Google Colab demo

[josephrocca]

I'm been playing around trying to create a minimal Google Colab demo for this repository, but am running into some error messages that you can see here:

• https://colab.research.google.com/gist/josephrocca/78b327f78531a2cb3b28e0f1b9a92d57/ict-image-completion-transformer.ipynb
• https://gist.github.com/josephrocca/78b327f78531a2cb3b28e0f1b9a92d57

As you can see, the ImageNet inference command (same as in README) throws an error like this:

RuntimeError: Error(s) in loading state_dict for InpaintGenerator_5:
    Missing key(s) in state_dict: "encoder.1.weight", "encoder.1.bias", "encoder.3.weight", ...............
    Unexpected key(s) in state_dict: "module.encoder.1.weight", "module.encoder.1.bias", ...............

I haven't dug into the other (FFHQ) error yet - it says something about transparency, which may be a mistake on my part with preparing the input image and mask (image, mask).

Thanks for your work on this repo and publicly releasing the code and pre-trained models! Can't wait to try it out.

[gigadeplex]

Notice the "module" in "module.encoder.1.weight" and notice how it's not in the model you're trying to load it to. That "module" prefix just means the model that was used to create those weights was using nn.DataParallel. Either go to comment the if statement in Guided_Upsample/models.py line around 77 or just map the weights yourself.

[ntbjx]

Notice the "module" in "module.encoder.1.weight" and notice how it's not in the model you're trying to load it to. That "module" prefix just means the model that was used to create those weights was using nn.DataParallel. Either go to comment the if statement in Guided_Upsample/models.py line around 77 or just map the weights yourself.

Thanks a lot for your comment, after I removed the if statement on line 71, the error went away.