How would one go about training the network with one channel images?

Open patakk opened this issue 7 years ago • 2 comments

Let's say I have normal RGB images and would like to only take the Y component of the YUV color space, how would one go about doing that and setting up tfrecords?

Feb 15 '18 11:02 patakk

I don't know TF but I suspect it is similar to pytorch

you simply provide images with dimensions (xsize, ysize, depth) where depth is not 3 (RGB) but 1 (Y)

Apr 28 '19 20:04 makeyourownalgorithmicart

I honestly can't remember why I even asked this question, but I guess I wanted to know how to convert RGB images to grayscale and save it to tfrecords, but I could've just googled it..

May 02 '19 20:05 patakk