提交 b467d33c 编写于 作者: Eric.Lee2021's avatar Eric.Lee2021 🚴🏻

update readme about face detect

上级 f9ae67ef
......@@ -25,9 +25,18 @@
* [数据集下载地址(百度网盘 Password: c680 )](https://pan.baidu.com/s/1H0YH8jMEXeIcubLEv0W_yw)
### 2、脸部检测数据集
该项目采用的是开源数据集 WIDERFACE,其下载地址为 http://shuoyang1213.me/WIDERFACE/
```
@inproceedings{yang2016wider,
Author = {Yang, Shuo and Luo, Ping and Loy, Chen Change and Tang, Xiaoou},
Booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
Title = {WIDER FACE: A Face Detection Benchmark},
Year = {2016}}
```
* [该项目制作的训练集的数据集下载地址(百度网盘 Password: r77x )](https://pan.baidu.com/s/1Jsm1qPPzAW46LRW5nUClzQ)
数据格式: size是全图分辨率, (x,y) 是目标物体中心对于全图的归一化坐标,w,h是目标物体边界框对于全图的归一化宽、高。
### 数据格式
size是全图分辨率, (x,y) 是目标物体中心对于全图的归一化坐标,w,h是目标物体边界框对于全图的归一化宽、高。
```
dw = 1./(size[0])
......@@ -53,7 +62,9 @@ Contextual Attention for Hand Detection in the Wild. S. Narasimhaswamy, Z. Wei,
### 1、手部检测预训练模型
* [预训练模型下载地址(百度网盘 Password: 7mk0 )](https://pan.baidu.com/s/1hqzvz0MeFX0EdpWXUV6aFg)
### 2、脸部检测预训练模型
### 2、脸部检测预训练模型
* [预训练模型下载地址(百度网盘 Password: l2a3 )](https://pan.baidu.com/s/1xVtZUMD94DiT9FQQ66xG1A)
## 项目使用方法
......
......@@ -9,8 +9,11 @@ import numpy as np
if __name__ == "__main__":
path='./datasets_fusion_hand_train/anno/train.txt'
path_voc_names = './cfg/hand.names'
# path='./datasets_fusion_hand_train/anno/train.txt'
# path_voc_names = './cfg/hand.names'
path='./yolo_widerface_open_train/anno/train.txt'
path_voc_names = './cfg/face.names'
with open(path_voc_names, 'r') as f:
label_map = f.readlines()
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册