CaiOrange

如题，改动了网络结构后原有的模型转换方法不支持了.

请问报错：TypeError: list indices must be integers or slices, not list的原因是什么

2

按照大佬的思路将改进点在yolov5上实现，在将Concat改为ADD时报如题错误，请问这个错误原因及修改方法

对于修改过结构的模型要如何进行转换？

1

如题，我对yolov5的backbone进行了更换，如果向生成基于这个模型的engine文件应该对tensorrtx的哪部分进行调整？

something wrong after running : python3 gen_wts.py -w yolov5s.pt -o yolov5s.wts

2

env:TX2 NX jetpack 4.5.1 Yolo v5s 5.0 tensorrtx 5.0 I try to generate .wts from pytorch with .pt, run : python3 gen_wts.py -w yolov5s.pt -o yolov5s.wts I got yolov5s and...

Does gen_wts_yoloV5.py support the improved model?

11

I try to run python3 gen_wts_yoloV5.py -w yolov5s.pt (the yolov5s.pt was trained by yolov5 with a modified backbone and neck) ，the output is 'Model not supported'. Although I got yolov5.cfg...

Does it affect the relative or absolute path of the file after the migration operation is completed?

1

After completing the rootfs migration, the .so file is displayed for some object detection models when running DeepStream, and the file does exist on the path given by the error...

What is the difference between the five hyp file? And how to select the appropriate hyp file?

5

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. ### Question I noticed that the/data/hyps folder contains five hyp files...

YOLOV5 model has very weak detection capability after deployment

2

`Jetpack 4.6 deepstream 6.0.1 yolov5 6.1 ` I tested yolov5s , yolov7 , yolor （untrained,all of them），the can work well. I trained yolov5（changed backbone，but layers(CBH , LC_block , Dense) can...