Engineering-Course/LIP_JPPNet

Input Size

b121351 opened this issue · 2 comments

What must be the input size of the image? How is it giving the output with the same dimensions as that of input image? Where is it resizing?

The input size is fixed for training which you can change according to your GPU memory.
For testing, the input is the original image and the predicted result is resized to the same size of the input image.

Okay. Thank you!