i have a problem while training my deep learning model

Question

hi everyone ,
i'm working on deep learning model to predict if images if they contain dog or cat ,
but when i try to train the model i get this error : (can anyone please help me to fix the problem ?)

InvalidArgumentError Traceback (most recent call last)
c:\Users\jebalia\Vs-Data-workplace\Project\cat-dog\DogsVsCats (no-transfer-learning).ipynb Cellule 27 in <cell line: 1>()
1 with tf.device('/device:GPU:0') :
2 epochs = 40
----> 3 history = korobka.fit(train_generator,
4 validation_data = validation_generator,
5 epochs=epochs,
6 validation_steps= len(val_set) // batch_size,
7 steps_per_epoch= len(train_set)// batch_size,
8 callbacks= [early_stopping]
9 )

File c:\Users\jebalia\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\utils\traceback_utils.py:67, in filter_traceback.<locals>.error_handler(*args, **kwargs)
65 except Exception as e: # pylint: disable=broad-except
66 filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67 raise e.with_traceback(filtered_tb) from None
68 finally:
69 del filtered_tb

File c:\Users\jebalia\AppData\Local\Programs\Python\Python310\lib\site-packages\tensorflow\python\eager\execute.py:54, in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
52 try:
53 ctx.ensure_initialized()
---> 54 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
55 inputs, attrs, num_outputs)
...
File "c:\Users\jebalia\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\layers\preprocessing\image_preprocessing.py", line 416, in _batch_augment
return self._map_fn(self._augment, inputs)
Node: 'sequential_1/sequential/random_flip/map/TensorArrayUnstack/TensorListFromTensor'
Specified a list w

Answer 1

I am not sure but I think you need to reshape the data.

See this line in your error (your above comment)
"
TensorListFromTensor
Specified a list with shape [244,244,3] from a tensor with shape [224,224,3]

"

Answer 2

the rest of the error :

File "c:\Users\jebalia\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\layers\preprocessing\image_preprocessing.py", line 416, in _batch_augment
return self._map_fn(self._augment, inputs)
Node: 'sequential_1/sequential/random_flip/map/TensorArrayUnstack/TensorListFromTensor'
Specified a list with shape [244,244,3] from a tensor with shape [224,224,3]
[[{{node sequential_1/sequential/random_flip/map/TensorArrayUnstack/TensorListFromTensor}}]] [Op:__inference_train_function_2542]