Deepskyhunter
Deepskyhunter
> Why was the approach in your previous PR seemingly completely abandoned? It seems that the previous approach ignore the intermediate state completely.
 It has around 200 log messages
`plt.imshow(img, cmap="gray") ` or other [colormap](https://matplotlib.org/stable/tutorials/colors/colormaps.html)
Try follow GPU setup at www.tensorflow.org/install/pip