Hi, thanks for the great code!

I wonder do you have plans to support resuming from checkpoints for classification? As we all know, in terms of training ImageNet, the training process is really long and it can be interrupted somehow, but I haven't notice any code related to "resume" in scripts/classification/train_imagenet.py.

Maybe @hetong007 ? Thanks in advance.

voting_label = output.sum(dim=3).sum(dim=2).sum(dim=1).argmax(dim=0)
What is the result of this step? I can't understand how to get the serial number of classification label.Who can tell me something about this?
@yysijie

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.

Along with citations and links