Sunny Deng

Removing slice does not require retraining the model. However, you should decode the boxes as if you had inputted an image two times larger than the network input size. If...

>  > Thank you very much for your reply. I modified the resolution in the export code（640x604->320x240）. but i met the same phenomenon, Do you mean I need to...

Well, that's weird. Did you run onnx-sim to simplify the model after generating the model? Or did you make any modifications to the code? On Fri, Jul 24, 2020, 11:09...

Another solution is replacing the slice operation with convolutions, and you can make the output exactly the same as the python version. On Fri, Jul 24, 2020, 11:42 kadebudongtan wrote:...

Check this out. https://github.com/Tencent/ncnn/blob/master/tools/onnx/onnx2ncnn.cpp

bin and param are models for NCNN framework. For more information please refer to the NCNN project. 2021年9月27日(月) 17:09 NTHoang99 ***@***.***>: > I trained model yolov5 for object detection and...

ONNX converts the operation of line 87 in [common.py](https://github.com/ultralytics/yolov5/blob/master/models/common.py) ``` return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1)) ``` into a slice operation with...

Of course, you can remove the slice operation without retraining. On Thu, Jul 9, 2020, 16:17 tadejj wrote: > Hi, > Can I remove slice operation for trained model? I...

Sorry, I have never encountered this kind of error. Maybe you should open an issue in the NCNN project, and, could you provide detailed information about how you generate the...

Please reassure that you have set the input size to be half of the image size when exporting the onnx model if you would like to use my code directly...