Python train_domain_A.py -use_v2_degradation -continue_train -training_dataset domain_A -name domainA_SR_old_photos -label_nc 0 -loadSize 256 -fineSize 256 -dataroot -no_instance -resize_or_crop crop_only -batchSize 100 -no_html -gpu_ids 0,1,2,3 -self_gen -nThreads 4 -n_downsample_global 3 -k_size 4 -use_v2 -mc 64 -start_r 1 -kl 1 -no_cgan -outputs_dir -checkpoints_dir Put the folders of VOC dataset, collected old photos (e.g., Real_L_old and Real_RGB_old) into one shared folder. 5) GUIĪ user-friendly GUI which takes input of image by user and shows result in respective window. Since the model is pretrained with 256*256 images, the model may not work ideally for arbitrary resolution. This repo is mainly for research purpose and we have not yet optimized the running performance. More details could be found in our journal submission and. We use a progressive generator to refine the face regions of old photos.
Python test.py -Scratch_and_Quality_restore \
