YangZeyu95/unofficial-implement-of-openpose：使用 Tensorflow 实现 Openpose

项目介绍

YangZeyu95/unofficial-implement-of-openpose 是一个托管在 GitHub 上的开源项目，主要使用 Python 编写，目前获得 271 个 Star、79 次 Fork。

仓库全名: YangZeyu95/unofficial-implement-of-openpose

README 摘要

Unofficial-Implement-of-Openpose You can check the full result on YouTube or bilibili An easy implement of openpose using TensorFlow. Only basic python is used, so the code is easy to understand. You can check the graph, internal outputs of every stage and histogram of every layer in tensorboard. Original Repo(Caffe) : https://github.com/CMU-Perceptual-Computing-Lab/openpose. The Dataloader and Post-processing code…

完整内容见 GitHub 原始 README 或本页。

常见问题

unofficial-implement-of-openpose 用什么语言开发？

主要使用 Python 编写，目前有 271 个 Star。

如何获取 unofficial-implement-of-openpose 的源码？

可以直接克隆仓库：git clone https://github.com/YangZeyu95/unofficial-implement-of-openpose.git；安装与运行步骤见仓库 README。

unofficial-implement-of-openpose 最近还在维护吗？

仓库最近一次更新为 2021年3月12日，当前有 31 个未关闭 Issue；Star 数为 271，可作为社区活跃度的参考。

关于

GitHub 原始描述（英文）

Implement of Openpose use Tensorflow

deep-learning deep-neural-networks openpose pose-estimation tensorflow vgg

271 Stars
79 Forks
271 Watching

描述取自 GitHub 官方 API，保持仓库作者书写的原文。

简要分析

热度分

700

价值分

211

活跃状态

活跃

GitHub

Unofficial-Implement-of-Openpose

You can check the full result on YouTube or bilibili

An easy implement of openpose using TensorFlow.

Only basic python is used, so the code is easy to understand.

You can check the graph, internal outputs of every stage and histogram of every layer in tensorboard.

Original Repo(Caffe) : https://github.com/CMU-Perceptual-Computing-Lab/openpose.

The Dataloader and Post-processing code is from tf-pose-estimation.

Python 3.6

Training

Download vgg19 weights file here or 链接: https://pan.baidu.com/s/1t6iouKeDZBZRRg4BXsv5GA 提取码: 4k1w and uzip to ‘checkpoints/vgg/’ (please create the path yourself).
Download COCO2017: 2017 Train images, 2017 Val images and 2017 Train/Val annotations here.
make sure have this structure:
-COCO/
　-images/
　　-train2017/
　　-val2017/
　-annotations/
Specify ‘–annot_path_train’ and ‘–img_path_train’ in train.py to your own ‘COCO/annotations/’ and ‘COCO/images/’.
run train.py python train.py and install requirements follow the error and run again.

Test

Specify --checkpoint_path to the folder includes checkpoint files in run.py.

running on webcam python run.py
running on video python run.py --video images/video.avi
running on imagepython run.py --image images/ski.jpg

pretrained model on COCO 2017 is available here or 链接: https://pan.baidu.com/s/1jcwRsOuEaveZRBU50lP_cQ 提取码: mqkr, this checkpoint includes fine-tuned vgg weights.

暂无评论

unofficial-implement-of-openpose