yolo-fastestv2-opencv icon indicating copy to clipboard operation
yolo-fastestv2-opencv copied to clipboard

使用OpenCV部署Yolo-FastestV2,包含C++和Python两种版本的程序

Results 11 yolo-fastestv2-opencv issues
Sort by recently updated
recently updated
newest added

我用原作者的pytorch2onnx导出onnx文件后,进行加载识别时出现以下错误 ``` Traceback (most recent call last): File "E:\MyWork\Yolo-FastestV2\dnn.py", line 112, in outputs = model.detect(srcimg) File "E:\MyWork\Yolo-FastestV2\dnn.py", line 91, in detect outputs[top:top + length, 0:2] = (outs[row_ind:row_ind + length, ValueError:...

使用您提供的convert-onnx进行yolo fastest v2内pth转换时,提示以下报错 D:\labelImg\yolofastv2\convert_onnx>python pytorch2onnx.py --data coco.data --weights coco.pth load param... D:\labelImg\yolofastv2\convert_onnx\model\backbone\shufflenetv2.py:59: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record...

我在原代码model/detector.py的forward function里修改,因为我看这里有两个tensor output,但他们size不一样 ![image](https://user-images.githubusercontent.com/41173132/142958182-a35cc582-603d-4200-953e-eaa87f142375.png) ![image](https://user-images.githubusercontent.com/41173132/142958204-96323531-23a3-4879-8437-be51ebb528bd.png) 我也不是很确定是不是修改这里,求指导~ Any helps will be appreciated!! _Originally posted by @danielzhangau in https://github.com/hpc203/yolo-fastestv2-opencv/issues/1#issuecomment-976087012_

请问有转onnx的文件吗,官方的转出来用不了,不知道怎么改

hello I want use videocapture(1) ,but there are some problems with the modified program,there is noexport screen

大佬,能给出一个 使用onnxruntiem 推理的代码吗

自己训练的权重文件转onnx 用opencv c++调用后报错terminate called after throwing an instance of 'cv::Exception' what(): OpenCV(4.6.0) /home/xy/opencv/modules/core/src/out.cpp:87: error: (-215:Assertion failed) m.dims

![image](https://user-images.githubusercontent.com/56476646/199404299-a877c4f7-63a0-45b6-954d-d1708a52d88d.png) 请问下这是怎么回事,大家知道怎么解决么