When testing, if you change the size of the input image, the test time on the GPU will be very long, without changing the size of the image, the second start time will be normal; this problem was not found on the CPU; is this a problem for tensorflow?
The size of the image will affect the time it takes to run super resolution. This is because we use a windowed approach to resize parts of the image at a time, and then stitch it back together
When testing, if you change the size of the input image, the test time on the GPU will be very long, without changing the size of the image, the second start time will be normal; this problem was not found on the CPU; is this a problem for tensorflow?