Comments (1)
Hi!
I have implemented neither 1 nor 2 but I believe it should be quite straightforward to add these features to the code now.
Especially for 1, do you mean that you want the classifier label scores? if yes you can change the backbone and use one which outputs scores instead of features.
For 2: Because the features are densely extracted at a fixed fps, it should be also easy to get the timestamp for each feature.
from video_feature_extractor.
Related Issues (20)
- How can i make csv form i got video path key error !!!!!
- Decoding video - ffprobe failed at: HOT 12
- .
- video
- multi view feature extraction
- Question about feature dimension HOT 2
- I3D or C3D? HOT 7
- same dimensional feature output for all input videos of different lengths HOT 1
- Running fine but feature file not there HOT 1
- Convert numpy to classes (label)
- please advice on the feature
- extract.py gives errors
- Error when runing "python extract.py --csv=input.csv --type=2d --batch_size=64 --num_decoding_thread=1" on windows and linux HOT 5
- Question about input
- Question on output dimension HOT 2
- 3D ReNext101 Feature HOT 3
- Can I extract 3D features per frame? HOT 2
- Data doesn't store properly HOT 8
- regarding requirements HOT 2
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 video_feature_extractor.