search

Zheng222 / IMDN

Lightweight Image Super-Resolution with Information Multi-distillation Network (ACM MM 2019, Winner Award of ICCVW AIM 2019 Constrained SR Track1&Track2)
418 stars 69 forks source link

Training and Testing #11

Closed sertankaya closed 4 years ago

sertankaya commented 4 years ago

Hi Zheng,

This a great repo. Appreciate for letting us use it. I have 2 questions regarding training and testing.

1-) Why do we use testing data (testing folders) as validation data during training ? In train_IMDN.py: image

2-) Can we test our LR images without corresponding HR images? Ideally, we want to generate HR images from LR images? Do we have to have --test_hr_folder in order to test LR images?

python test_IMDN.py --test_hr_folder Test_Datasets/Set5/ --test_lr_folder Test_Datasets/Set5_LR/x2/ --output_folder results/Set5/x2 --checkpoint checkpoints/IMDN_x2.pth --upscale_factor 2

Zheng222 commented 4 years ago

@sertankaya Hello, 1. Through Set5 dataset is testing data, it is usually used in the valid phase in the SR field.

  1. The --test_hr_folder is for computing PSNR and SSIM, so you can modify the test_IMDN.py to implement your goal.