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

How do I create ActivityNet SRL in new dataset #8

Open
kelikeli opened this issue Mar 2, 2022 · 3 comments
Open

How do I create ActivityNet SRL in new dataset #8

kelikeli opened this issue Mar 2, 2022 · 3 comments

Comments

@kelikeli
Copy link

kelikeli commented Mar 2, 2022

Hi, thanks for your work. I am very interested in ActivityNet SRL. Now, I want to create ActivityNet SRL in my dataset, but I am very confused and don't know exactly how to do it and what part of the code to execute?

In the decode section of your project, you show: "The code is for generating the dataset from the parent datasets. If you just want to use ASRL as a training bed, you can skip this. See data". So, if I want to create an ActivityNet SRL for my own dataset, should I stop at the decode part of the code?

@TheShadow29
Copy link
Owner

@kelikeli Thanks for your interest.

If you want to create ASRL-like for your own dataset, you should follow the instructions in https://github.com/TheShadow29/vognet-pytorch/tree/master/dcode

You may have to change a few things to customize to your own dataset.

@kelikeli
Copy link
Author

kelikeli commented Mar 2, 2022

Ok, Thank you very much for your reply

@kelikeli
Copy link
Author

kelikeli commented Mar 4, 2022

@kelikeli Thanks for your interest.

If you want to create ASRL-like for your own dataset, you should follow the instructions in https://github.com/TheShadow29/vognet-pytorch/tree/master/dcode

You may have to change a few things to customize to your own dataset.
@TheShadow29
image

image

When I run the command "bash download_asrl_parent_ann.sh", should I choose the "all" among the three options in bash? In addition, this data is about 530G. If I want to create ASRL-like on my own dataset, do I need to use this 530G file?

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