Change the batch_size parameter

[Kamyar-azar]

Hi Arturo,
I was wondering if we can change the batch_size value as well? When I tried to change its value, I got the below error:

  File "C:\Users\kamyr\anaconda3\envs\tensorflow_gpu\lib\site-packages\IPython\core\interactiveshell.py", line 3417, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-6-0a14997f5eab>", line 36, in <module>
    shuffle=False)
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py", line 1100, in fit
    tmp_logs = self.train_function(iterator)
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py", line 828, in __call__
    result = self._call(*args, **kwds)
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py", line 888, in _call
    return self._stateless_fn(*args, **kwds)
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py", line 2943, in __call__
    filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py", line 1919, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py", line 560, in call
    ctx=ctx)
  File "C:\Users\kamyr\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\execute.py", line 60, in quick_execute
    inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError:  Incompatible shapes: [1310] vs. [32,32]
	 [[node loss/mul (defined at <ipython-input-2-9dae00935354>:63) ]] [Op:__inference_train_function_7212]
Errors may have originated from an input operation.
Input Source operations connected to node loss/mul:
 loss/sub (defined at <ipython-input-2-9dae00935354>:62)
Function call stack:
train_function

Thanks for the support.