Skip to content
#

yolov3

Here are 1,309 public repositories matching this topic...

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

  • Updated Jun 1, 2022
  • Python
yfq512
yfq512 commented Nov 30, 2020
    1. 准备数据,制作训练时需要的文件(data文件夹下面的四个文件:数据类名,锚框,训练数据,测试数据)
    1. 根据步骤1修改core/config.py文件
    1. 基于yolo原始权重训练,(或者从头训练)(这步教程写的很清楚)
    1. 当loss为1左右时,模型就已经有效果了,训练过程中会保存很多模型,选择一个loss最小的,并根据所选择的模型名修改freeze_graph.py,修改后运行freeze_graph.py,会在项目根目录生成***.pb文件
    1. 修改demo文件,如修改video_demo.py,修改调用的***.pb文件路径,修改num_class为自己数据类个数
good first issue

Improve this page

Add a description, image, and links to the yolov3 topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the yolov3 topic, visit your repo's landing page and select "manage topics."

Learn more