Comments (13)
First of all, I apologize for the missing details about the experimental settings on ActivityNet.
Since I extracted the features for ActivityNet by myself, they might be different from those you used.
For example, the sampling rate of the videos or the pre-trained I3D models could be different.
I used the original fps of the videos and the pre-trained models from this repo.
For the hyperparameters, the batch size, the margin, alpha, (r_act, r_bkg), and the NMS threshold are set to 512, 250, 1e-4, (5, 50), and 0.8, respectively.
I hope this would help.
from wtal-uncertainty-modeling.
Can you share the feature of act1.2?
from wtal-uncertainty-modeling.
Thanks for your wonderful work. Could you please share your features in Activitynet 1.3?
from wtal-uncertainty-modeling.
Hi, have you got the better result after you set the hyperparameters as mentioned?
Thanks.
from wtal-uncertainty-modeling.
Hi @Pilhyeon, thanks for your great work! Now I'm following your BMUE and have some trouble in reproducing the results on ActivityNet dataset.
I have tried to do some experiments on ActivityNet v1.2. I downloaded the I3D features provided by this link and adapt them to BMUE format. The following are some of my results. All experiments run for 6k epochs, the results are showed in the form of "(average_mAP, Test_acc)":
- [no params changed] (0.0390, 0.43)
According to Sec 4.1 in your arXiv paper, T=50, so I set num_segments as 50 and do the following experiments:
[num_segments: 50] (0.0275, 0.31)
- [class_th: 0.1] (0.0332, 0.36)
- [class_th: 0.1, act_thresh_cas: np.arange(0.0, 0.15, 0.015)] (0.0400, 0.36)
Besides, I also tried to change "act_thresh_magnitudes", "NMS thresh", "alpha", "_lambda & gamma in get_proposal_oic()", etc. The results don't seem to get better: the test accuracy is around 0.4 and the average_mAP is very low. It's hard for me to find the best settings. Could you please share your params settings on ActivityNet 1.2 & 1.3 datasets? Or give me some advice on which params to change?
Looking forward to your reply and I'd be glad to cite your excellent work. Thanks!
Hi toby ,
Can you kindly share your version of the repo for ActivityNet dataset in this email : [email protected] if possible ?
from wtal-uncertainty-modeling.
Hi @Pilhyeon, thanks for your great work! Now I'm following your BMUE and have some trouble in reproducing the results on ActivityNet dataset.
I have tried to do some experiments on ActivityNet v1.2. I downloaded the I3D features provided by this link and adapt them to BMUE format. The following are some of my results. All experiments run for 6k epochs, the results are showed in the form of "(average_mAP, Test_acc)":
- [no params changed] (0.0390, 0.43)
According to Sec 4.1 in your arXiv paper, T=50, so I set num_segments as 50 and do the following experiments:
[num_segments: 50] (0.0275, 0.31)
- [class_th: 0.1] (0.0332, 0.36)
- [class_th: 0.1, act_thresh_cas: np.arange(0.0, 0.15, 0.015)] (0.0400, 0.36)
Besides, I also tried to change "act_thresh_magnitudes", "NMS thresh", "alpha", "_lambda & gamma in get_proposal_oic()", etc. The results don't seem to get better: the test accuracy is around 0.4 and the average_mAP is very low. It's hard for me to find the best settings. Could you please share your params settings on ActivityNet 1.2 & 1.3 datasets? Or give me some advice on which params to change?
Looking forward to your reply and I'd be glad to cite your excellent work. Thanks!
hi @tobbysong, have you got the better result after you set the hyperparameters as mentioned?
from wtal-uncertainty-modeling.
@xumh-9 @cecilia930426 @sauradip
ActivityNet1.2 from W-TALC github.
ActivityNet1.3 from A2CL-PT github.
from wtal-uncertainty-modeling.
how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'?
Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3?
That will very helpful. @Pilhyeon
from wtal-uncertainty-modeling.
how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'?
Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3?
That will very helpful.@kiwiJ
Hi, could you reproduce the result of 41.8 mAP about THUMOS14 in paper without their pre-trained model?
from wtal-uncertainty-modeling.
how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'?
Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3?
That will very helpful.@kiwiJHi, could you reproduce the result of 41.8 mAP about THUMOS14 in paper without their pre-trained model?
Unfortunately, it's only around 40.0 mAP
from wtal-uncertainty-modeling.
how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'?
Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3?
That will very helpful.@kiwiJHi, could you reproduce the result of 41.8 mAP about THUMOS14 in paper without their pre-trained model?
Unfortunately, it's only around 40.0 mAP
The best result I got is 40.2, I sent email to author, but he cannot provide any training log and told me the random seed is unknown for the best result...I have tried many random seed but it did not work...
from wtal-uncertainty-modeling.
how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'?
Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3?
That will very helpful.@kiwiJHi, could you reproduce the result of 41.8 mAP about THUMOS14 in paper without their pre-trained model?
Unfortunately, it's only around 40.0 mAP
The best result I got is 40.2, I sent email to author, but he cannot provide any training log and told me the random seed is unknown for the best result...I have tried many random seed but it did not work...
Me too. I run the code and only get the result of 40.2 mAP about THUMOS14.
from wtal-uncertainty-modeling.
how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'?
Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3?
That will very helpful.@kiwiJHi, could you reproduce the result of 41.8 mAP about THUMOS14 in paper without their pre-trained model?
Unfortunately, it's only around 40.0 mAP
The best result I got is 40.2, I sent email to author, but he cannot provide any training log and told me the random seed is unknown for the best result...I have tried many random seed but it did not work...
Me too. I run the code and only get the result of 40.2 mAP about THUMOS14.
Me too. Has anyone reproduced the reported performance?
from wtal-uncertainty-modeling.
Related Issues (20)
- > Can't reproduce the result? HOT 11
- Results of your provided pre-trained model HOT 2
- Cannot get provided feature. HOT 1
- Some questions in your paper HOT 6
- questions about thumos feature HOT 1
- Why there is a dropout when generate pseudo action features? HOT 1
- Act1.2 and act1.3 feature? HOT 1
- Can anyone reproduce the results in the paper?
- hi, about test code -upsample and down HOT 1
- GPU utilization is low HOT 1
- How long is the training time HOT 2
- How to get WUM_result_numpy
- Why choose softmax as the activation function instead of sigmoid? HOT 2
- Dataloader of ActivityNet 1.3
- An Error implement about `nms` HOT 3
- Confusion of proposal HOT 2
- question about feat_magnitudes
- Question about Figure 2 in paper. HOT 2
- ActivityNet 1.3 Features and model HOT 1
- the newest result HOT 1
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 wtal-uncertainty-modeling.