Useful or not, from you.
tensorflow Lossy conversion from float32 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.

Version : tensorflow-gpu==2.0.0-beta1 OS : Ubuntu 18.04 LTS

W0621 10:32:12.746317 139752995510080 util.py:64] Lossy conversion from float32 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.

not something important but do you know how to remove this warning?

I already included import os import tensorflow as tf os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

That's a useful answer
Without any help

This warning is generated by imageio, not tensorflow: https://github.com/imageio/imageio/blob/ef1f24f23ae959cccf646128dba7b403638d9b5e/imageio/core/util.py

You can use tf.convert_image_dtype to make sure that images are properly scaled to 0...255.