-
Notifications
You must be signed in to change notification settings - Fork 97
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
What the paramaters for training JHMDB-21 #25
Comments
46 seems okay, max you going to get is about 48-51%. But don't go on frames mAP on jhmdb21, check video mAP. It is a small dataset so frame-mAP is usually unstable. You can see the original SSD settings here https://pdfs.semanticscholar.org/50be/f2075a6f50a2525c3166a14ad413b7d38a0e.pdf. I think the initial learning rate of 0.0005 and then drop it after 2.5k or 5k iteration should do it on rgb stream bu ton flow |
Thanks for quick reply. I will try. |
Hi, Gurkirt. I tried to train JHMDB only rgb images again as you said. The frame-map is about 46%. However, the video-mAP @0.2 is only 46% which is very far from 60.8% reported in your paper. As I need to compare with your method, I really need to repeat your results. Could you give me some suggestions training on JHMDB, please? Or can you release some configuration files for training JHMDB? |
I am not sure if you are using correct protocol and annotation fo rJHMDB-21. Try tube building and evaluation protocol from https://bitbucket.org/sahasuman/bmvc2016_code/src/master/ |
Also, RGB is a small contributor on JHMDB compared to optical flow. |
I used the codes under the folder 'online_tubes' in this project to evaluate JHMDB. I know you just gave ucf101 as an example in this project. But I think the evaluation method should be same for JHMDB, right? So I modified it to test JHMDB. Or I have to change to use the evaluation from https://bitbucket.org/sahasuman/bmvc2016_code/src/master/? Is it different evaluation from this project? |
Should work. Just take care the fact that JHMDB videos are trimmed, unlike in ucf where videos are untrimmed. |
Hi, I am sorry to disturb you again. But I am still not clear about what I should take care about trimmed videos JHMDB for the evaluation. The evaluation should be same with the untrimmed videos UCF101, right? I used the same evaluation for ucf101 and JHMDB, but the video-mAP for UCF101 is same with you reported in the paper and for JHMDB is much lower than the paper. I am really confused. |
Hi, Gurkirt, |
Yes, you are right. |
Hi, I am trying to train models on JHMDB-21 using your code. I only modify the ratios of each class. But the results are very bad. For the first split of JHMDB, the frame-map@0.5 is only 46%. Do you have any suggestions for training JHMDB?
The text was updated successfully, but these errors were encountered: