DeepLabCut Networks for 2D Pose Estimation
收藏DataCite Commons2025-01-06 更新2025-04-15 收录
下载链接：
https://dataverse.harvard.edu/citation?persistentId=doi:10.7910/DVN/ACNHMP
下载链接
链接失效反馈官方服务：
资源简介：
<p>
This folder contains trained DeepLabCut networks for 2D pose estimation from multiple viewpoints, as described in this work.
It includes three subfolders, each corresponding to a different network for performing 2D pose estimation on <strong>side</strong> (cam1), <strong>side-front</strong> (cam2), and <strong>front</strong> (cam3) views. We used the same networks for mirror cameras (e.g., the right and left sides).
</p>
<p>
For more details on how to use these networks for 2D pose estimation and how to triangulate them to obtain 3D pose estimation, please visit the <a href="https://github.com/NeLy-EPFL/kinematics3d" target="_blank">NeLy-EPFL/kinematics3d GitHub repository</a>.
</p>
<p>
The accompanying PDF (tracked_keypoints_setup.pdf) provides information about the locations of the tracked points.
</p>
<p>
To uncompress the file, run the following command in the terminal:
</p>
<pre>
$ tar -xvf filename.tgz
</pre>
提供机构：
Harvard Dataverse
创建时间：
2024-12-12
