Comments (5)
1, We failed to train one model to work fine for many other datasets.
2, SBR could help in this case, but we found that SBR is sensitive to many aspects, such as hyper-parameters and resolution. It would cost much time to tune it in another dataset/model.
3, Since different videos may have different LK iterations to converge, it is not that straightforward to implement it by batch.
from landmark-detection.
Thank you for your reply!
- Could you please confirm that you failed to train the model by the way you mentioned in the following issue?
You need to retrain the model on another video. If you want to use the trained model on any video, it requires to train this model on a very large number of videos.
Originally posted by @D-X-Y in facebookresearch/supervision-by-registration#40 (comment)
- Could you please share any experience or suggestion on the initialization of the hyper-parameters ? How to decide the value? The training process is very slow, after one epoch the lk loss is almost the same (0.4-0.7), is it normal?
from landmark-detection.
Hi @Jar7 ,
1, Yes, training the model with SBR on the target video is necessary to get a visually good effect.
2, It is hard to give a precise hyper-parameter for me right now. In my experience, I would debug to see the intermedia LK results on the training data, and see whether these hyper-parameters cause many failure cases or not.
from landmark-detection.
Hi @Jar7 ,
1, Yes, training the model with SBR on the target video is necessary to get a visually good effect.2, It is hard to give a precise hyper-parameter for me right now. In my experience, I would debug to see the intermedia LK results on the training data, and see whether these hyper-parameters cause many failure cases or not.
Thank you!
from landmark-detection.
Hi @D-X-Y,
Excuse me, May I have further questions..
I found that the pretrained model cpm_vgg16-epoch-049-050.pth output stable landmarks for demo-sbr.mp4. Has the demo-sbr,mp4 been trained? How many epoch should be trained for each video?
Have you found why a model for any video cannot be trained? Is it because the lk operation is sensitive to the video? If the lkloss is changed to another opt-flow loss, whether another additive loss would help to stabilize the output of backbone?
from landmark-detection.
Related Issues (20)
- Pretrained Model of SRT? HOT 3
- How to divide 300VW-Dataset into 3 categories HOT 1
- lk_target_loss return None, scale of batch_locs? How to set forward_max and fb_thresh? HOT 3
- [SAN/SBR] Problems in point_meta about apply_rotate . HOT 1
- Can someone share the paper SRT? HOT 1
- why dont normalized the network outputs to (0-1)? HOT 6
- Problem about training SBR with 300VW dataset HOT 1
- SRT inference HOT 8
- SBR using for our videos
- training failed in SRT heatmaps? HOT 1
- SRT inference get wrong results HOT 6
- SRT results HOT 1
- SBR inference on new video
- how to get arhuments of --face
- SRT inference on video HOT 2
- [Dataset issues] How to download "Synthetic-Face" dataset? HOT 2
- [feature request] SRT improve video inference
- [feature request] SRT inference on multiview images and videos
- ModuleNotFoundError: No module named 'xvision' HOT 3
- Confuse about "batch_interpolate_flow" function in SRT/lib/sbr/interpolate.py
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 landmark-detection.