I am trying to reproduce experimental results of one paper.
The authors specify “requirements.txt” for Python versions
click matplotlib numpy opencv-python==184.108.40.206 pandas pathy==0.4.0 PyYAML==5.4.1 scikit-learn scipy seaborn torch==1.7.1 torchvision==0.8.2 tqdm urllib3==1.26.3
But this does not work on A100 GPU because of torch version (maybe?).
So I updated the torch & torchvision version as follows:
pip3 install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
Now, the environment is prepared and I am using ResNet50 loading from torch.hub (https://download.pytorch.org/models/resnet50-19c8e357.pth).
Then, I take an image from ImageNet and give it as an input.
However, the outputs of ResNet50 for different versions of torch and torchvision were different even though the pre-processing of the input was the same.
This means that when a model has the same parameters, the prediction of it is dependent on torch & torchvision versions, which I think is undesirable.
So what is the cause of this?