PyTorch Network Loader

Allows the easy creation and training of neural networks in PyTorch using .json files. Network creation automatically tracks layer output shapes; therefore, knowledge of the input into each layer is not needed. Networks are loaded from .json files, constructed, then a network object is returned that has all the training functionality built into it.

See the Wiki for more information on how to use this package.
For a real-world example of the Network object from this package in use, see Fast Spectra Predictor Network.

Requirements

Using Within Projects

• pip install netloader @ git+https://github.com/EthanTreg/PyTorch-Network-Loader@LATEST-VERSION¹ to requirements.txt
• Install using pip install -r requirements.txt
• Example of InceptionV4 can be downloaded under ./network_configs/inceptionv4.json along with the composite layers in ./network_configs/composite_layers/

Locally Running NetLoader

• Clone or download the repository
• Install dependencies: pip install -r requirements.txt
• PyTorch's dependencies²:
  NVIDIA GPU with CUDA Toolkit ~= v12.1

Footnotes

1. To use normalizing flows, netloader must be pip installed with the optional argument flows: pip install netloader[flows] @ git+https://github.com/EthanTreg/PyTorch-Network-Loader@LATEST-VERSION ↩

2. Only required for use with NVIDIA GPU, v11.8 is also supported, but requirements.txt will try to install the v12.1 version ↩