owaisCS
owaisCS
I noticed that in this Github repo you have uploaded the TimeSformer model pre-trained on ImageNet-21K, Could you please update/send the TimeSformer model pre-trained on ImageNet-1K? Or else as mentioned...
In CLIP published paper the reported train-test split size is: train = 9,537 test = 1,794 While in the UCF-101 original repo(https://www.crcv.ucf.edu/data/UCF101.php#:~:text=UCF101%20is%20an%20action%20recognition,which%20has%2050%20action%20categories.) size given is: train = 9537 test =...
When I am trying to run the following file: (https://github.com/facebookincubator/submitit/blob/main/docs/examples/torch_distributed.py) its working fine but when I try to add slurm_additional_parameters={"mem_per_gpu": 55} parameter as specified in https://github.com/facebookincubator/submitit/blob/990d7168d932ab7f9c13e0b5e0ff21571c4c6d11/submitit/slurm/test_slurm.py#L492 I am getting the...
My sincere appreciation for your research on Reversible Transformers. As I see in the hompage (https://github.com/facebookresearch/SlowFast/blob/main/projects/rev/README.md) the pretrained weights for Rev-VIT and Rev-MVIT has been released. But for Rev-SWIN only...