https://github.com/liushuan/YOLO-V3-Tensorflow2.0-Face-Detect-via-Wider-Face

使用 TensorFlow2.0 训练YOLOV3模型 和Wider Face 数据集，进行人脸检测
https://github.com/liushuan/YOLO-V3-Tensorflow2.0-Face-Detect-via-Wider-Face

Last synced: 3 months ago
JSON representation

使用 TensorFlow2.0 训练YOLOV3模型 和Wider Face 数据集，进行人脸检测

• Host: GitHub
• URL: https://github.com/liushuan/YOLO-V3-Tensorflow2.0-Face-Detect-via-Wider-Face
• Owner: liushuan
• Created: 2019-07-25T02:22:27.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2023-03-25T00:19:23.000Z (almost 2 years ago)
• Last Synced: 2024-08-02T19:01:54.396Z (6 months ago)
• Language: Python
• Size: 5.46 MB
• Stars: 21
• Watchers: 1
• Forks: 9
• Open Issues: 5
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Tensorflow2 - liushuan/YOLO-V3-Tensorflow2.0-Face-Detect-via-Wider-Face

README

        
# TensorFlow2.x-YOLOv3

A minimal tensorflow implementation of YOLOv3, with support for training, inference and evaluation.

## Installation

Install requirements and download pretrained weights

```

$ pip3 install -r ./docs/requirements.txt

$ wget https://pjreddie.com/media/files/yolov3.weights

```

## Quick start

In this part, we will use pretrained weights to make predictions on both image and video.

```

$ python image_demo.py

$ python video_demo.py # if use camera, set video_path = 0

```

![image](./docs/kite_result.jpg)

## Train yymnist

Download [yymnist](https://github.com/YunYang1994/yymnist) dataset and make data.

```

$ git clone https://github.com/YunYang1994/yymnist.git

$ python yymnist/make_data.py --images_num 1000 --images_path ./data/dataset/train --labels_txt ./data/dataset/yymnist_train.txt

$ python yymnist/make_data.py --images_num 200  --images_path ./data/dataset/test  --labels_txt ./data/dataset/yymnist_test.txt

```

Open `./core/config.py` and do some configurations

```

__C.YOLO.CLASSES                = "./data/classes/yymnist.names"

```

Finally, you can train it and then evaluate your model

```

$ python train.py

$ tensorboard --logdir ./data/log

$ python test.py

$ cd ../mAP

$ python main.py        # Detection images are expected to save in `YOLOV3/data/detection`

```

Track training progress in Tensorboard and go to http://localhost:6006/

```

$ tensorboard --logdir ./data/log

```

![image](./docs/loss.png)

| train |test|

|---|---

|![image](./docs/01554.jpg)|![image](./docs/01567.jpg)|