Updates for Python3

[rggs]

I've updated the files necessary to use python3 and the newer versions of Pytorch, at least with the MNIST dataset and the cluster_greyscale_twohead script.

[PHOSPHENES8]

Hi，thank you for your great job!
I am stuck to a problem that when I run the cluster task, the command I use is as follows:
python -m code.scripts.cluster.cluster_greyscale_twohead --model_ind 685 --arch ClusterNet6cTwoHead --mode IID --dataset MNIST --dataset_root /datasets/MNIST --gt_k 10 --output_k_A 50 --output_k_B 10 --lamb_A 1.0 --lamb_B 1.0 --lr 0.0001 --num_epochs 3200 --batch_sz 700 --num_dataloaders 5 --num_sub_heads 5 --crop_orig --crop_other --tf1_crop centre_half --tf2_crop random --tf1_crop_sz 20 --tf2_crop_szs 16 20 24 --input_sz 24 --rot_val 25 --no_flip --head_B_epochs 2 > out/sh10_gpu3_m685.out &
However, I got the issue report as :
Traceback (most recent call last): File "D:\Anaconda3\envs\tf2\lib\runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "D:\Anaconda3\envs\tf2\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Users\kunkun\Desktop\IIC\code\scripts\cluster\cluster_greyscale_twohead.py", line 498, in <module> train() File "C:\Users\kunkun\Desktop\IIC\code\scripts\cluster\cluster_greyscale_twohead.py", line 381, in train avg_loss_batch.backward() File "D:\Anaconda3\envs\tf2\lib\site-packages\torch\tensor.py", line 221, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "D:\Anaconda3\envs\tf2\lib\site-packages\torch\autograd\__init__.py", line 132, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: unsupported operation: more than one element of the written-to tensor refers to a single memory location. Please clone() the tensor before performing the operation.

I am sincerely looking forward to your reply. Hope everything goes well! @rggs @sebastiani