-
Could you share wingloss in train prototxt example like EuclideanLoss
```
layer {
name: "loss"
type: "EuclideanLoss"
bottom: "fc2"
bottom: "label"
top: "loss"
loss_weight: 100
…
-
大佬你好，
请问在用原始的oks loss训练关键点的时候，有些特定的关键点会乱飘，这个怎么解决呀？
-
您好，请问您readme.md中的demo展示是使用哪种backbone得到的结果呢？还有在train过程中仅使用了wing_loss嘛？
-
Hi @github-luffy,
I trained AuxiliaryNet on WFLW data set using WingLoss and loss and failure rate: L1 staturate after 80 Epoch. Does this mean model is converged/generalised?
What was your final lo…
-
Hi sir thanks for the wonderful project. I would like to know if you could provide steps on how to train and test using custom dataset. Thanks
-
There are different approaches on normalizing Mean Error, I would like to know how did you achieve this in your evaluation.
The inter-pupil distance is kind of confuse for me, since 68 landmarks do n…
-
请问在您计算wing loss的时候，作为ground truth的 68个3D人脸点是怎么得到的？
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### YOLOv8 Component
_No response_
### Bug
…
-
## Development Plan 2023
We are excited to announce the release of MMPose 1.0.0 as a part of the OpenMMLab 2.0 project!
MMPose v1.0.0 is a major update, including many API and config file changes,…
Tau-J updated
3 months ago
-
I trained based on your code, while the result is far lower than the paper, can you share your result?