vhad/openpose
1
0
Fork 0
mirror of https://github.com/gosticks/openpose.git synced 2026-08-16 22:30:19 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Added CMake info in installer.md

Browse Source
This commit is contained in:
gineshidalgo99
2017-09-19 23:32:11 -04:00
parent 134b3e930d
commit d423db5fa1
6 changed files with 27 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -61,7 +61,7 @@ OpenPose is a **library for real-time multi-person keypoint detection and multi-
## Introduction
OpenPose represents the **first real-time system to jointly detect human body, hand and facial keypoints (in total 130 keypoints) on single images**. In addition, the system computational performance on body keypoint estimation is invariant to the number of detected people in the image. It uses Caffe, but it could easily be ported to other frameworks (Tensorflow, Torch, etc.). If you implement any of those, feel free to make a pull request!
OpenPose is authored by [Gines Hidalgo](http://gines-hidalgo.site123.me/), [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/). In addition, it is being maintained by [Gines Hidalgo](http://gines-hidalgo.site123.me/) and [Bikramjot Singh Hanzra](https://www.linkedin.com/in/bikz05).
OpenPose is authored by [Gines Hidalgo](http://gines-hidalgo.site123.me/), [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/). In addition, it is being maintained by [Gines Hidalgo](http://gines-hidalgo.site123.me/) and [Bikramjot Hanzra](https://www.linkedin.com/in/bikz05).
It is freely available for free non-commercial use, and may be redistributed under these conditions. Please, see the [license](LICENSE) for further details. [Interested in a commercial license? Check this link](https://flintbox.com/public/project/47343/). For commercial queries, contact [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/).
doc/contributors.md
+1 -1
View File
@@ -11,5 +11,5 @@ OpenPose is authored by [Gines Hidalgo](https://www.linkedin.com/in/gineshidalgo
### Contributors
We would also like to thank the following people who have highly contributed to OpenPose:
1. [Bikramjot Singh Hanzra](https://www.linkedin.com/in/bikz05): OpenPose maintainer and CMake version creator.
1. [Bikramjot Hanzra](https://www.linkedin.com/in/bikz05): OpenPose maintainer and CMake version creator.
2. [Helen Medina](https://github.com/helen-medina): Windows version creator.
doc/installation.md
+6 -1
View File
@@ -48,8 +48,13 @@ OpenPose can be easily updated by clicking the `synchronization` button at the t
## Ubuntu
### Installation - CMake
Recommended installation method. It is simpler and it offers many more customization settings. See [doc/installation_cmake.md](/installation_cmake.md). Note that it is a beta version, if it fails, please post in GitHub and use [Installation - Script Compilation](#installation---script-compilation) meanwhile.
### Installation - Script Compilation
**Highly important**: This script only works with CUDA 8 and Ubuntu 14 or 16. Otherwise, check [Manual Compilation](#manual-compilation).
**Highly important**: This script only works with CUDA 8 and Ubuntu 14 or 16. Otherwise, see [doc/installation_cmake.md](/installation_cmake.md) or [Installation - Manual Compilation](#installation---manual-compilation).
1. Required: CUDA, cuDNN, OpenCV and Atlas must be already installed on your machine.
1. [CUDA](https://developer.nvidia.com/cuda-downloads) must be installed. You should reboot your machine after installing CUDA.
2. [cuDNN](https://developer.nvidia.com/cudnn): Once you have downloaded it, just unzip it and copy (merge) the contents on the CUDA folder, e.g. `/usr/local/cuda-8.0/`. Note: We found OpenPose working ~10% faster with cuDNN 5.1 compared to cuDNN 6. Otherwise, check [Compiling without cuDNN](#compiling-without-cudnn).
doc/installation_cmake.md
+11 -17
View File
@@ -1,12 +1,11 @@
OpenPose - Installation using CMake
====================================
The CMake installation is experimental. It will eventually replace the standard and current installation system, but at the moment it is a beta version.
## Contents
1. [Requirements](#requirements)
2. [Clone and Update the Repository](#clone-and-update-the-repository)
3. [Installation](#installation)
1. [Operating Systems](#operating-systems)
2. [Requirements](#requirements)
3. [Clone and Update the Repository](#clone-and-update-the-repository)
4. [Installation](#installation)
1. [Caffe Prerequisites (Ubuntu Only)](#caffe-prerequisites-ubuntu-only)
2. [OpenPose Configuration](#openpose-configuration)
3. [OpenPose Building](#openpose-building)
@@ -20,23 +19,18 @@ The CMake installation is experimental. It will eventually replace the standard
## Requirements
- Ubuntu (tested on 14 and 16). Windows CMake version will come soon.
- NVIDIA graphics card with at least 1.6 GB available (the `nvidia-smi` command checks the available GPU memory in Ubuntu).
- At least 2 GB of free RAM memory.
- Highly recommended: A CPU with at least 8 cores.
## Operating Systems
- **Ubuntu** 14 and 16.
Note: These requirements assume the default configuration (i.e. `--net_resolution "656x368"` and `scale_number 1`). You might need more (with a greater net resolution and/or number of scales) or less resources (with smaller net resolution and/or using the MPI and MPI_4 models).
## Requirements
See [doc/quick_start.md#requirements](./quick_start.md#requirements).
## Clone and Update the Repository
The first step is to clone the OpenPose repository. It might be done with [GitHub Desktop](https://desktop.github.com/) in Windows and from the terminal in Ubuntu:
```bash
git clone https://github.com/CMU-Perceptual-Computing-Lab/openpose
```
OpenPose can be easily updated by clicking the `synchronization` button at the top-right part in GitHub Desktop in Windows, or by running `git pull origin master` in Ubuntu. After OpenPose has been updated, just run the [Reinstallation](#reinstallation) section described below for your specific Operating System.
See [doc/quick_start.md#clone-and-update-the-repository](./quick_start.md#clone-and-update-the-repository).
doc/release_notes.md
+5 -4
View File
@@ -102,10 +102,11 @@ OpenPose Library - Release Notes
## Current version (future OpenPose 1.0.3)
## Current version (future OpenPose 1.1.0)
1. Main improvements:
1. Added how to use keypoint data in `examples/tutorial_wrapper/`.
2. Added flag for warnings of type `-Wsign-compare` and removed in code.
3. Slightly improved accuracy by considering ears-shoulder connection (e.g. 0.4 mAP for 1 scale in validation set).
1. Added CMake installer for Ubuntu.
2. Added how to use keypoint data in `examples/tutorial_wrapper/`.
3. Added flag for warnings of type `-Wsign-compare` and removed in code.
4. Slightly improved accuracy by considering ears-shoulder connection (e.g. 0.4 mAP for 1 scale in validation set).
2. Main bugs fixed:
1. Windows version crashing with std::map copy.
examples/tests/pose_accuracy_coco_test.sh
+3 -3
View File
@@ -17,11 +17,11 @@ clear && clear
# Parameters
IMAGE_FOLDER=/home/gines/devel/images/val2014/
$JSON_FOLDER=../evaluation/coco/results/openpose/
JSON_FOLDER=../evaluation/coco/results/openpose/
OP_BIN=./build/examples/openpose/openpose.bin
# 1 scale
$OP_BIN --image_dir $IMAGE_FOLDER --write_coco_json ${JSON_FOLDER}1_test.json --no_display --render_pose 0 --frame_last 3558
$OP_BIN --image_dir $IMAGE_FOLDER --write_coco_json ${JSON_FOLDER}1.json --no_display --render_pose 0 --frame_last 3558
# # 3 scales
# $OP_BIN --image_dir $IMAGE_FOLDER --write_coco_json ${JSON_FOLDER}1_3.json --no_display --render_pose 0 --scale_number 3 --scale_gap 0.25 --frame_last 3558
@@ -30,4 +30,4 @@ $OP_BIN --image_dir $IMAGE_FOLDER --write_coco_json ${JSON_FOLDER}1_test.json --
# $OP_BIN --num_gpu 1 --image_dir $IMAGE_FOLDER --write_coco_json ${JSON_FOLDER}1_4.json --no_display --render_pose 0 --num_gpu 1 --scale_number 4 --scale_gap 0.25 --net_resolution "1312x736" --frame_last 3558
# Debugging - Rendered frames saved
# $OP_BIN --image_dir $IMAGE_FOLDER --write_images ${JSON_FOLDER}frameOutput --no_display
# $OP_BIN --image_dir $IMAGE_FOLDER --write_images ${JSON_FOLDER}frameOutput --no_display