ActionCLIP

ActionCLIP copied to clipboard

Thanks for your amazing work! The KLLoss in the implementation is divided by feature dims (times batch_size in [code](https://github.com/sallymmx/ActionCLIP/blob/31c34df17dce917d67127b7fb155922c4744f680/utils/KLLoss.py#L27)), instead of batch size. The [docs of PyTorch](https://pytorch.org/docs/stable/generated/torch.nn.KLDivLoss.html) points that `reduction...

xk-huang

dengfenglai321

ModuleNotFoundError: No module named 'RandAugment'

2

how to install this api?

Bobby-youngking

dengfenglai321

Thank you for your share, it's a great work. And I find you didn't release 30 crops testing script for the best performance. Will this part be released？

icyzhang0923

I'm very interested in the work you have done. Could you provide pre-training models of UCF101 and HMDB51? Thanks a lot!

Morning-YU

您好，您的工作使我受益良多。我精读了您的论文，并对您论文中第4.5章节附录中的HMDB51和UCF101的结果深感兴趣！ 请问我在哪能继续学习到您论文附录中的相关知识呢？ 对此，我非常期待您的回复，同时祝您新春愉快！

TJQdoIt9527

I want to know if I can get some visualized results.

fengjingchehu

environment.yml

1

Tourbillon007

This PR integrates two TinyCLIP ViT models to the existing model framework with minimal changes. This is possible because TinyCLIP provides a pure ViT-based model, like CLIP. The TinyCLIP model...

FransHk