您好，我想请教一下这个问题！

[stxg13056]

E:\anaconda3\python.exe "D:/My--Study/My work/DLPan-Toolbox-main/01-DL-toolbox(Pytorch)/UDL/pansharpening/run_test_pansharpening.py" 111 entrypoint 111 None 222 pansharpening 111 None 333 BDPN D:\My--Study\My work\DLPan-Toolbox-main\01-DL-toolbox(Pytorch)\UDL\Basis\option.py:113: UserWarning: Note: FusionNet, DiCNN, PNN don't have high-pass filter warnings.warn(warning) accumulated_step = 1 amp = None amp_opt_level = 'O0' arch = 'BDPN' backend = 'nccl' clip_max_norm = 0 crop_batch_size = 128 device = 'cuda' dist_url = 'env://' global_rank = 0 gpu_ids = [0] launcher = 'none' load_model_strict = True local_rank = 0 log_dir = 'logs' mode = None model_style = None once_epoch = False reg = True reset_lr = False resume_mode = 'best' rgb_range = 255 save_top_k = 5 seed = 10 start_epoch = 1 task = 'pansharpening' tfb_dir = None use_log = True use_tfb = False validate = False scale = [1] data_dir = '../Data/pansharpening' best_prec1 = 10000 best_prec5 = 10000 metrics = 'loss' save_fmt = 'mat' taskhead = 'pansharpening' img_range = 2047.0 best_epoch = 1 dataset = dict(train='wv3', val='NY1_WV3_RR') epochs = 1000 eval = False experimental_desc = 'Test' lr = 0.0001 lr_scheduler = True out_dir = 'D:/My--Study/My work/DLPan-Toolbox-main/01-DL-toolbox(Pytorch)/UDL//results/pansharpening' print_freq = 50 resume_from = 'D:/My--Study/My work/DLPan-Toolbox-main/01-DL-toolbox(Pytorch)/UDL//results/pansharpening/wv3/BDPN/Test/.pth.tar' samples_per_gpu = 8 workers_per_gpu = 0

accumulated_step = 1 amp = None amp_opt_level = 'O0' arch = 'BDPN' backend = 'nccl' clip_max_norm = 0 crop_batch_size = 128 device = 'cuda' dist_url = 'env://' global_rank = 0 gpu_ids = [0] launcher = 'none' load_model_strict = True local_rank = 0 log_dir = 'logs' mode = None model_style = None once_epoch = False reg = True reset_lr = False resume_mode = 'best' rgb_range = 255 save_top_k = 5 seed = 10 start_epoch = 1 task = 'pansharpening' tfb_dir = None use_log = True use_tfb = False validate = False scale = [1] data_dir = '../Data/pansharpening' best_prec1 = 10000 best_prec5 = 10000 metrics = 'loss' save_fmt = 'mat' taskhead = 'pansharpening' img_range = 2047.0 best_epoch = 1 dataset = dict(train='wv3', val='NY1_WV3_RR') epochs = 1000 eval = False experimental_desc = 'Test' lr = 0.0001 lr_scheduler = True out_dir = 'D:/My--Study/My work/DLPan-Toolbox-main/01-DL-toolbox(Pytorch)/UDL//results/pansharpening' print_freq = 50 resume_from = 'D:/My--Study/My work/DLPan-Toolbox-main/01-DL-toolbox(Pytorch)/UDL//results/pansharpening/wv3/BDPN/Test/.pth.tar' samples_per_gpu = 8 workers_per_gpu = 0 workflow = [('train', 50)]

dict_keys(['pansharpening', 'entrypoint', 'BDPN', 'DiCNN1', 'DRPNN', 'FusionNet', 'MSDCNN', 'PanNet', 'PNN']) => creating D:\My--Study\My work\DLPan-Toolbox-main\01-DL-toolbox(Pytorch)\UDL\results\pansharpening\wv3\BDPN\Test

• Set random seed to 10 E:\anaconda3\lib\site-packages\torch\nn_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead. warnings.warn(warning.format(ret)) D:\My--Study\My work\DLPan-Toolbox-main\01-DL-toolbox(Pytorch)\UDL\AutoDL\trainer.py:86: UserWarning: config is now expected to have a runner section, please set runner in your config. warnings.warn( Traceback (most recent call last): File "D:/My--Study/My work/DLPan-Toolbox-main/01-DL-toolbox(Pytorch)/UDL/pansharpening/run_test_pansharpening.py", line 17, in main(cfg) File "D:\My--Study\My work\DLPan-Toolbox-main\01-DL-toolbox(Pytorch)\UDL\AutoDL\trainer.py", line 256, in main trainer( File "D:\My--Study\My work\DLPan-Toolbox-main\01-DL-toolbox(Pytorch)\UDL\AutoDL\trainer.py", line 194, in trainer runner.register_hook( File "D:\My--Study\My work\DLPan-Toolbox-main\01-DL-toolbox(Pytorch)\UDL\mmcv\mmcv\runner\base_runner.py", line 282, in register_hook assert isinstance(hook, Hook) AssertionError loading SingleDataset: ['../Data/pansharpening/test_data/wv3/NY1_WV3_RR.mat'] with 2047.0

Process finished with exit code 1

[XiaoXiao-Woo]

It seems you have modified the pre-defined hyper-parameters. I don't see the above, please show more details.

[stxg13056]

Thanks for reminding me that I have solved this problem. I have another question. How do I visualize the generated. mat file?

[XiaoXiao-Woo]

You can use showimage8 in postprocess.py https://github.com/XiaoXiao-Woo/PanCollection/blob/dev/UDL/Basis/postprocess.py to visualize MS image.

stxg13056 @.***> 于2022年10月6日周四 16:26写道：

Thanks for reminding me that I have solved this problem. I have another question. How do I visualize the generated. mat file?

— Reply to this email directly, view it on GitHub https://github.com/liangjiandeng/DLPan-Toolbox/issues/3#issuecomment-1269573935, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADTCMXRZRL2YIL5QOPIXQFTWB2EK3ANCNFSM6AAAAAAQ6JZG2A . You are receiving this because you commented.Message ID: @.***>

[stxg13056]

Thanks！