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

Uncertain about testing input_data size. #12

Open
wenlongxie opened this issue May 22, 2018 · 0 comments
Open

Uncertain about testing input_data size. #12

wenlongxie opened this issue May 22, 2018 · 0 comments

Comments

@wenlongxie
Copy link

Thanks for you share this excellent reseach!
I'm confused some line in 'model.py'.

input_data : ndarray
Must be three dimensional, where first dimension is the number of
input video stream(s), the second is the number of time steps, and
the third is the size of the visual encoder output for each time
step. Shape of tensor = (n_vids, L, input_size).
# --- (n_vids,L=video_length,D=500)=(1,video_length,500) ---

I ran your codes and pre_trained model on THUMOS14 , and then updated results in recall_eval.ipynb, and then plot_results.ipynb.

The curve 'sst_demo' (using sst_demo_th14_k32.hkl for predicting) is much lower than DAPs and SST in the average_recall figure. The highest average recall achieves 0.588 while 0.637 in your figure.

I am wondering if when predicting each video is the input_data size should be (1,video_length,500) according to your paper.

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

1 participant