Fast Super-Resolution Convolutional Neural Network (FSRCNN) Structure

Hi all,
I was trying to implement the model as defined here in this FSRCNN, but i am pretty sure i messed up with the structure in the end,
Can someone invest their spare time to help me as to where i am wrong?
Thanks,
Aditya.

my_code

The problem is that the loss is not decreasing at all…(due to structural defects at the end…)

The dataset is quite small…

img_004_SRF_2_LRimg_005_SRF_2_LRimg_004_SRF_2_HRimg_006_SRF_2_LRimg_007_SRF_2_LRimg_006_SRF_2_HRimg_005_SRF_2_HRimg_007_SRF_2_HRimg_008_SRF_2_HRimg_008_SRF_2_LRimg_009_SRF_2_LRimg_0010_SRF_2_HRimg_0010_SRF_2_LRimg_009_SRF_2_HRimg_0011_SRF_2_LRimg_0011_SRF_2_HR

I suggest you use #applications or #theory for discussing new papers, unless they are part of this course, since otherwise it can get a bit overwhelming for the other students!

1 Like