Closed jiao0805 closed 7 years ago
Yes, you can. Make sure that you load or convert the image as 3 channel tensor, e.g. by calling scipy.misc.imread(image_file, mode='RGB')
. The input producer of KittiSeg works out of the box with this code for greyscale images.
Thanks a lot for your help! ^-^
Hi Mr.Marvin Teichmann I found this in the usage that: The images is a tensor with shape [None, h, w, 3]. Where h and w can have arbitrary size.
My training data is gray images with no rgb channels. Can I still use this code and vgg to train them?