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

Awesome project! Question about rescale the feature length. #1

Open
ideaRunner opened this issue Nov 15, 2019 · 15 comments
Open

Awesome project! Question about rescale the feature length. #1

ideaRunner opened this issue Nov 15, 2019 · 15 comments

Comments

@ideaRunner
Copy link

Thanks for sharing!
The inference speed is extremely faster with a better result.
I'm thinking about how to reproduce the result on other datasets.
Could you share some detail or insight about how to use linear interpolation to rescale the feature length of all videos to same length 100 ?

Any method function, reference papers or codes will be thankful.

@pengxiaoxiao
Copy link

video_info_19993.json?

@pengxiaoxiao
Copy link

Hello, do you have the code to reproduce this article? The author has no working training code. How do you reason?

@lijiannuist
Copy link
Contributor

@ideaRunner
After you use TSN to extract video features, the features length is different. You must reshape these features by fitting and interpolation functions.
image

@lijiannuist
Copy link
Contributor

Hi @pengxiaoxiao
With these inference codes,you can repeat the results in our paper.

@pengxiaoxiao
Copy link

yean, thank you!

@pengxiaoxiao
Copy link

tensorflow.python.framework.errors_impl.NotFoundError: /home/shawxiao/video/ActionDetection-DBG/custom_op/prop_tcfg.so: undefined symbol: _ZN10tensorflow8internal21CheckOpMessageBuilder9NewStringEv

@pengxiaoxiao
Copy link

why?

@lijiannuist
Copy link
Contributor

@pengxiaoxiao
check your tensorflow version

@pengxiaoxiao
Copy link

Tensorflow-gpu == 1.9.0
Python == 3.6

@ideaRunner
Copy link
Author

@lijiannuist Yes, even some video's feature-length is less than 100, it must be fixed-length to feed into the network.
Thank you for sharing such kind of straightforward code!

@ideaRunner
Copy link
Author

@pengxiaoxiao Hi, pengxiaoxiao. For now, I am going to reproduce the inference results.
It is better to re-open an issue as your question is not related to this one.
The more detailed information about this issue, the more accurate the solution you will get.

@pengxiaoxiao
Copy link

thank you! I solved it by g++-5!

@gtgtgt1117
Copy link

@ideaRunner
After you use TSN to extract video features, the features length is different. You must reshape these features by fitting and interpolation functions.
image

How to extract features with TSN? Is removing the FC layer of TSN a feature?

@ideaRunner
Copy link
Author

@quanh1990
Copy link

hi @gtgtgt1117, The author answered at https://github.com/TencentYoutuResearch/ActionDetection-DBG/issues/6

@ideaRunner Page missing, could you please describe the solution, thanks very much

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

5 participants