9/yPwbOcN/XDBKShfMc+GXuut8aZjDc+Xw+TjvtNCoqKoiOjubmm2/mnnvuISqqxVfejHGoQnlx7UH+sHugrznY1ynzSwalB47vc6LjnWTRuoubODrXJpCasoRUsP+9oIWyBjEc2KyqWwFEZBYwHljbwPLXUzty1FjgQ1UtdNf9EGfAmYaGqAxb8fHxrFy5EoC8vDwmTpzIwYMH+e1vf+txZMacgMqyugf2bx3kC52z/voH/uqKhrfZqrVz9p+QAvEp0K5H7fuEFGdefAoktKsti46H4j1QtAsO7oCDO93XDji4C7b9B4p2QnW94bOjYpzaxpGk0aVeUukCSZ3A16Kv3wlaKL+FrvgNrI5TixgRaEF3aMIewIKjrNs1BDE2qQ4dOjB9+nSGDRvGgw8+SHV1Nffffz8LFy6krKyMO++8k9tvv52FCxfy4IMPkpqayldffcXQoUOZOXMmIsL999/PvHnziI6OZsyYMTz66KPk5+dzxx13sH37dgAef/xxRo4ceYxoTItXWe6cuZcXQ/kh9+W+LwtU3tByftNHO9D7WtU9sKf29jvI1z/Yu2XxbcF3gpdet81wXg2proZD+U7SKNrll0DcZLJrFWx4DypL6q4nUZDY4duJw/+V3AVi4k4s7mYkXNLkBGCOqlYdz0oiMhmYDJCZmXnUZX/71hrW7jx4wgEGcmqX1vzmewOOa52ePXtSVVVFXl4e//rXv2jTpg1Lly6lrKyMkSNHMmbMGABWrFjBmjVr6NKlCyNHjuTzzz+nf//+vPHGG6xfvx4RYf/+/QDcdddd3HPPPZxzzjls376dsWPHsm7dukbdV+ORsiLI3wD5652z8cY6mNcXkwix7qtVEsQmOQfzNunO+9ik2vnx7eqe8df8jIkPrz6AqChI7ui8GqLq1HAO7qxXG3F/FmyBr/8NZQGauxLaQ9tM6DAAOg6ATgOh40Dn+2ghQpkgdgD+6T3dLQtkAs7YyP7rnldv3YX1V1LV6cB0gKysrGY3sMUHH3zA6tWrmTNnDgAHDhxg06ZNxMbGMnz4cNLT0wEYPHgw33zzDWeeeSZxcXH88Ic/5NJLL+XSSy8F4KOPPmLt2tqWu4MHD1JcXExSUlLT75Q5MRWlULAJ8tZB3tran/u3f3tZ/4N5bJJzQK9zME8M8DMRWiXXXa/mZ0xC5LbLizgH9IQU5wDfkLIip+mqaGfdBFK4FTZ9ACtn1i6b3NlJFB0H1P5M7X3iNSUPhTJBLAV6i0gPnAP+BGBi/YVEpB/QDvivX/F84A8i0s6dHgP88mSCOd4z/VDZunUrPp+PDh06oKo8+eSTjB07ts4yCxcupFWrVkemfT4flZWVREdHs2TJEj7++GPmzJnDU089xYIFC6iurmbx4sXExbX8Km+zV1XpHFT8k0DeOqespgIdFQ2pfSB9GAy5GTqcCmn9nKt2YhIj92DupVbJkJYMaX0Czy/Ogz1fwZ41sNv9uXVhbS3OFwtpfd2E4Zc8kgI+ZTtshCxBqGqliEzBOdj7gBmqukZEpgLZqjrPXXQCMEv9hrZT1UIR+R1OkgGYWtNh3ZzV9BVMmTIFEWHs2LE8/fTTXHDBBcTExLBx40a6dm24q6W4uJjDhw/zne98h5EjR9KzZ08AxowZw5NPPsm9994LwMqVKxk8eHCT7JNpQHU1HMipVyNYB3s3QFW5u5BASk/o0B8GXO787HAqpPSC6FhPwzfHKakDJF0AvS6oLauqgL2b3MThJo0tn8Aqv2ttEju4TVMDapNHap+w+f2HtA9CVd8F3q1X9r/1ph9sYN0ZwIyQBddESkpKGDx48JHLXG+66SZ++tOfAnDrrbfyzTffMGTIEFSVtLQ03nzzzQa3VVRUxPjx4yktLUVVeeyxxwB44oknuPPOOzn99NOprKxk1KhRPPPMM02yfxFP1bmapn6NIG89VByqXa51upMAep3vJIEO/Z0DQWyCd7Gb0PLFQMdTnRfX1pYf2uski5qksecr+GI6VJU586OiIbWvX+KoqW10bPI+nhYzJnVWVpbWHzBo3bp19O/f36OIwo99HyfpcKHTWexfI8hb63Ry1khMq60JpPVzk0E/iGvjXdwm/FVVQsHmukljzxqnr6NGQmptsqhJHql9T/pqKhFZpqpZgeaFy1VMxoSX4nzIXQI5X8Cu1U4yKN5dO79VaycRnDq+tkaQ1j/s25RNmPJFOycSHfrBaVfXlh8udBPGmtqmquznoNJ9rpr4nA7wnufDJQ8F3vZJsARhTHW1UzPIWQw5blIo3OrM88W6TUMXuP/AbjJo3TW8Luk0LVNCCvQ413nVqK5y/j73fFXbIV5eFJKPtwRhIk9ZEexYBtu/cJJBbnbtde4JqZB5Jgy9BTJGQOfBEXFDlGlGotxaQ2pvGHBFSD/KEoRp2VSdewlyvqh97VkDWg2IUyMYeKWTDDKGO1cVWc3AGMAShGlpKsth92rYvthNCEtq+w5ikyA9C0bd6ySDrlnOox6MMQFZgjDN26G9frWDJbBjee3lgm27QY9RTjLIGOFc9RHl8zZeY5oRSxBNYPfu3dx9990sXbqUtm3b0rFjRx5//HH69GngrkwTWHW1c6PZdv/O5C3OvKgY6DIYht/mJIT04c7jno0xJ8wSRIipKldccQWTJk1i1qxZAKxatYo9e/ZYgjiWsmLYkV2bDHKW1u1MzhjhPIoiYwR0OcM6k41pZJYgQuyTTz4hJiaGO+6440jZoEGDUFXuvfde3nvvPUSEBx54gOuuu67BR33Pnz+f5557jtmzZwPO85oeffRR3n77ba92LXT2fQMf/BrWv+3XmdwfBl7hdiaPsM5kY5pA5CSI9+6H3V827jY7nXbMm1NqDvL1zZ07l5UrV7Jq1Sr27t3LsGHDGDVqFBD4Ud8XXXQRkydP5tChQyQmJvLaa68xYcKExt0fr5Ufgn8/Bv950nncwFlToMdop2PZOpONaXL2WEiPfPbZZ1x//fX4fD46duzI6NGjWbrUeTZhzaO+o6KijjzqOzo6mnHjxvHWW29RWVnJO++8w/jx4z3ei0aiCl/OgSez4N+POncn/zgbxvwOel9kycEYj0RODSIEt6EHY8CAAUfGewhWoEd9A0yYMIGnnnqKlJQUsrKySE5ObtRYPbFrFbx3H2z/r3NT2jUvQGbAgQeNMU3MahAhdsEFF1BWVsb06dOPlK1evZq2bdvy2muvUVVVRX5+Pp9++inDhw8/6rZGjx7N8uXL+fvf/978m5cO7YV5P4G/jXYeiXzZk3DbJ5YcjAkjkVOD8IiI8MYbb3D33Xfz8MMPExcXR/fu3Xn88ccpLi5m0KBBiAiPPPIInTp1Yv369Q1uy+fzcemll/LCCy/w4osvNuFeNKKqCljyd1j4kPM47DP/B0b/wpqRjAlD9rjvCOL597FlgXOxwN4N0OtCGPdHZ5QtY4xn7HHfxluFX8P8X8GGd6BdD7h+FvQZZ5epGhPmLEGY0Ckrhs9qLluNgQt/A2fdCdGtjr2uMcZzIU0QIjIO+AvOmNTPquq3LiUSkWuBBwEFVqnqRLe8Cqi5cWG7ql52IjGoKmJnqjRpU6IqfDkbPvxfKNoFp18HF/3WHn1hTDMTsgQhIj5gGnAxkAssFZF5qrrWb5newC+Bkaq6T0Q6+G2iRFUHn0wMcXFxFBQU0L59+4hOEqpKQUEBcXFN8CiKnSudy1ZzFjuPv7j2JefZSMaYZieUNYjhwGZV3QogIrOA8cBav2VuA6ap6j4AVc1rzADS09PJzc0lPz+/MTfbLMXFxZGenh66DyjOhwVTYfnLkJgKlz0Fg2+AKLuS2pjmKpQJoiuQ4zedC9S/yL0PgIh8jtMM9aCqvu/OixORbKASeEhV36z/ASIyGZgMkJmZ+a0AYmJi6NGjx0nuhjmqqgpYMh0WPuxctnrWnc5lq3FtvI7MGHOSvO6kjgZ6A+cB6cCnInKaqu4HuqnqDhHpCSwQkS9VdYv/yqo6HZgOzmWuTRu6YfPH8P79sHcjnHIRjP0jpNkTao1pKUKZIHYAGX7T6W6Zv1zgC1WtAL4WkY04CWOpqu4AUNWtIrIQOAPYgvFe4Vb3stV33ctWX4M+Y+2yVWNamFA2EC8FeotIDxGJBSYA8+ot8yZO7QERScVpctoqIu1EpJVf+Ujq9l0YL5QVw0e/hWkj4OtP4aIH4c4voK/d02BMSxSyGoSqVorIFGA+Tv/CDFVdIyJTgWxVnefOGyMia4Eq4F5VLRCRs4G/iUg1ThJ7yP/qJ9PEVGH16/DRb5zLVgdd79zTYJetGtOitehHbZhGsGO5c9lq7hLnstVL/gQZw7yOyhjTSOxRG+b4FefDx7+FFTMhMQ3GT4NBE+2yVWMiiCUIU1dVBXzxN1j0MFQchrOnwKhfQFxrryMzxjQxSxCmVnUV/PNWWPsmnHKx87TV1N5eR2WM8YglCONQde5pWPsmXDwVRt7ldUTGGI9Zg7JxfPaYc0f0WVMsORhjAEsQBpyO6I+nwmnXwsW/8zoaY0yYsAQR6TbOd8aG7nm+c6WSXaVkjHHZ0SCS5SyF1ydBp9PgupchOtbriIwxYcQSRKTK3wivXAPJneCG2dAq2euIjDFhxhJEJDq4C2ZeCVHRcNNcSOpw7HWMMRHHLnONNCX7YeZVULIPbnkHUnp6HZExJkxZgogkFaUw6wZn/IYbXocuJzWiqzGmhbMEESmqq2DubbDtM7jqOeh1gdcRGWPCnPVBRAJVeO8XsG4ejP0DnHa11xEZY5oBSxCR4N+PwtJn4ewfO2NGG2NMECxBtHTLX4IFv4fTr4OLpnodjTGmGbEE0ZJteA/eugt6XWh3SRtjjltIjxgiMk5ENojIZhG5v4FlrhWRtSKyRkRe8SufJCKb3NekUMbZIuUsgdnfh86D4NqXwBfjdUTGmGYmZFcxiYgPmAZcDOQCS0Vknv/Y0iLSG/glMFJV94lIB7c8BfgNkAUosMxdd1+o4m1R8jfAK9c6Y0ZPnA2tkryOyBjTDIWyBjEc2KyqW1W1HJgFjK+3zG3AtJoDv6rmueVjgQ9VtdCd9yEwLoSxthwHd8LLV0JUDNw4F5LSvI7IGNNMhTJBdAVy/KZz3TJ/fYA+IvK5iCwWkXHHsS4iMllEskUkOz8/vxFDb6ZK9jl3SZcegBvnQEoPryMyxjRjXvdaRgO9gfOA64G/i0jbYFdW1emqmqWqWWlpEX6mXFEKr06EvZtgwkyn78EYY05CKBPEDiDDbzrdLfOXC8xT1QpV/RrYiJMwglnX1Kiugrm3wvb/wBXPQM/zvI7IGNMChDJBLAV6i0gPEYkFJgDz6i3zJk7tARFJxWly2grMB8aISDsRaQeMcctMfarw7s9h3Vsw7iG7S9oY02hCdhWTqlaKyBScA7sPmKGqa0RkKpCtqvOoTQRrgSrgXlUtABCR3+EkGYCpqloYqlibtU//BNkzYOTdcOaPvI7GGNOCiKp6HUOjyMrK0uzsbK/DaFrLXnBuhBt0PVz+NIh4HZExppkRkWWqmhVonted1OZErX8X3r4HTrkILnvSkoMxptFZgmiOti+GOd+HzoPhmhftLmljTEhYgmhu8tbBK9dB667uWNJ2l7QxJjQsQTQnB3Y4N8JFt3LGkk5M9ToiY0wLZiPKNRdH7pI+CN9/F9p19zoiY0wLZwmiOagogVevh8ItcOM/ofPpXkdkjIkAliDCXVUl/PNWp2P66hnQY5TXERljIoQliHCmCu/+DNa/DZc8AgOv9DoiY0wEsU7qcLboYedmuHN+CiNu9zoaY0yEsQQRrrJnwMI/wuAb4ML/9ToaY0wEsgQRjta9De/8DHqPge/9xe6SNsZ4whJEuNn2X/jnD6HLELjmBbtL2hjjGUsQ4WTPWnj1OmiTARNfh9hEryMyxkQwu4opHJTsh/XvwILfQ3S8c69DYnuvozLGRDhLEF4pK4IN78NX/4QtH0NVObTrAde9DO26eR2dMcZYgmhS5Ydh0wdOUtj0AVSWQnIXGD4ZBlwJXYdYh7QxJmxYggi1yjLY/LGTFDa8BxWHILEDDLnZSQoZIyDKuoKMMeEnpAlCRMYBf8EZcvRZVX2o3vxbgD8BO9yip1T1WXdeFfClW75dVS8LZayNqqoCti5yksL6d6DsAMSnwOnXOEmh+zkQ5fM6SmOMOaqgEoSIzAWeA95T1eog1/EB04CLgVxgqYjMU9W19RZ9TVWnBNhEiaoODuazwkJ1FXzzmZMU1r0FJYXQqg30v9RJCj1H2yWrxphmJdgaxF+B7wNPiMhs4HlV3XCMdYYDm1V1K4CIzALGA/UTRPNVXQ05i+GrubD2X3AoD2ISod93nKRwyoXO2A3GGNMMBZUgVPUj4CMRaQNc777PAf4OzFTVigCrdQVy/KZzgREBlrtKREYBG4F7VLVmnTgRyQYqgYdU9c36K4rIZGAyQGZmZjC7cvJUYcdyp6aw5g0o2gnRcdBnrJMUeo+B2ISmicUYY0Io6D4IEWkP3AjcBKwA/gGcA0wCzjvBz38LeFVVy0TkduBF4AJ3XjdV3SEiPYEFIvKlqm7xX1lVpwPTAbKysvQEYzg2Vdi92qkprHkD9m8DXyycchEMmAp9x0Gr5JB9vDHGeCHYPog3gL7Ay8D3VHWXO+s19yw/kB1Aht90OrWd0QCoaoHf5LPAI37zdrg/t4rIQuAMoE6CCLm89W5NYS4UbIaoaOh5Hoy+D/p9F+LbNmk4xhjTlIKtQTyhqp8EmqGqWQ2ssxToLSI9cBLDBGCi/wIi0tkv2VwGrHPL2wGH3ZpFKjASv+QRUgVb3JrCXMhbCxLlXHV01hTof5nd4WyMiRjBJohTRWSFqu6HIwfw61X1rw2toKqVIjIFmI9zmesMVV0jIlOBbFWdB/xERC7D6WcoBG5xV+8P/E1EqnGeF/VQgKufGs++bU7T0Zq5sGuVU5Z5FlzyJzh1PCR3DNlHG2NMuBLVYzfdi8jK+pecugnjjJBFdpyysrI0O7uh1q6jKNwKT7i70XUoDLwKTr0c2nRt3ACNMSYMiciyhlqCgq1B+ERE1M0m7j0OsY0VoKdSesJ3H4NeF0BKD6+jMcaYsBFsgngfp0P6b+707W5ZyzDsh15HYIwxYSfYBHEfTlL4kTv9Ic5VR8YYY1qoYG+Uqwaedl/GGGMiQLD3QfQG/gicCsTVlKtqzxDFZYwxxmPBPmf6eZzaQyVwPvASMDNUQRljjPFesAkiXlU/xrksdpuqPgh8N3RhGWOM8VqwndRlIhIFbHJvftsBJIUuLGOMMV4LtgZxF5AA/AQYivPQvkmhCsoYY4z3jlmDcG+Ku05Vfw4U44wLYYwxpoU7Zg1CVatwHuttjDEmggTbB7FCROYBs4FDNYWqOjckURljjPFcsAkiDiigdjAfAAUsQRhjTAsV7J3U1u9gjDERJtg7qZ/HqTHUoao/aPSIjDHGhIVgm5je9nsfB1wB7Gz8cIwxxoSLYJuY/uk/LSKvAp+FJCJjjDFhIdgb5errDXQ41kIiMk5ENojIZhG5P8D8W0QkX0RWuq9b/eZNEpFN7stuyjPGmCYWbB9EEXX7IHbjjBFxtHV8wDTgYiAXWCoi8wKMLf2aqk6pt24K8Bsgy/3cZe66+4KJ1xhjzMkLtokp+QS2PRzYrKpbAURkFjAeqJ8gAjR3sSEAABeFSURBVBkLfKiqhe66HwLjgFdPIA5jjDEnIKgmJhG5QkTa+E23FZHLj7FaVyDHbzrXLavvKhFZLSJzRCTjeNYVkckiki0i2fn5+cHsijHGmCAF2wfxG1U9UDOhqvtxmoBO1ltAd1U9HWcY0xePZ2VVna6qWaqalZaW1gjhGGOMqRFsggi03LGap3YAGX7T6W7ZEapaoKpl7uSzOE+KDWpdY4wxoRVsgsgWkcdEpJf7egxYdox1lgK9RaSHiMQCE4B5/guISGe/ycuAde77+cAYEWknIu2AMW6ZMcaYJhLsjXI/Bn4NvIZzVdGHwJ1HW0FVK93BheYDPmCGqq4RkalAtqrOA34iIpfhDGVaCNzirlsoIr/DSTIAU2s6rI0xxjQNUf3WEzSapaysLM3OzvY6DGOMaVZEZJmqZgWaF+xVTB+KSFu/6XYiYk0+xhjTggXbB5HqXrkEgHvD2jHvpDbGGNN8BZsgqkUks2ZCRLoT4OmuxhhjWo5gO6l/BXwmIosAAc4FJocsKmOMCSMVVdXs3F/C9sLDta+Cw5RWVNGnYzJ9OyXTr1NrenVIpFW0z+twG02wj9p4X0SycJLCCuBNoCSUgRljTFNRVQ6UVNRJADmFh9lW4Lzfub+Ear82k1hfFOkp8cT6ovh8cwHlVdUAREcJPdMS6dupNf06JTuvzq3p0iYOEfFo705csA/ruxW4C+eGtZXAmcB/qTsEqTHGhK1AtYAc9+e2gsMUlVbWWT41KZaMlASGdmvHFWd0JSMlgcyUBLq1T6BjchxRUXJku9/sPcT63UWs332QDbuLWL5tH2+tqh0yJzkumn6damsaNe+T42Ka9Ds4XkFd5ioiXwLDgMWqOlhE+gF/UNUrQx1gsOwyV2PM/sPlAROAUwsopcqvGlBTC8h0D/yZKQlkuAkgo10Cia2CbYEP7GBpBRt3F9VJHOt3FVFUVpuIuraNp3/nuomjR2oi0b4THYnh+B3tMtdgv4FSVS0VEUSklaquF5G+jRijMcYEpbSiimXb9vFNwaG6SaDgMAcbqAUMyWzH5YPdBJCSQGa9WkAotI6LIat7ClndU46UqSo7D5SyftdBN3EUsWH3QT7ZkH8kecVGR3FKWhL9OrtNVG7iSEtu1eTNVMEmiFz3Pog3gQ9FZB+wLXRhGWNMLVXlqx0Hmb0sh3+t3MmBkgqgbi1gSGa72tpAI9UCGpuI0LVtPF3bxnNh/45Hyssqq9iSd+hITWPd7iI+37yXuctrH0GXkhhL347JdRJHn47JxMeGrlP8uO+kFpHRQBvgfVUtD0lUJ8CamIxpeQqKy3hz5U5mZ+ewfncRraKjGDewE5cP7kq/zskhrwV4bd+h8jpNVOt2F7FxdxElFVUAiED39omMPKU9v7/8tBP6jMZoYjpCVRedUBTGGBOEyqpqFm3M5/XsHBasz6OiShmU0ZbfXz6Q7w3qQpv48O7YbUztEmM5q1d7zurV/khZdbWSs+8w63YVOf0auw8SqicmhVf9yxgTsTbnFTN7WQ5zl+8gv6iM1KRYbjm7O9dkZdCn44kMatkyRUUJ3don0q19IuMGdgrpZ1mCMMZ4pqi0grdX7+L17BxWbN+PL0q4oF8Hrhmazvn9OhDThFfzmG+zBGGMaVLV1crirwuYk53Lu1/torSimt4dkvjVd/pz+RldSUtu5XWIxmUJwhjTJHL3Heafy3YwZ3kOOYUlJMdFc9WQdK7JymBQeptmeadxS2cJwhgTMqUVVcxfs5vXs3P4z5YCAEb2SuXnY/oydkAn4mJaznOLWiJLEMaYRqWqrMo9wOvZOby1aidFpZVkpMRz94V9uGpoV9LbJXgdogmSJQhjTKPILyrjjRW5zM7OZVNeMXExUXxnYGeuzkrnzB7tW/T9Ci1VSBOEiIwD/oIzJvWzqvpQA8tdBcwBhqlqtjvexDpgg7vIYlW9I5SxGmOOX0VVNQvW5zE7O5dPNuRRVa0MyWzLH688je+e3pnWYf4wOnN0IUsQIuIDpgEXA7nAUhGZp6pr6y2XjPOk2C/qbWKLqg4OVXzGhCtVZW9xORt2F7Fhj/Osnk15xVRXK/GxPhJio4mP8bnv3Z8x0bXvY31+8+uWJ8REEx/rI8YnJ9UpvGF3EbOzc3hz5Q72FpeTltyKW8/twTVD0zmlg92z0FKEsgYxHNisqlsBRGQWMB5YW2+53wEPA/eGMBZjwlJRaQUb9xSzYXcRG/cUHUkKhYdqn2LTPjGW3h2TaBXto6S8iryiUg6XV1FSXnXkZ814BMHyRQkJdZKMk0gSYn3ExfiOvI+vl3gqq5S3V+9kVe4BoqOEC/t34NqsDEb3SWvSJ5CaphHKBNEVyPGbzgVG+C8gIkOADFV9R0TqJ4geIrICOAg8oKr/rv8BIjIZd2S7zMzM+rONCRtllVVszT/kVytwXjv21467lRDro0/HZC7u35G+7ngBfTslk5p07PsCKquqKamoTRqHy6soqaikpLyaw+WVlFT4lZdXuvO/vXxxWSX5RWVHlnfmV9YZLKdfp2R+fempXD64C+2DiM00X551UotIFPAYcEuA2buATFUtEJGhwJsiMkBVD/ovpKrTgengPKwvxCEbc0zV1cr2wsO1SWCP83C1rXsPHXmcc3SU0CstiaHd2jFxRCZ93SEru7aNP+GO3GhfFMm+qJAMQKOqlFVWU1JeRUV1NWlJTf/YaeONUCaIHUCG33S6W1YjGRgILHT/2DoB80TkMlXNBsoAVHWZiGwB+gD2uFYTFlSV/KIy1tdrGtq0p/jIkzYBMlMS6NMxmbEDOtGnUzJ9OzoDwsRGN5/mGBEhLsZn9yxEoFAmiKVAbxHpgZMYJgATa2aq6gEgtWZaRBYCP3evYkoDClW1SkR6Ar2BrSGM1ZgG1YwM5t80tHFPEfsOVxxZJjWpFX07JXH98Ez6dkqib6fW9O6QFHbjERhzPEL216uqlSIyBZiPc5nrDFVdIyJTgWxVnXeU1UcBU0WkAqgG7lDVwlDFaoy/w+WVfLG1kEUb8/l0Yz5b9x46Mi+pVTR9OiYxbmAn+nZMPlIrsLZ40xId94BB4coGDDInSlXZuKeYTzfms2hjPku+LqS8qpq4mCjO6tmerO4pRwaZ79o23trfTYvSqAMGGdMSHDhcwedb9rJog5MUdh8sBaBPxyQmnd2N0X06kNW9nbW7m4hmCcJEhKpq5csdB47UElZs30e1QnJcNOf2TmV0nzRG9Umjc5t4r0M1JmxYgjAtVl5RKf/euJdFG/P596Z89h2uQARO79qGKeefwui+aQxKb2s3eBnTAEsQpsUor6xm+fZ9LNqYz6IN+azd5dw2k5rUivP7dWB0nzTO7Z1GSmKsx5Ea0zxYgjDNWk7hYSchbMznP5v3cqi8iugoYWi3dvxiXF9G90mjf6fW9iRRY06AJQjTrJSUV7H46wIWbah7CWp6u3guP6Mro/ukcVav9iG5o9iYSGMJwoQ1VWVTXu0lqF98XUh5pXMJ6pk923PTWd0Y3SeNHqmJdvmpMY3MEoQJS0u+LmTu8lwWbcxn1wHnEtTeHZK4+cxujO6bxrDuKXYJqjEhZgnChJW1Ow/yyPz1LNyQT3KraM7pncpdFzqXoHZpa5egGtOULEGYsLC94DCPfbiBf63aSXKraO6/pB+3nN3dagnGeMgShPFUflEZTy3YxCtLtuOLEu4Y3Ys7RvWiTYJ1MhvjNUsQxhNFpRX8/dOtPPvZ15RVVnPdsAzuurA3HVvHeR2aMcZlCcI0qdKKKmYu3sa0Tzaz73AF3z29Mz8f05ceqYleh2aMqccShGkSVdXK3OW5PP7RJnbsL+Hc3qn8Ymw/Tktv43VoxpgGWIIwIaWqfLh2D3+av4FNecUMSm/DI1efzshTUo+9sjHGU5YgTMh8sbWAh99fz/Lt++mZmshfbxjCJQM72Q1txjQTliBMo/O/l6Fj61b88crTuGZouj011ZhmJqQJQkTGAX/BGXL0WVV9qIHlrgLmAMNUNdst+yXwQ6AK+Imqzg9lrObk2b0MxrQsIUsQIuIDpgEXA7nAUhGZp6pr6y2XDNwFfOFXdiowARgAdAE+EpE+qloVqnjNibN7GYxpmUJZgxgObFbVrQAiMgsYD6ytt9zvgIeBe/3KxgOzVLUM+FpENrvb+28I4zXHye5lMKZlC2WC6Ark+E3nAiP8FxCRIUCGqr4jIvfWW3dxvXW71v8AEZkMTAbIzMxspLDNsdi9DMZEBs86qUUkCngMuOVEt6Gq04HpAFlZWdo4kZmG2L0MxkSWUCaIHUCG33S6W1YjGRgILHQve+wEzBORy4JY1zShQPcy/Onq0znb7mUwpkULZYJYCvQWkR44B/cJwMSamap6ADhyhBGRhcDPVTVbREqAV0TkMZxO6t7AkhDGahpQ516GtESevmEI4+xeBmMiQsgShKpWisgUYD7OZa4zVHWNiEwFslV13lHWXSMir+N0aFcCd9oVTE1r3a6DPPL+ej7ZkE+n1nE8dOVpXG33MhgTUUS1ZTTdZ2VlaXZ2ttdhhCVVpayymtKKKkoqqiitqKakvIrSyipK3Z8l5bXzs78p5F+rdtI6Lob/Oa8Xk+xeBmNaLBFZpqpZgebZndRh5Ju9hyg8XE5pRZX7qj2Ql5RXUVbpTvsd6GuWLTnys5qyOtPOcscjLiaKH43uxe2je9Em3u5lMCZSWYIIA9XVyv+9u47nPvv6mMuKQHyMj/gYH3ExPuJioohzpxNio0lJdMpq5sfH+oiLjiIu1kdctDMd77denN+2aspbx8dYjcEYYwnCa2WVVdw7ezXzVu1k4ohMLu7f8ciBP97voB4X7SMuNopYX5R1EBtjmoQlCA8VlVZw+8vL+M+WAu4b1487Rve0g78xJmxYgvBI3sFSbnl+KRv2FPHoNYO4emi61yEZY0wdliA8sDW/mJtnLKHwUDnPTcrivL4dvA7JGGO+xRJEE1uxfR8/eGEpUSK8etuZDMpo63VIxhgTkCWIJrRg/R7u/McKUpNjeekHI+zhdsaYsGYJoom8np3DL+d+Sf/OyTx/y3DSklt5HZIxxhyVJYgQU1WmfbKZRz/YyLm9U3n6xqEktbKv3RgT/uxIFUJV1cqD89bw8uJtXD64C49cPYjYaHuWkTGmebAEESKlFVXcPWsl76/ZzeRRPbl/XD+iouweB2NM82EJIgQOHK7gtpezWfJ1IQ98tz+3ntvT65CMMea4WYJoZLsOlDBpxhK+3nuIJ64/g8sGdfE6JGOMOSGWIBrRpj1F3DxjCUWllbzw/eGMtBHXjDHNmCWIRrL0m0JufTGb2OgoXrv9TAZ0sXGajTHNmyWIRjB/zW5+8uoKuraN58UfDCcjJcHrkIwx5qSF9JpLERknIhtEZLOI3B9g/h0i8qWIrBSRz0TkVLe8u4iUuOUrReSZUMZ5MmYu3saPZi6jf+fWzPnR2ZYcjDEtRshqECLiA6YBFwO5wFIRmaeqa/0We0VVn3GXvwx4DBjnztuiqoNDFd/JUlX+/OFGnliwmfP7pjHthiEkxFqFzBjTcoTyiDYc2KyqWwFEZBYwHjiSIFT1oN/yiUCzGCC7sqqaX73xFa9l53BtVjp/uOI0on12A5wxpmUJZYLoCuT4TecCI+ovJCJ3Aj8FYoEL/Gb1EJEVwEHgAVX9d4B1JwOTATIzMxsv8qMoKa9iyivL+Xh9Hj++4BR+enEfG+THGNMieX7aq6rTVLUXcB/wgFu8C8hU1TNwkscrItI6wLrTVTVLVbPS0tJCHmvhoXImPruYBRvy+N34AfxsTF9LDsaYFiuUNYgdQIbfdLpb1pBZwNMAqloGlLnvl4nIFqAPkB2aUI8tp/Awk55fQu6+Ep6+YQjjBnb2KhRjjGkSoaxBLAV6i0gPEYkFJgDz/BcQkd5+k98FNrnlaW4nNyLSE+gNbA1hrEe1dudBrnr6P+wtKmPmD0dYcjDGRISQ1SBUtVJEpgDzAR8wQ1XXiMhUIFtV5wFTROQioALYB0xyVx8FTBWRCqAauENVC0MV69H8Z8tebn9pGYmtopl9x9n07ZTsRRjGGNPkRLVZXDh0TFlZWZqd3bgtUG+v3slPX1tFt/YJvPiD4XRpG9+o2zfGGK+JyDJVzQo0zy7cb8Dzn3/N1LfXktWtHc/ePIw2CTFeh2SMMU3KEkQ9qsrD72/gmUVbGDugI3+ZcAZxMT6vwzLGmCZnCcJPRVU1981ZzdwVO7jxzEx+e9lAfDbIjzEmQlmCcB0qq+RH/1jOpxvz+fmYPtx5/il2j4MxJqJZggD2FpfxgxeWsmbnQR6+6jSuG9Y0d2UbY0w4i/gEsWN/CRP/vpg9B0uZftNQLuzf0euQjDEmLER8gkhJiKVXWhJ/vm4wQzLbeR2OMcaEjYhPEPGxPmbcMszrMIwxJux4/rA+Y4wx4ckShDHGmIAsQRhjjAnIEoQxxpiALEEYY4wJyBKEMcaYgCxBGGOMCcgShDHGmIBazIBBIpIPbDuJTaQCexspnObOvou67Puoy76PWi3hu+imqmmBZrSYBHGyRCS7oVGVIo19F3XZ91GXfR+1Wvp3YU1MxhhjArIEYYwxJiBLELWmex1AGLHvoi77Puqy76NWi/4urA/CGGNMQFaDMMYYE5AlCGOMMQFFfIIQkXEiskFENovI/V7H4yURyRCRT0RkrYisEZG7vI7JayLiE5EVIvK217F4TUTaisgcEVkvIutE5CyvY/KSiNzj/p98JSKvikic1zE1tohOECLiA6YBlwCnAteLyKneRuWpSuBnqnoqcCZwZ4R/HwB3Aeu8DiJM/AV4X1X7AYOI4O9FRLoCPwGyVHUg4AMmeBtV44voBAEMBzar6lZVLQdmAeM9jskzqrpLVZe774twDgBdvY3KOyKSDnwXeNbrWLwmIm2AUcBzAKparqr7vY3Kc9FAvIhEAwnATo/jaXSRniC6Ajl+07lE8AHRn4h0B84AvvA2Ek89DvwCqPY6kDDQA8gHnneb3J4VkUSvg/KKqu4AHgW2A7uAA6r6gbdRNb5ITxAmABFJAv4J3K2qB72OxwsicimQp6rLvI4lTEQDQ4CnVfUM4BAQsX12ItIOp7WhB9AFSBSRG72NqvFFeoLYAWT4Tae7ZRFLRGJwksM/VHWu1/F4aCRwmYh8g9P0eIGIzPQ2JE/lArmqWlOjnIOTMCLVRcDXqpqvqhXAXOBsj2NqdJGeIJYCvUWkh4jE4nQyzfM4Js+IiOC0Ma9T1ce8jsdLqvpLVU1X1e44fxcLVLXFnSEGS1V3Azki0tctuhBY62FIXtsOnCkiCe7/zYW0wE77aK8D8JKqVorIFGA+zlUIM1R1jcdheWkkcBPwpYisdMv+P1V918OYTPj4MfAP92RqK/B9j+PxjKp+ISJzgOU4V/+toAU+dsMetWGMMSagSG9iMsYY0wBLEMYYYwKyBGGMMSYgSxDGGGMCsgRhjDEmIEsQxoQBETnPnhhrwo0lCGOMMQFZgjDmOIjIjSKyRERWisjf3PEiikXkz+7YAB+LSJq77GARWSwiq0XkDff5PYjIKSLykYisEpHlItLL3XyS33gL/3Dv0DXGM5YgjAmSiPQHrgNGqupgoAq4AUgEslV1ALAI+I27ykvAfap6OvClX/k/gGmqOgjn+T273PIzgLtxxibpiXNnuzGeiehHbRhznC4EhgJL3ZP7eCAP53Hgr7nLzATmuuMntFXVRW75i8BsEUkGuqrqGwCqWgrgbm+Jqua60yuB7sBnod8tYwKzBGFM8AR4UVV/WadQ5Nf1ljvR59eU+b2vwv4/jcesicmY4H0MXC0iHQBEJEVEuuH8H13tLjMR+ExVDwD7RORct/wmYJE7Ul+uiFzubqOViCQ06V4YEyQ7QzEmSKq6VkQeAD4QkSigArgTZ/Cc4e68PJx+CoBJwDNuAvB/+ulNwN9EZKq7jWuacDeMCZo9zdWYkyQixaqa5HUcxjQ2a2IyxhgTkNUgjDHGBGQ1CGOMMQFZgjDGGBOQJQhjjDEBWYIwxhgTkCUIY4wxAf0/U88ZXBiLou4AAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
       ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "  <div dir=rtl id=\"dataset\">\n",
-        "  <font face=\"XB Zar\" size=4>\n",
-        "      <hr/>\n",
-        "      معماری مدل‌ها و Hyperparameter ها را به دلخواه تغییر دهید و نتایج مختلف را آزمایش کنید.\n",
-        "      <br>\n",
-        "\n",
-        "\n",
-        "\n",
-        "می‌توانید سعی کنید با راهکارهایی که در فصل قبل آموختید، جلوی Overfit شدن مدل‌ها را گرفته و نتایج را دوباره مقایسه کنید.\n",
-        "\n",
-        "\n",
-        "  </font>\n",
-        "  </div>\n"
-      ],
-      "metadata": {
-        "id": "dEOYWf_C02w1"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [],
-      "metadata": {
-        "id": "TBu8JwYw0bGj"
-      },
-      "execution_count": null,
-      "outputs": []
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
     }
-  ]
-}
\ No newline at end of file
+   ],
+   "source": [
+    "plt.plot(dense_history.history['val_accuracy'])\n",
+    "plt.plot(conv_history.history['val_accuracy'])\n",
+    "plt.title('Dense vs. Conv Model Accuracy')\n",
+    "plt.ylabel('accuracy')\n",
+    "plt.xlabel('epoch')\n",
+    "plt.legend(['Dense', 'Conv'], loc='upper left')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dEOYWf_C02w1"
+   },
+   "source": [
+    "  <div dir=rtl id=\"dataset\">\n",
+    "  <font face=\"XB Zar\" size=4>\n",
+    "      <hr/>\n",
+    "      معماری مدل‌ها و Hyperparameter ها را به دلخواه تغییر دهید و نتایج مختلف را آزمایش کنید.\n",
+    "      <br>\n",
+    "\n",
+    "\n",
+    "\n",
+    "می‌توانید سعی کنید با راهکارهایی که در فصل قبل آموختید، جلوی Overfit شدن مدل‌ها را گرفته و نتایج را دوباره مقایسه کنید.\n",
+    "\n",
+    "\n",
+    "  </font>\n",
+    "  </div>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "TBu8JwYw0bGj"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "collapsed_sections": [],
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}