Comments (2)
Thanks for your interest in our work.
frame/video_test_0000131/ 1 0 1
frame/video_test_0000131/ 5 0 1
In this case, actually the first clip read by C3D is from 1 to 16 and the second clip to be read is 5-20.
from scnn.
Hi,zhengshou
Thank you for your replying.I'm so sorry to trouble you again. I'm very interested in your work. So I have some questiones of how to prepare the training lst of the proposal networks and the details of the training procedures.
I write the code to generate the lst, but I think there maybe some misunderstanding.
Fisrst of all, in my code, for the all videos (trimmed videos and untrimmed videos), I have conduct the sliding windows,and set the label of every segments of the trimmed videos to 1(positive label), and set the instance of the untrimmed videos to 1(positive label),and the background to 0(negative label). Am I right?
If I am right, there are a lot of rows, at least 100k rows in the lst. But as mentioned in your paper, all three stages, the training itrations are 30k. So I think my code to generate the training lst is wrong.
So, my questiones as follows
1 how to use the trimmed videos, do I need to use the sliding windows to the trimmed windows? If not , how to generate the trianing lst of the trimmed videos?
2 For the untrimmed videoes, as the videos are more longer than the trimmed videos, and there will be a lot of segments for each videos, do I need to use them all? here is my lst sample
BaseballPitch/v_BaseballPitch_g25_c07/ 73 1 2
BaseballPitch/v_BaseballPitch_g25_c07/ 81 1 2
BaseballPitch/v_BaseballPitch_g25_c07/ 1 1 4
BaseballPitch/v_BaseballPitch_g25_c07/ 17 1 4
BaseballPitch/v_BaseballPitch_g25_c07/ 33 1 4
BaseballPitch/v_BaseballPitch_g25_c07/ 49 1 4
BaseballPitch/video_validation_0000266/ 1 0 1
BaseballPitch/video_validation_0000266/ 5 0 1
BaseballPitch/video_validation_0000266/ 9 0 1
BaseballPitch/video_validation_0000266/ 13 0 1
BaseballPitch/video_validation_0000266/ 17 0 1
BaseballPitch/video_validation_0000266/ 21 0 1
BaseballPitch/video_validation_0000266/ 25 0 1
BaseballPitch/video_validation_0000266/ 29 0 1
BaseballPitch/video_validation_0000266/ 33 0 1
BaseballPitch/video_validation_0000266/ 37 0 1
please help me to check out is there some mistakes in my lst.
hope your reply,thanks
best wishes
Tim
from scnn.
Related Issues (20)
- demo problem HOT 2
- experiment/THUMOS14/network_proposal/result/res_seg_swin.mat HOT 3
- issue about demo result HOT 1
- Changes to VideoDataLayer break test cases for C3D HOT 1
- extract_image_features.bin HOT 3
- The question about eval result HOT 2
- Question of the training details of training my own models
- Possible to share the results file for THUMOS14 test? HOT 2
- Cannot use C3D v1.1 for demo HOT 3
- prob files in pred/pro/output/ are not created HOT 5
- the outputs of proposal network (probabilities of proposals) are same and very low HOT 1
- MEXaction2 HOT 1
- run demo problem about 000001.prob
- Why not use cls network in prediction?
- how windows 10 ?
- !@
- Bug in run_demo.py at line 194.
- label tool
- The pretrained model URL has no content
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 scnn.