Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

About I3D feature #21

Open
xljh0520 opened this issue Apr 3, 2022 · 5 comments
Open

About I3D feature #21

xljh0520 opened this issue Apr 3, 2022 · 5 comments

Comments

@xljh0520
Copy link

xljh0520 commented Apr 3, 2022

Hi, thanks for releasing your code! I have a question about how you extract the feature in Charades dataset with I3D model. Could you help me with it? Thanks in advance!

@JonghwanMun
Copy link
Owner

I used the pre-trained model (i.e., the models/rgb_charades.pt from https://github.com/piergiaj/pytorch-i3d), so I did not fine-tune I3D model by myself.

I think you can fine-tune I3D model by following the instruction in https://github.com/piergiaj/pytorch-i3d.

@xljh0520
Copy link
Author

xljh0520 commented Apr 4, 2022

I used the pre-trained model (i.e., the models/rgb_charades.pt from https://github.com/piergiaj/pytorch-i3d), so I did not fine-tune I3D model by myself.

I think you can fine-tune I3D model by following the instruction in https://github.com/piergiaj/pytorch-i3d.

Thanks for your reply! I still have some questions about the detail of the feature extractor.

  1. Did you use the code from pytorch-i3d to extract the feature of Charades videos?
  2. If so, what is the hyperparameter setting, such as fps and stride? Because I tried to extract the feature in another video and I think it's best to keep the feature extractor hyperparameter the same as yours.

Thanks in advance!

@JonghwanMun
Copy link
Owner

JonghwanMun commented Apr 4, 2022

I am not sure, but, I used pytorch-i3d following ExCL: Extractive Clip Localization Using Natural Language Descriptions

I think, following the paper, I would use 5 fps (or 30 fps).
For stride, I think you can compute it reversely from extracted I3D features of Charades.
For extraction code, I used the code from pytorch-i3d after a minor modification.

@xljh0520
Copy link
Author

xljh0520 commented Apr 4, 2022

I am not sure, but, I used pytorch-i3d following ExCL: Extractive Clip Localization Using Natural Language Descriptions

I think, following the paper, I would use 5 fps (or 30 fps). For stride, I think you can compute it reversely from extracted I3D features of Charades. For extraction code, I used the code from pytorch-i3d after a minor modification.

Could you share the code you modified? Thanks a lot!

@JonghwanMun
Copy link
Owner

Sorry that I do not have the modified code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants