Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Docs] how to set sigmas? #2969

Open
liujingtingdev opened this issue Feb 27, 2024 · 3 comments
Open

[Docs] how to set sigmas? #2969

liujingtingdev opened this issue Feb 27, 2024 · 3 comments
Assignees

Comments

@liujingtingdev
Copy link

📚 The doc issue

I want to fine-tune RTMPose with human3.6m dataset, I use the h36m_to_coco.py code provided by mmpose to generate human3.6 dataset in coco format, how to set sigmas and joint_weights during training, is it the setting h36m.py in config?

Suggest a potential alternative/fix

add this in the fine-tune page

@liujingtingdev
Copy link
Author

I would also like to ask a question, how do I generate the bbox_file required for the top-down model h36m_to_coco.py can only generate annotations files?

@Ben-Louis
Copy link
Collaborator

  1. sigmas and joint_weights should be set in the metainfo file of the dataset
  2. To generate bbox_file, please refer to https://github.com/open-mmlab/mmpose/blob/main/tools/misc/generate_bbox_file.py

@liujingtingdev
Copy link
Author

Thank you very much for your answer, but I encountered a new problem when configuring the environment, and after configuring the environment according to the documentation, I encountered the following problem
02/29 21:28:05 - mmengine - WARNING - mmpose is not installed and its modules will not be registered. If you want to use modules defined in mmpose, Please install mmpose by pip install mmpose. 02/29 21:28:05 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "visualizer" registry tree. As a workaround, the current "visualizer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. Traceback (most recent call last): File "./tools/train.py", line 162, in <module> main() File "./tools/train.py", line 155, in main runner = Runner.from_cfg(cfg) File "C:\Users\sutai\.conda\envs\mymmpose\lib\site-packages\mmengine\runner\runner.py", line 462, in from_cfg runner = cls( File "C:\Users\sutai\.conda\envs\mymmpose\lib\site-packages\mmengine\runner\runner.py", line 416, in __init__ self.visualizer = self.build_visualizer(visualizer) File "C:\Users\sutai\.conda\envs\mymmpose\lib\site-packages\mmengine\runner\runner.py", line 803, in build_visualizer return VISUALIZERS.build(visualizer) File "C:\Users\sutai\.conda\envs\mymmpose\lib\site-packages\mmengine\registry\registry.py", line 570, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "C:\Users\sutai\.conda\envs\mymmpose\lib\site-packages\mmengine\registry\build_functions.py", line 100, in build_from_cfg raise KeyError( KeyError: 'PoseLocalVisualizer is not in the mmengine::visualizer registry. Please check whether the value of PoseLocalVisualizer` is correct or it was registered as expected. More details can be found at https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module'

You can see from the pip list that mmpose has installed version 1.3.1
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants