MIVRC / SeaNet-PyTorch

This repository is a PyTorch version of "Soft-edge Assisted Network for Single Image Super-Resolution". (IEEE TIP 2020)
27 stars 10 forks source link

Testing code error #4

Open praful1993 opened 2 years ago

praful1993 commented 2 years ago

How to solve this error?? (pytorch0.4) G:\EDGE\seanet-pytorch-master\Test\code>python main.py --data_test MyImage --scale 4 --model SEAN --pre_train F:/Nancy/seanet-pytorch-master/Test/model/SEAN_x4.pt --test_only --chop --save "SEAN" --testpath ../LR/LRBI --testset Set5 usage: main.py [-h] [--debug] [--template TEMPLATE] [--n_threads N_THREADS] [--cpu] [--n_GPUs N_GPUS] [--seed SEED] [--dir_data DIR_DATA] [--dir_demo DIR_DEMO] [--data_train DATA_TRAIN] [--data_test DATA_TEST] [--benchmark_noise] [--n_train N_TRAIN] [--n_val N_VAL] [--offset_val OFFSET_VAL] [--ext EXT] [--scale SCALE] [--patch_size PATCH_SIZE] [--rgb_range RGB_RANGE] [--n_colors N_COLORS] [--noise NOISE] [--chop] [--model MODEL] [--act ACT] [--pre_train PRE_TRAIN] [--extend EXTEND] [--n_resblocks N_RESBLOCKS] [--n_feats N_FEATS] [--res_scale RES_SCALE] [--shift_mean SHIFT_MEAN] [--precision {single,half}] [--reset] [--test_every TEST_EVERY] [--epochs EPOCHS] [--batch_size BATCH_SIZE] [--split_batch SPLIT_BATCH] [--self_ensemble] [--test_only] [--gan_k GAN_K] [--lr LR] [--lr_decay LR_DECAY] [--decay_type DECAY_TYPE] [--gamma GAMMA] [--optimizer {SGD,ADAM,RMSprop}] [--momentum MOMENTUM] [--beta1 BETA1] [--beta2 BETA2] [--epsilon EPSILON] [--weight_decay WEIGHT_DECAY] [--loss LOSS] [--skip_threshold SKIP_THRESHOLD] [--n_resgroups N_RESGROUPS] [--reduction REDUCTION] [--testpath TESTPATH] [--testset TESTSET] [--degradation DEGRADATION] main.py: error: unrecognized arguments: --save SEAN

zkh123456789 commented 1 year ago

I also encountered this problem, have you solved it?

IceyWuu commented 1 week ago

Gosh, code in this repo is a mess! You can add parser.add_argument('--save', type=str, default='test', help='file name to save') in the test option.py file, this option file miss so many args, can find in the train option.py

I also encountered this problem, have you solved it?