MoViNet-pytorch icon indicating copy to clipboard operation
MoViNet-pytorch copied to clipboard

MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;

Results 18 MoViNet-pytorch issues
Sort by recently updated
recently updated
newest added

Can I use this code to train the model on my own dataset? If so, how should the dataset be structured?

Can I use this code to train the model on my own dataset? If so, how should the dataset be structured?

Thanks a lot for your codes. I have problem with the training of kinetics400. ```python kinetics400_train = torchvision.datasets.Kinetics400(root='...', step_between_clips=clip_steps, frames_per_clip=num_frames, frame_rate=5, extensions=('mp4'), transform=transform, num_workers=2) ``` I wrote this `Dataset` in...

Could you please provide us with the parameters that trained on Charades ? (I just want to do a inferrance with Charades parameters on our self-bulit datasets). Thanks a lot!

In which data set is the pre training weight?

Hi, thanks for your great work in movinet. I met a problem when testing hmdb51 videos. For example, the inference result for "brush hair" seems weird, in some frames, the...

Hi, I am trying to reproduce the MoViNet-A0-Stream model on the Kinetics test set, specifically on the part of the test annotations that are publicly available here: [https://storage.googleapis.com/deepmind-media/Datasets/kinetics600.tar.gz](https://storage.googleapis.com/deepmind-media/Datasets/kinetics600.tar.gz) I get...

Hi, Could you provide trained weights on SSv2 dataset? ![Screenshot 2024-11-13 at 3 28 55 PM](https://github.com/user-attachments/assets/4230473d-68fa-4da7-86f2-2e48a321850f) Thanks!