After running the code
python test_sidd_b2u.py --checkpoint ./pretrained_models/rawRGB_112rf20_beta19.4.pth --test_dirs ./data/validation --save_test_path ./test --log_name validation_b2u_unet_raw_112rf20 --beta 19.4, I could get results - INFO: ----Average PSNR/SSIM results for SIDD_Val---- PSNR_DN: 50.615073 dB; SSIM_DN: 0.990160 ----PSNR_EXP: 51.337338 dB; SSIM_EXP: 0.991482 ----PSNR_MID: 51.364046 dB; SSIM_MID: 0.991515 from the pretrained checkpoint.
It seems that PSNR_MID and SSIM_MID are similar with evaluated numbers for Table 3.
What does "_MID" mean? and Are they the evaluted metrics for the official manuscript?
After running the code
python test_sidd_b2u.py --checkpoint ./pretrained_models/rawRGB_112rf20_beta19.4.pth --test_dirs ./data/validation --save_test_path ./test --log_name validation_b2u_unet_raw_112rf20 --beta 19.4, I could get results- INFO: ----Average PSNR/SSIM results for SIDD_Val---- PSNR_DN: 50.615073 dB; SSIM_DN: 0.990160 ----PSNR_EXP: 51.337338 dB; SSIM_EXP: 0.991482 ----PSNR_MID: 51.364046 dB; SSIM_MID: 0.991515from the pretrained checkpoint.It seems that PSNR_MID and SSIM_MID are similar with evaluated numbers for Table 3. What does "_MID" mean? and Are they the evaluted metrics for the official manuscript?