You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: .github/CI_deprecated/Readme_Travis_badges_table_and_backup_instructions.md
+1
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,7 @@
1
1
In order to recover Travis:
2
2
1. Uncomment all the lines of code in ".travis.yml" and move it back to the main folder (e.g., at the same level than the global README.md and CMakeLists.txt files).
Copy file name to clipboardExpand all lines: .github/issue_template.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -82,4 +82,4 @@ Select the topic(s) on your post, delete the rest:
82
82
- Portable demo or compiled library?
83
83
84
84
10. If **speed performance** issue:
85
-
- Report OpenPose timing speed based on [this link](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/speed_up_openpose.md#profiling-speed).
85
+
- Report OpenPose timing speed based on [this link](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/maximizing_openpose_speed.md#profiling-speed).
Copy file name to clipboardExpand all lines: README.md
+5-5
Original file line number
Diff line number
Diff line change
@@ -10,14 +10,14 @@
10
10
11
11
[**OpenPose**](https://github.com/CMU-Perceptual-Computing-Lab/openpose) has represented the **first real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images**.
12
12
13
-
It is **authored by [Gines Hidalgo](https://www.gineshidalgo.com), [Zhe Cao](https://people.eecs.berkeley.edu/~zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Hanbyul Joo](https://jhugestar.github.io), and [Yaser Sheikh](http://www.cs.cmu.edu/~yaser)**, and **maintained by [Gines Hidalgo](https://www.gineshidalgo.com) and [Yaadhav Raaj](https://www.raaj.tech)**. OpenPose would not be possible without the [**CMU Panoptic Studio dataset**](http://domedb.perception.cs.cmu.edu). We would also like to thank all the people who helped OpenPose in any way ([doc/contributors.md](doc/contributors.md)).
13
+
It is **authored by [Ginés Hidalgo](https://www.gineshidalgo.com), [Zhe Cao](https://people.eecs.berkeley.edu/~zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Hanbyul Joo](https://jhugestar.github.io), and [Yaser Sheikh](http://www.cs.cmu.edu/~yaser)**, and **maintained by [Ginés Hidalgo](https://www.gineshidalgo.com) and [Yaadhav Raaj](https://www.raaj.tech)**. OpenPose would not be possible without the [**CMU Panoptic Studio dataset**](http://domedb.perception.cs.cmu.edu). We would also like to thank all the people who helped OpenPose in any way ([doc/authors_and_contributors.md](doc/authors_and_contributors.md)).
<sup>Authors <a href="https://www.gineshidalgo.com" target="_blank">Gines Hidalgo</a> (left) and <a href="https://jhugestar.github.io" target="_blank">Hanbyul Joo</a> (right) in front of the <a href="http://domedb.perception.cs.cmu.edu" target="_blank">CMU Panoptic Studio</a></sup>
20
+
<sup>Authors <a href="https://www.gineshidalgo.com" target="_blank">Ginés Hidalgo</a> (left) and <a href="https://jhugestar.github.io" target="_blank">Hanbyul Joo</a> (right) in front of the <a href="http://domedb.perception.cs.cmu.edu" target="_blank">CMU Panoptic Studio</a></sup>
21
21
</p>
22
22
23
23
@@ -54,7 +54,7 @@ It is **authored by [Gines Hidalgo](https://www.gineshidalgo.com), [Zhe Cao](htt
<sup><a href="http://tianyizhao.com" target="_blank">Tianyi Zhao</a> and <a href="https://www.gineshidalgo.com" target="_blank">Gines Hidalgo</a> testing the <a href="https://github.com/CMU-Perceptual-Computing-Lab/openpose_unity_plugin" target="_blank">OpenPose Unity Plugin</a></sup>
66
+
<sup><a href="http://tianyizhao.com" target="_blank">Tianyi Zhao</a> and <a href="https://www.gineshidalgo.com" target="_blank">Ginés Hidalgo</a> testing the <a href="https://github.com/CMU-Perceptual-Computing-Lab/openpose_unity_plugin" target="_blank">OpenPose Unity Plugin</a></sup>
67
67
</p>
68
68
69
69
### Runtime Analysis
@@ -94,7 +94,7 @@ We show an inference time comparison between the 3 available pose estimation lib
94
94
-[**Command-line demo**](doc/demo_quick_start.md) for built-in functionality.
95
95
-[**C++ API**](examples/tutorial_api_cpp/) and [**Python API**](doc/python_api.md) for custom functionality. E.g., adding your custom inputs, pre-processing, post-posprocessing, and output steps.
96
96
97
-
For further details, check [all released features](doc/released_features.md) and [release notes](doc/release_notes.md).
97
+
For further details, check the [major released features](doc/major_released_features.md) and [release notes](doc/release_notes.md) docs.
Copy file name to clipboardExpand all lines: doc/README.md
+2-2
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose - Quick Start
1
+
OpenPose Doc
2
2
==========================
3
3
4
4
Most users can simply use the OpenPose Demo without reading any C++/Python code. Users that need to add additional functionality (new inputs, outputs, etc) should check the C++/Python APIs:
- You should be familiar with the [**OpenPose Demo**](demo_quick_start.md) and the main OpenPose flags before trying to read the C++ or Python API examples. Otherwise, it will be way harder to follow.
26
26
- For quick prototyping: You can simply duplicate and rename any of the [existing example files](../examples/tutorial_api_python/) within that same folder.
27
27
28
-
-[**Speeding up OpenPose and benchmark**](speed_up_openpose.md): Check the OpenPose Benchmark as well as some hints to speed up and/or reduce the memory requirements for OpenPose.
28
+
-[**Speeding up OpenPose and benchmark**](maximizing_openpose_speed.md): Check the OpenPose Benchmark as well as some hints to speed up and/or reduce the memory requirements for OpenPose.
29
29
30
30
-[**Calibration toolbox**](advanced/calibration_module.md) and [**3D OpenPose**](advanced/3d_reconstruction_module.md): Calibrate your cameras for 3D OpenPose (or any other stereo vision tasks) and start obtaining 3D keypoints!
Copy file name to clipboardExpand all lines: doc/advanced/library_structure/README.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose C++ API - Introduction
1
+
OpenPose Doc - Advanced Doc - Library Structure
2
2
====================================
3
3
4
4
As a user, you do not need to know anything about this section! This section is intended for OpenPose internal developpers. It is exposed publicly, but you can skip this whole folder if you are just trying to use OpenPose or create new code/demos using OpenPose.
Copy file name to clipboardExpand all lines: doc/advanced/standalone_face_or_hand_keypoint_detector.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose - Standalone Face Or Hand Keypoint Detector
1
+
OpenPose Doc - Advanced Doc - Standalone Face Or Hand Keypoint Detector
2
2
====================================
3
3
4
4
In case of hand camera views at which the hands are visible but not the rest of the body, or if you do not need the body keypoint detector and want to speed up the process, you can use the OpenPose face or hand keypoint detectors with your own face or hand detectors, rather than using the body keypoint detector as initial detector for those.
Copy file name to clipboardExpand all lines: doc/authors_and_contributors.md
+2-4
Original file line number
Diff line number
Diff line change
@@ -1,12 +1,10 @@
1
-
OpenPose - Authors and Contributors
1
+
OpenPose Doc - Authors and Contributors
2
2
====================================
3
3
4
4
5
5
6
6
### Authors
7
-
OpenPose is authored by [Gines Hidalgo](https://www.gineshidalgo.com/), [Zhe Cao](http://www.andrew.cmu.edu/user/zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon/), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Hanbyul Joo](http://www.cs.cmu.edu/~hanbyulj/), and [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/).
8
-
9
-
The body pose estimation work is based on the following and original 2 repositories: [CVPR 2017 repository](https://github.com/ZheC/Multi-Person-Pose-Estimation) and [ECCV 2016 repository](https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose).
7
+
OpenPose is authored by [Ginés Hidalgo](https://www.gineshidalgo.com/), [Zhe Cao](http://www.andrew.cmu.edu/user/zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon/), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Hanbyul Joo](http://www.cs.cmu.edu/~hanbyulj/), and [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/). The body pose estimation work is based on the following and original 2 repositories: [CVPR 2017 repository](https://github.com/ZheC/Multi-Person-Pose-Estimation) and [ECCV 2016 repository](https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose).
Copy file name to clipboardExpand all lines: doc/demo_not_quick_start.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose Demo - Not Quick Start
1
+
OpenPose Doc - Demo - Not Quick Start
2
2
====================================
3
3
4
4
This document is a more detailed continuation of [doc/demo_quick_start.md](demo_quick_start.md), and it assumes the user is quite familiar with the OpenPose demo and the contents of [doc/demo_quick_start.md](demo_quick_start.md).
Copy file name to clipboardExpand all lines: doc/demo_quick_start.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose Demo - Quick Start
1
+
OpenPose Doc - Demo - Quick Start
2
2
====================================
3
3
4
4
Forget about the OpenPose code, just download the portable Windows binaries (or compile the code from source) and use the demo by following this tutorial!
**Q: Low speed** - OpenPose is quite slow, is it normal? How can I speed it up?
209
209
210
-
**A**: Check [doc/speed_up_openpose.md](speed_up_openpose.md) to discover the approximate speed of your graphics card and some speed tips.
210
+
**A**: Check [doc/maximizing_openpose_speed.md](maximizing_openpose_speed.md) to discover the approximate speed of your graphics card and some speed tips.
211
211
212
212
213
213
214
214
#### How to Measure the Latency Time?
215
215
**Q: How to measure/calculate/estimate the latency/lag time?**
216
216
217
-
**A**: [Profile](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/speed_up_openpose.md#profiling-speed) the OpenPose speed. For 1-GPU or CPU-only systems (use `--disable_multi_thread` for simplicity in multi-GPU systems for latency measurement), the latency will be roughly the sum of all the reported measurements.
217
+
**A**: [Profile](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/maximizing_openpose_speed.md#profiling-speed) the OpenPose speed. For 1-GPU or CPU-only systems (use `--disable_multi_thread` for simplicity in multi-GPU systems for latency measurement), the latency will be roughly the sum of all the reported measurements.
218
218
219
219
220
220
221
221
#### CPU Version Too Slow
222
222
**Q: The CPU version is insanely slow compared to the GPU version.**
223
223
224
-
**A**: Check [doc/speed_up_openpose.md#cpu-version](speed_up_openpose.md#cpu-version) to discover the approximate speed and some speed tips.
224
+
**A**: Check [doc/maximizing_openpose_speed.md#cpu-version](maximizing_openpose_speed.md#cpu-version) to discover the approximate speed and some speed tips.
225
225
226
226
227
227
228
228
#### Profiling Speed and Estimating FPS without Display
229
-
Check the [doc/speed_up_openpose.md#profiling-speed](speed_up_openpose.md#profiling-speed) section.
229
+
Check the [doc/maximizing_openpose_speed.md#profiling-speed](maximizing_openpose_speed.md#profiling-speed) section.
Copy file name to clipboardExpand all lines: doc/installation/README.md
+4-4
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose - Installation
1
+
OpenPose Doc - Installation
2
2
==========================
3
3
4
4
## Contents
@@ -132,7 +132,7 @@ cmake-gui ..
132
132
133
133
5. Set the `GPU_MODE` flag to the proper value and click `Configure` again:
134
134
1. If your machine has an Nvidia GPU, you should most probably not modify this flag and skip this step. Cases in which you might have to change it:
135
-
- If you have a Nvidia GPU with 2GB of memory or less: Then you will have to follow some of the tricks in [doc/speed_up_openpose.md](../speed_up_openpose.md) or change `GPU_MODE` back to `CPU_ONLY`.
135
+
- If you have a Nvidia GPU with 2GB of memory or less: Then you will have to follow some of the tricks in [doc/maximizing_openpose_speed.md](../maximizing_openpose_speed.md) or change `GPU_MODE` back to `CPU_ONLY`.
136
136
- If you cannot install CUDA, then you can also set `GPU_MODE` to `CPU_ONLY`.
137
137
2. Mac OSX and machines with a non-Nvidia GPU (Intel or AMD GPUs): Set the `GPU_MODE` flag to `CPU_ONLY` (easier to install but slower runtime) or `OPENCL` (GPU-accelerated, it is harder to install but provides a faster runtime speed). For more details on OpenCV support, see [doc/prerequisites.md](prerequisites.md) and [OpenCL Version](#opencl-version).
138
138
3. If your machine does not have any GPU, set the `GPU_MODE` flag to `CPU_ONLY`.
@@ -276,7 +276,7 @@ See [doc/advanced/deployment.md](../advanced/deployment.md).
276
276
277
277
278
278
### Maximum Speed
279
-
Check the OpenPose Benchmark as well as some hints to speed up and/or reduce the memory requirements to run OpenPose on [doc/speed_up_openpose.md](../speed_up_openpose.md).
279
+
Check the OpenPose Benchmark as well as some hints to speed up and/or reduce the memory requirements to run OpenPose on [doc/maximizing_openpose_speed.md](../maximizing_openpose_speed.md).
280
280
281
281
282
282
@@ -297,7 +297,7 @@ export MKL_NUM_THREADS="8"
297
297
export OMP_NUM_THREADS="8"
298
298
```
299
299
300
-
Increasing the number of threads results in a higher RAM memory usage. You can check the [doc/speed_up_openpose.md](../speed_up_openpose.md) for more information about speed and memory requirements in several CPUs and GPUs.
300
+
Increasing the number of threads results in a higher RAM memory usage. You can check the [doc/maximizing_openpose_speed.md](../maximizing_openpose_speed.md) for more information about speed and memory requirements in several CPUs and GPUs.
Copy file name to clipboardExpand all lines: doc/installation/jetson_tx/installation_jetson_tx1.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
OpenPose - Installation on Nvidia Jetson TX1
1
+
OpenPose Doc - Installation - Installation on Nvidia Jetson TX1
2
2
====================================
3
3
## Introduction
4
4
We do not officially support TX1, but thanks to @dreinsdo, we have these instructions about how he made it work in his TX1. We would like to thank @dreinsdo, who added this documentation in [this GitHub issue post](https://github.com/CMU-Perceptual-Computing-Lab/openpose/issues/1124#issuecomment-474090671). If you face any issue, feel free to post on that issue post.
Note that OpenPose for Nvidia Jetson TX2 was developed and it is maintained by the community. The OpenPose authors will not be able to provide official support for it.
Note that OpenPose for Nvidia Jetson TX2 was developed and it is maintained by the community. The OpenPose authors will not be able to provide official support for it.
0 commit comments