MT yolov6 training and testing

1、 View virtual environment

conda env list

2、 Delete virtual environment

conda env remove -p  Virtual environment path to delete 

Example

conda env remove -p C:\Users\Admin\anaconda3\envs\pointbert

3、 New virtual environment

conda create -n env python==3.6( Version number )

4、 Activate the virtual environment

conda activate yolo6

5、 Get into yolo6 Folder

cd C:\Users\Admin\Desktop\YOLOv6-main

6、 Environment required for installation

pip install -r requirements.txt

7、 Download weight
https://github.com/meituan/YOLOv6/releases/tag/0.1.0

Put it under the project folder

8、 Yes yolo6 To test

python tools/infer.py --weights yolov6s.pt --source img.jpg / imgdir

Execute the following instructions

python tools/infer.py --weights yolov6s.pt --source data/images

The test results are as follows ：

The test results are in runs\inference\exp Under the folder

9、 The system configuration
see torch edition

see cuda edition
nvcc --versio