yolov5 v6.0版本

[lyc728]

无法进行推理，使用代码无法得到推理结果，保存的图是原图

[Wangwang99999]

I found the reason, but don't know how to fix it. There is no 'model.24.anchor_grid' in trained model with yolov5-6.0, but it do exist in pretrained models, and exist in yolov5-5.0 trained models.

[dao027]

I found the reason, but don't know how to fix it. There is no 'model.24.anchor_grid' in trained model with yolov5-6.0, but it do exist in pretrained models, and exist in yolov5-5.0 trained models.

i got the same problem, yolov5s v6.1 , using official way to convert model: python export.py --weights xxx.pt --include engine onnx --imgsz 640 --device 0 --batch-size 4

after compile and using: ./yolov5 -d ../test/xxx.engine ../samples

i got no result(no bbox) on output images

[wang-xinyu]

Guys, you need to find out why the trained model doesn't contain anchor info.

[dao027]

Guys, you need to find out why the trained model doesn't contain anchor info.

roger, i will check this

[hua1024]

@dao027 Hei，I have the same problem , can you solved it?

[dao027]

negative, cant use engine file from yolov5 official convertion, u need to convert pth model to engine by way in this repo

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.