You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
daiao
9c9ba6554a
|
4 years ago | |
---|---|---|
__pycache__ | 4 years ago | |
cfg | 4 years ago | |
data | 4 years ago | |
det | 4 years ago | |
imgs | 4 years ago | |
.gitignore | 4 years ago | |
LICENSE | 4 years ago | |
README.md | 4 years ago | |
darknet.py | 4 years ago | |
detect.py | 4 years ago | |
dog-cycle-car.png | 4 years ago | |
pallete | 4 years ago | |
util.py | 4 years ago | |
video.py | 4 years ago |
README.md
YOLO_v3_PyTorch
代码实现
- 创建 YOLOv3 网络层级☑
- 实现网络的前向传播☑
- objectness 置信度阈值和非极大值抑制☑
- 设计输入和输出管道☑
- 在视频/网络摄像头上运行检测器☑
背景知识
- 卷积神经网络的工作原理,包括残差块、跳过连接和上采样;
- 目标检测、边界框回归、IoU 和非极大值抑制(NMS);
- 基础的 PyTorch 使用,会创建简单的神经网络;
- 阅读 YOLO 三篇论文,了解 YOLO 的工作原理。
版本条件
- Ubuntu 16.04LTS(64-bit)
- Python 3.6.5(pip3)
- torch 0.4.0(cpu)
- OpenCV 3.4.2
安装指南
- git clone https://testgitea.educoder.net/daiao/YOLO_v3_PyTorch.git
- cd YOLO_v3_PyTorch
- wget https://pjreddie.com/media/files/yolov3.weights
- python detect.py
tips
- 提前将需要检测的图片放入 imgs 文件夹下
- 检测结果图片将被保存在 det 文件夹下