Wrong result for onnx-ncnn yolov5s_6.0

eoxn13cs  于 4个月前  发布在  其他
关注(0)|答案(7)|浏览(43)

Problem: incorrect detection

Windows platform. Image with wrong detection for example:

model | 模型 | モデル

  1. original model: https://github.com/ultralytics/yolov5

how to reproduce | 复现步骤 | 再現方法

  1. Install yolov5 steps from Quick Start Examples.
  2. Verify: python detect.py --source data/images --weights yolov5s.pt --conf 0.25 .
  3. Export for solve problems 'Unsupported slice step !': python export.py --include onnx --weight yolov5s.pt --img 640 --train --simplify . According to this.
  4. Conversion using out-of-the-box web model conversion (https://convertmodel.com/#outputFormat=ncnn): check both 'Optimize', check 'Generate ft16 model'.
  5. Comparing my .param file with the param file example ( https://github.com/nihui/ncnn-assets/blob/master/models/yolov5s_6.0.param ). The layers are the same, only the numbers differ. Size the .bin file is the same as in the example
  6. Use ncnn tutorial ( https://github.com/Tencent/ncnn/blob/master/examples/yolov5.cpp ) for yolov5s_6.0. Rewrite ex.extract() according to my .param file numbers.
  7. ...And I get a completely incorrect detection result :(

@zhiliu6, could you tell me how you converted the model? it seemed to me that I was doing similar steps, but this is not the case :(

gupuwyp2

gupuwyp21#

I have similar problems,run on android,params yololv5 6.0 by pnnx

traffic_model.zip

azpvetkf

azpvetkf2#

Running into a similar issue. Have you had any luck resolving this @xbc922@Draft00@zhiliu6?

rjee0c15

rjee0c153#

Running into a similar issue. Have you had any luck resolving this @xbc922@Draft00@zhiliu6?

@lizozom, Nope :(. I had to use yolov4.

but5z9lq

but5z9lq4#

@Draft00 my intuition tells me that the processing of images is different between the python and JavaScript versions.
I'm not an ML pro, so I'm having a hard time analysing this myself.

mxg2im7a

mxg2im7a5#

I have the same issue with yolov5n.

yptwkmov

yptwkmov6#

cc I ended up using an older version as well.

kqqjbcuj

kqqjbcuj7#

the same error, can you solve it ?

相关问题