Input images have to be 32-bit
faymanns opened this issue · comments
Florian Aymanns commented
The input image to model.predict(img, axes='YX', n_tiles=(2,1))
has to be a 32-bit image.
Using 16-bit images results in hot pixels in the background with values close to the saturation value of 16-bit.
Tim-Oliver Buchholz commented
Hi @faymanns
This is true, the networks expect 32-bit float images. We should probably add a test and convert-step in our predict method.
Thanks for reporting!