Open Draft00 opened 2 years ago
I have similar problems,run on android,params yololv5 6.0 by pnnx
Running into a similar issue. Have you had any luck resolving this @xbc922 @Draft00 @zhiliu6?
Running into a similar issue. Have you had any luck resolving this @xbc922 @Draft00 @zhiliu6?
@lizozom, Nope :(. I had to use yolov4.
@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.
I have the same issue with yolov5n.
cc I ended up using an older version as well.
the same error, can you solve it ?
针对onnx模型转换的各种问题,推荐使用最新的pnnx工具转换到ncnn In view of various problems in onnx model conversion, it is recommended to use the latest pnnx tool to convert your model to ncnn
pip install pnnx
pnnx model.onnx inputshape=[1,3,224,224]
详细参考文档 Detailed reference documentation https://github.com/pnnx/pnnx https://github.com/Tencent/ncnn/wiki/use-ncnn-with-pytorch-or-onnx#how-to-use-pnnx
Problem: incorrect detection
Windows platform. Image with wrong detection for example:
model | 模型 | モデル
how to reproduce | 复现步骤 | 再現方法
python detect.py --source data/images --weights yolov5s.pt --conf 0.25
.python export.py --include onnx --weight yolov5s.pt --img 640 --train --simplify
. According to this.ex.extract()
according to my .param file numbers.@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 :(