MoViNet-pytorch
MoViNet-pytorch copied to clipboard
MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;
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?  Thanks!