search

jmiller656 / EDSR-Tensorflow

Tensorflow implementation of Enhanced Deep Residual Networks for Single Image Super-Resolution
MIT License
330 stars 107 forks source link

code #33

Closed cyforsr closed 5 years ago

cyforsr commented 5 years ago

After shrinking the image size by using transform.resize, the image value is in the range of 0-1(float64). And we are still subtracting the mean of each batch. The mean value is 127 in the code. Is it reasonable?