PackagesNotFoundError: torchvision-cpu==0.2.0

[jmuff44xv]

I try to follow your installation instructions: I download and install Miniconda3-py38_4.10.3-Windows-x86_64.exe (is this not correct?) and then I execute:

conda install pytorch-cpu=0.4.1 torchvision-cpu==0.2.0 cpuonly -c pytorch

as instructed. But I get the error message:

Collecting package metadata (current_repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.

PackagesNotFoundError: The following packages are not available from current channels:

  - torchvision-cpu==0.2.0

Current channels:

  - https://conda.anaconda.org/pytorch/win-64
  - https://conda.anaconda.org/pytorch/noarch
  - https://repo.anaconda.com/pkgs/main/win-64
  - https://repo.anaconda.com/pkgs/main/noarch
  - https://repo.anaconda.com/pkgs/r/win-64
  - https://repo.anaconda.com/pkgs/r/noarch
  - https://repo.anaconda.com/pkgs/msys2/win-64
  - https://repo.anaconda.com/pkgs/msys2/noarch

To search for alternate channels that may provide the conda package you're
looking for, navigate to

    https://anaconda.org

and use the search bar at the top of the page.

[AtomicNess123]

Same problem here. PackagesNotFoundError: The following packages are not available from current channels:

• torchvision-cpu==0.2.0
• pytorch-cpu=0.4.1

Current channels:

• https://conda.anaconda.org/pytorch/osx-64
• https://conda.anaconda.org/pytorch/noarch
• https://repo.anaconda.com/pkgs/main/osx-64
• https://repo.anaconda.com/pkgs/main/noarch
• https://repo.anaconda.com/pkgs/r/osx-64
• https://repo.anaconda.com/pkgs/r/noarch

[Artyrm]

You can safely go with:

pytorch                   1.10.2
torchvision               0.11.3

The only problem you will have with outdated parameter in dataloader.py And that you can fix with this replacement in line 97:

        -resized_img = img.resize(resizeDim, Image.ANTIALIAS) if (resizeDim != None) else img
        +resized_img = img.resize(resizeDim, Image.LANCZOS) if (resizeDim != None) else img

[tsh78c9jk9]

You can safely go with:

pytorch                   1.10.2
torchvision               0.11.3

The only problem you will have with outdated parameter in dataloader.py And that you can fix with this replacement in line 97:

        -resized_img = img.resize(resizeDim, Image.ANTIALIAS) if (resizeDim != None) else img
        +resized_img = img.resize(resizeDim, Image.LANCZOS) if (resizeDim != None) else img

many thanks!

I think the key is the fix in dataloader.py. I used pytorch==2.1.0, it's also ok.