self.info["photoshop"] = photoshop UnboundLocalError: local variable 'photoshop' referenced before

Initializing Datasets and Dataloaders...
Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
Params to learn:
     classifier.1.weight
     classifier.1.bias
Epoch 0/1
----------
train Loss: 0.7456 Acc: 0.4918
Traceback (most recent call last):
  File "F:/python_learn/pytorch_learn/transfer_learning/finetuning_convent.py", line 494, in <module>
    model_ft,hist = train_model(model_ft,dataloaders_dict,criterion,optimizer_ft,num_epochs,is_inception = (model_name=="inception"))
  File "F:/python_learn/pytorch_learn/transfer_learning/finetuning_convent.py", line 150, in train_model
    for inputs,labels in dataloaders[phase_]:
  File "D:\tools\conda\envs\torch\lib\site-packages\torch\utils\data\dataloader.py", line 582, in __next__
    return self._process_next_batch(batch)
  File "D