Kevin Deng

Results 5 comments of Kevin Deng

error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'

Use jpeg, not png

error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'

我猜测是因为png带alpha通道（rgba），通道数是4因此报错。换成jpg就没事了。

error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'

> 问题依旧存在，还是报error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'错误，但是只要把“自动面部焦点剪裁”关掉就能正常出图 > > > 我猜测是因为png带alpha通道（rgba），通道数是4因此报错。换成jpg就没事了。 我试了下，使用第一项Single Image的确不行。我是使用Batch from Directory并使用jpg可以正常使用，希望对你有帮助。...

error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'

> > > 问题依旧存在，还是报error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'错误，但是只要把“自动面部焦点剪裁”关掉就能正常出图 > > > > 我猜测是因为png带alpha通道（rgba），通道数是4因此报错。换成jpg就没事了。 >...

error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:396: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 4 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'

> 版本升级为4.10.0.84之后还是老问题，啥都不显示就自动结束了，连日志都没有 当时是打算训练模型才打算用这个功能的，现在已经半退坑Stable-Diffusion了，暂时就这样吧...... 我中秋刚接触，那时候训练的，的确也就那样。