requirements.txt please

[zhichucode]

Please share the requirements.txt file please

[zhichucode]

torch==1.0.0
torchvision==0.2.1
tensorflow==1.3.0
scipy==1.5.4
sklearn
matplotlib==2.2.5
pyparsing==2.4.7
scikit-image
numpy==1.16.4
tqdm

#https://discuss.pytorch.org/t/nvidia-a100-gpu-runtimeerror-cudnn-error-cudnn-status-mapping-error/121648/3
# pip3 install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html

[jmtc7]

The code uses scipy.misc.toimage(), which was deprecated in SciPy 1.0.0 and removed in 1.3.0 (as discussed here). I'm using SciPy 1.2.3 instead, which is the last predecessor of 1.3.0 (see SciPy releases for reference).