https://github.com/vietanhdev/deep-human-pose

https://github.com/vietanhdev/deep-human-pose

Last synced: 10 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/vietanhdev/deep-human-pose
• Owner: vietanhdev
• Created: 2020-11-17T06:16:56.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-11-27T10:20:56.000Z (over 5 years ago)
• Last Synced: 2025-03-02T19:33:09.874Z (over 1 year ago)
• Language: Python
• Size: 22.4 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Deep Human Pose

## I. Introduction

- Human keypoint detection.

## II. Environment:

- We use Tensorflow 2.0.0.

- Install environment from `environment.yml` file using Anaconda and Miniconda and activate that environment.

## III. Training and testing

### Training

- Modify config files at `config_shufflenetv2.json` and `config_efficientnet.json` to use for training and testing.

- Example of commands for training:

```

python train.py -c config_shufflenetv2.json

```

Or 

```

python train.py -c config_efficientnet.json

```

### Testing

```

python test.py -c config_shufflenetv2.json

```

Or 

```

python test.py -c config_efficientnet.json

```

### References

- MPII dataset to json: https://raw.githubusercontent.com/mitmul/deeppose/master/datasets/mpii_dataset.py.