/SwinCIR

Proposed model on Individual Study (Lab. Intern)

Primary LanguagePython

SwinCIR: SwinIR with multi-resolution connections

스크린샷 2022-12-20 오후 10 46 49

4x Result

PSNR

Dataset Bicubic SwinCIR
Set5 28.648 32.460
Set14 26.230 28.793
Urban100 23.220 26.329

Set14

Bicubic SwinCIR GT
image image image

Train Setting

Item Setting
Train Data DIV2K, Flickr2K
Preprocess [-1,1] Normalization
Random Transforms Crop {DIV2K(64x64), Flickr2K(64x64)}, Rotation {90 degree}
Validation Data DIV2K
Test Data Set5, Set14, Urban100
Scale 4x
Optimizer Adam
Learning Rate 2e-4
Scheduler Cosine Annealing with last LR of 1e-6
Trained Iterations 5e5
Loss L1
Batch 4 {2 for each GPU, total 2 GPUs are utilized}