Comments (10)
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
from realtime-action-detection.
Thanks for quick reply. I will try.
from realtime-action-detection.
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?
from realtime-action-detection.
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/
from realtime-action-detection.
Also, RGB is a small contributor on JHMDB compared to optical flow.
from realtime-action-detection.
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?
from realtime-action-detection.
Should work. Just take care the fact that JHMDB videos are trimmed, unlike in ucf where videos are untrimmed.
Good luck
from realtime-action-detection.
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.
from realtime-action-detection.
Hi, Gurkirt,
Do you mean that when I test JHMDB, I should not use the code 'path_smoother.m' for temporal trimming, but only use the action paths after the first pass dynamic programming for evaluating?
from realtime-action-detection.
Yes, you are right.
from realtime-action-detection.
Related Issues (20)
- Problem in running HOT 3
- Question about label/ HOT 4
- problems about the results HOT 1
- problems about test just useing one action of ucf24 which you provided HOT 3
- Testing detection using much more time than proposed in the paper HOT 1
- Detection box HOT 2
- will it work for multivariate time series classification for example mixture of categorical and continues data? HOT 10
- pytorch=1.2.0 ,I got a error. I hope to get your help HOT 2
- About reported results HOT 1
- problem with loading pretrained weights for custom dataset with different number of classes HOT 1
- Testing Pre-trained models HOT 4
- Did you implement the evaluation of action early prediction in the paper HOT 3
- About inference HOT 1
- about demo? HOT 1
- Real time implementation HOT 1
- How fast this repo? HOT 1
- colab version? HOT 1
- Error in Evaluation HOT 1
- Where is Viterbi algorithm in your code? HOT 1
- Download of pretrained brox flow trained model weights HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from realtime-action-detection.