Felipe Marra

[same](https://stackoverflow.com/questions/78531097/videoreader-on-torchvision-on-kaggle-outputs-attributeerror-av-audio-codeccont)

Try using a Conda environment. Besides torch still not being able to find my GPU, at least this error ain't showing up for me anymore.

Exactly. I went searching for a package just to get the infobox in an easier manner, but it seems like this API doesn't allow for that.

So, to solve the [Clone TensorFlow models repo into a 'models' directory](https://github.com/google-research/google-research/tree/master/frechet_audio_distance#clone-tensorflow-models-repo-into-a-models-directory) step: ```shell mkdir tensorflow_models touch tensorflow_models/__init__.py git clone https://github.com/tensorflow/models.git mv models/research/audioset tensorflow_models/audioset/ rm -rf models/ touch tensorflow_models/audioset/__init__.py vi...

That actually can be fixed just by changing the number of classes to 56, indicating the baseline was trained only in the mood/theme subset. Just one more thing, I created...

This time I'm using the small model, since it is just an example. Also, the dataset is another one, but this shouldn't change anything related to the presented problem. Ok,...