Comments (6)
I reimplement the ssv2 sampling and adjust the training setting accroding to the paper: change the iterations to 30,000 with batch-size 256, the sampling manner is change to TSN style and using 3 spatial crops for testing. The remaining settings are same with K400 as the provided scripts.
However, the VIT-B/16 model only archieves 58.9 top-1 acc on SSv2 (compared with 61.7 acc in the paper ). Do I missing same changes for SSv2 dataset?
from efficient-video-recognition.
I reimplement the ssv2 sampling and adjust the training setting accroding to the paper: change the iterations to 30,000 with batch-size 256, the sampling manner is change to TSN style and using 3 spatial crops for testing. The remaining settings are same with K400 as the provided scripts.
However, the VIT-B/16 model only archieves 58.9 top-1 acc on SSv2 (compared with 61.7 acc in the paper ). Do I missing same changes for SSv2 dataset?
from efficient-video-recognition.
Would you mind letting me know how many input frames and how many decoder layers you are using? 8 frames + 4 decoder layers should obtain similar performance as you reported. We use 12 decoder layers for SSv2 as we found they provide clear improvements (to about 61% accuracy).
from efficient-video-recognition.
I used 16 frames input and 4 layers decoder.
from efficient-video-recognition.
Thanks for your help @linziyi96 .
By changing the input frames to 8, and decoder layers to 12. I got 61.1% top-1 acc on SSv2 dataset.
I run this experiment with bs128, accrodingly changing the lr to 2e-4 and iterations to 60k steps.
from efficient-video-recognition.
Thanks for your help @linziyi96 . By changing the input frames to 8, and decoder layers to 12. I got 61.1% top-1 acc on SSv2 dataset.
I run this experiment with bs128, accrodingly changing the lr to 2e-4 and iterations to 60k steps.
Hello , did you reproduce the experimental results on the k400? The accuracy I got is a bit lower than in the paper(about 3%)
from efficient-video-recognition.
Related Issues (20)
- Is it possible that the Frozen CLIP model saw the validation set of Kinetics HOT 1
- Does action recognition not require the start time and end time? HOT 4
- bug HOT 2
- Ask for finetuning scripts HOT 1
- batchsize vs training iterations HOT 2
- Saved checkpoints corrupted? HOT 4
- Visualization of cross-frame attention maps HOT 1
- 。
- Could you share k600/k700 performance? (EOM)
- Wprev and Wnext in the formula of the cross-attention part of the paper don't seem to make sense
- Error when running with finetune backbone HOT 1
- accuracy of vitB16 and vitL_14
- Using ViT-L-14-336px checkpoint
- About params config
- fix DDP mode saving checkpoint HOT 1
- any plans for adding more comments?
- How to use the CLIP backbone with other dataset?
- Enquiry on the accessibility of SSV2 configs and checkpoints
- train error
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 efficient-video-recognition.