Can't get the same results as in the article with pretrained model.

[1214635079]

I tested Set5, Set14, BSD100 and urban100 datasets use pretrained models DBPN_x8.pth or DBPN-RES-MR64-3_8x.pth, but the results I got have a big gap with your results showed in the paper. Do I need to retrain the model? What's wrong with my operation? Thank you very much!

[shazib-summar]

Same issue here. The generated images are awful. I'm using the following configurations:

parser = argparse.ArgumentParser(description='PyTorch Super Res Example')
parser.add_argument('--upscale_factor', type=int, default=4, help="super resolution upscale factor")
parser.add_argument('--testBatchSize', type=int, default=1, help='testing batch size')
parser.add_argument('--gpu_mode', type=bool, default=True)
parser.add_argument('--self_ensemble', type=bool, default=False)
parser.add_argument('--chop_forward', type=bool, default=False)
parser.add_argument('--threads', type=int, default=1, help='number of threads for data loader to use')
parser.add_argument('--seed', type=int, default=123, help='random seed to use. Default=123')
parser.add_argument('--gpus', default=1, type=int, help='number of gpu')
parser.add_argument('--input_dir', type=str, default='Input')
parser.add_argument('--output', default='Results/', help='Location to save checkpoint models')
parser.add_argument('--test_dataset', type=str, default='Set5_LR_x4')
parser.add_argument('--model_type', type=str, default='DBPNLL')
parser.add_argument('--residual', type=bool, default=False)
parser.add_argument('--model', default='models/PIRM2018_region3.pth', help='sr pretrained base model')

[Sherif1994]

the same issue when I test the set5 images it gave good results but if I test image from my own it produces bad result had chessboard effect