You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have trained an EDSR-style network with 20 residual blocks (RB). The baseline network has 20 RBs, while the experimental variant inserts one MySS2D block in the middle, resulting in the structure: 10RBs + 1MySS2D + 10RBs.
Here are the details of my observations:
Training Details:
Patch Size: 128x128
Testing Observations:
Using 128x128 Blocks: When I divide the input image feature into 128x128 blocks before passing through the SS2D block, the PSNR is normal.
Using Original 512x512 Image: When I directly input the original image of 512x512 size, the PSNR is significantly lower, with around a 5dB drop compared to the baseline network.
This leads me to suspect that the SS2D block might be sensitive to the input image block size and possibly overfitted to the patch size used during training.
Description:
I have trained an EDSR-style network with 20 residual blocks (RB). The baseline network has 20 RBs, while the experimental variant inserts one MySS2D block in the middle, resulting in the structure: 10RBs + 1MySS2D + 10RBs.
Here are the details of my observations:
Training Details:
Testing Observations:
This leads me to suspect that the SS2D block might be sensitive to the input image block size and possibly overfitted to the patch size used during training.
Code Implementation:
Questions:
Thank you very much for your assistance!
The text was updated successfully, but these errors were encountered: