RuntimeError: Found 0 image pairs in given directories.

[saskra]

I followed these instructions: https://github.com/huiqu18/FullNet-varCE#model-training-and-test

But I get this error message:

(fullnet) saskra@a0619843801:~/PycharmProjects/FullNet-varCE/scripts$ bash run_GlaS.sh
2022-07-25 04:14        ***** Training starts *****
2022-07-25 04:14        save directory: /home/saskra/PycharmProjects/FullNet-varCE/experiments/GlaS/1
2022-07-25 04:14        
# ------------------------- Options ------------------------- #
             dataset: GlaS                               
             isTrain: True                               

*************** model ***************
                in_c: 3                                  
               out_c: 3                                  
            n_layers: 6                                  
         growth_rate: 24                                 
           drop_rate: 0.1                                
      compress_ratio: 0.5                                
           dilations: [1, 2, 4, 8, 16, 4, 1]             
           is_hybrid: True                               
          layer_type: basic                              

*************** train ***************
            data_dir: /home/saskra/PycharmProjects/FullNet-varCE/data/GlaS
            save_dir: /home/saskra/PycharmProjects/FullNet-varCE/experiments/GlaS/1
          input_size: 208                                
          num_epochs: 1000                               
          batch_size: 8                                  
         val_overlap: 80                                 
                  lr: 0.0005                             
        weight_decay: 0.0001                             
        log_interval: 50                                 
             workers: 2                                  
                 gpu: ['0', '1']                         
               alpha: 1.0                                
     checkpoint_freq: 100                                
         start_epoch: 0                                  
          checkpoint:                                    
             img_dir: /home/saskra/PycharmProjects/FullNet-varCE/data/GlaS/images
           label_dir: /home/saskra/PycharmProjects/FullNet-varCE/data/GlaS/labels
      weight_map_dir: /home/saskra/PycharmProjects/FullNet-varCE/data/GlaS/weight_maps

*************** transform ***************
train:
               scale: 238                                
     horizontal_flip: True                               
       random_affine: 0.3                                
      random_elastic: [6, 15]                            
     random_rotation: 90                                 
         random_crop: 208                                
      label_encoding: 2                                  
           to_tensor: 1                                  
           normalize: [[0.78780321 0.5120167  0.78493782],
                       [0.16766301 0.24838048 0.13225162]]
val:
               scale: 208                                
      label_encoding: 2                                  
           to_tensor: 1                                  
           normalize: [[0.78780321 0.5120167  0.78493782],
                       [0.16766301 0.24838048 0.13225162]]
# -------------------------- End -------------------------- #

2022-07-25 04:14        => Using variance term in loss...
Traceback (most recent call last):
  File "../train.py", line 319, in <module>
    main()
  File "../train.py", line 75, in main
    dsets[x] = DataFolder(dir_list, post_fix, num_channels, data_transforms[x])
  File "/home/saskra/PycharmProjects/FullNet-varCE/data_folder.py", line 70, in __init__
    raise(RuntimeError('Found 0 image pairs in given directories.'))
RuntimeError: Found 0 image pairs in given directories.

Could it be my folder structure (see below), what should it look like?

./images
./images/testA
./images/testB
./images/train
./labels
./labels_instance
./labels_instance/testA
./labels_instance/testB
./labels_instance/train
./labels/testA
./labels/testB
./labels/train
./weight_maps
./weight_maps/testA
./weight_maps/testB
./weight_maps/train