yolact-opencv-dnn-cpp-python icon indicating copy to clipboard operation
yolact-opencv-dnn-cpp-python copied to clipboard

使用opencv部署yolact实例分割,包含C++和Python两种版本的程序

Results 13 yolact-opencv-dnn-cpp-python issues
Sort by recently updated
recently updated
newest added

请问下self.conv_ws与self.conv_hs是如何设置的?我的模型出来的参数与您设置的参数不一致导致出错,我想修改这两个参数的值,但不知道该如何修改,能不能指导一下?非常感谢。 ![image](https://user-images.githubusercontent.com/55050914/185893245-cfd7ebe9-6c37-4e79-a1b1-3e29f5786f4e.png)

when I test the pyhton script: File "...\yolact-opencv-dnn-cpp-python-main\main_yolact.py", line 152, in decode priors[:, 2:] * np.exp(loc[:, 2:] * self.variances[1]), ValueError: operands could not be broadcast together with shapes (10597,2) (10597,79)...

我使用的你的yolact的c++版本检测我自己拍摄的照片,但是效果都不好,这是什么原因呢 ![yolact detect](https://user-images.githubusercontent.com/55723830/138623577-44bd1808-af6d-4554-a46a-6aea4e4894d0.png) ?

Hi all, I've trained a model and there is a shift in the photo. The mask is a little top. Original: ![image](https://user-images.githubusercontent.com/5433346/156185779-20a34552-3bbc-4fdb-8e10-9cbb4f650e7d.png) OpenCV: ![image](https://user-images.githubusercontent.com/5433346/156185992-0cb8eeae-0189-408d-9958-c0d0ca082c0a.png)

Hello. Thanks to your project, I could make the codes to convert from yolactedge to onnx. (yolactedge: https://github.com/haotian-liu/yolact_edge) I want to share my codes with other people, so I wonder...

hi,professor: i use your project code,then i success convert onnx model to nvidia tensorrt engine, but i don't konw when i infer with tensorrt, the yolact postprocess code how to...

请问这个是什么原因呢?是opencv-python的版本不对吗?我查了一下,其他人说把opencv-python改为4.5.1.48,但是这个方法也不行。 请问作者,您的opencv-python版本是多少呢?

main.cpp,make时报错: main.cpp:232:36: error: ‘class cv::dnn::experimental_dnn_34_v7::Net’ has no member named ‘getUnconnectedOutLayersNames’; did you mean ‘getUnconnectedOutLayers’? this->net.forward(outs, this->net.getUnconnectedOutLayersNames()); 我用的opencv3.4,请问是opencv版本的问题吗?

Hi, Could you please share the onnx model? and what script did you use for converting? Thanks!