ig65m-pytorch

ig65m-pytorch copied to clipboard

We should provide a tool where the user can load up a pre-trained model, point it at a dataset (e.g. directory of labeled videos), and have it fine-tune the model automatically.

you can easily repurpose the reference script from torchvision for that :)

Good point! For reference:

https://github.com/pytorch/vision/tree/v0.4.0/references/video_classification