vhad/openpose
1
0
Fork 0
mirror of https://github.com/gosticks/openpose.git synced 2026-08-13 21:00:22 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Deploy code docs to GitHub Pages Travis build: 440

Browse Source 
Commit: 72d1992a64
This commit is contained in:
Travis CI
2018-11-29 20:02:23 +00:00
parent 87c7d2f4df
commit fe1edcdbcc
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
html/index.html
+1 -1
View File
@@ -166,7 +166,7 @@ $(document).ready(function(){initNavTree('index.html','');});
<p>&lt;img src="doc/media/dance.gif", width="360"&gt; </p>
<h3>Runtime Analysis</h3>
<p>Inference time comparison between the 3 available pose estimation libraries: OpenPose, Mask R-CNN, and Alpha-Pose (fast Pytorch version): </p>
<p>&lt;img src="doc/media/dance.gif", width="360"&gt; </p>
<p>&lt;img src="doc/media/openpose_vs_competition.png", width="360"&gt; </p>
<p>This analysis was performed using the same images for each algorithm and a batch size of 1. Each analysis was repeated 1000 times and then averaged. This was all performed on a system with a Nvidia 1080 Ti and CUDA 8. Megvii (Face++) and MSRA GitHub repositories were excluded because they only provide pose estimation results given a cropped person. However, they suffer the same problem than Alpha-Pose and Mask R-CNN, their runtimes grow linearly with the number of people.</p>
<h2>Contents</h2>
<ol type="1">