coolbrain commented on issue #6999: bgr or rgb input to vgg16?
URL: 
https://github.com/apache/incubator-mxnet/issues/6999#issuecomment-321173914
 
 
   I had confirmed that VGG16 pre-trained model is directly converted from 
caffe model. In mxnet, the input channel of image is RGB, but BGR in caffe, so 
when converting the model, it adjusts the first convolution kernel sequence, so 
the result may be right.
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


With regards,
Apache Git Services

Reply via email to