Home
Projects
Resources
Alternatives
Blog
Sign In
YOLO V3 IOU
Save
YOLO3 动漫人脸检测 (Based on keras and tensorflow) 2019-1-19
Overview
Reviews
Resources
Project README
YOLO-V3-IOU
YOLO3 动漫人脸检测 2019-1-19
环境
tensorflow-gpu 1.12.0
Keras 2.2.4
注意
如果运行时出现 Blas SGEMM launch failed 错误,请参考https://github.com/qqwweee/keras-yolo3/issues/362
数据集的准备
数据集标签制作工具下载:https://github.com/tzutalin/labelImg
运行prepare.py将数据集划为训练集,验证集和测试集
训练模型
加载权重,将权重h5文件放入models文件夹
最新权重下载地址:https://pan.baidu.com/s/1QKODAhRU_Rw5lpf8NcIR4g
若重新开始训练,将load_pretrained置为False
设置学习率,若重新训练,建议设0.001,若加载权重,建议设较小的学习率
运行train.py
预测
加载权重,将训练好的权重h5文件放入models文件夹
运行run.py,对数据集进行预测输出,输出在outputs文件夹中
预测新的图片
from predict import YOLO
from PIL import Image
yolo = YOLO()
img = Image.open(r'./test.jpg')
output = yolo.detect_image(img)
output.show()
Demo
模型
Open Source Agenda is not affiliated with "YOLO V3 IOU" Project. README Source:
wmylxmj/YOLO-V3-IOU
Stars
128
Open Issues
8
Last Commit
2 years ago
Repository
wmylxmj/YOLO-V3-IOU
License
MIT
Tags
Anime
Cnn
Computer Vision
Deep Learning
Iou
Keras
Object Detection
Real Time
Yolo
Yolov3
Open Source Agenda Badge
Submit Review
Review Your Favorite Project
Submit Resource
Articles, Courses, Videos
Submit Article
Submit a post to our blog
From the blog
Dec 11, 2022
How to Choose Which Programming Language to Learn First?
From the blog
Dec 11, 2022
How to Choose Which Programming Language to Learn First?
Home
Projects
Resources
Alternatives
Blog
Sign In
Sign In to OSA
I agree with
Terms of Service
and
Privacy Policy
Sign In with Github