Error when checking target: expected dense_1 to have 4 dimensions, but got array with shape (128, 10)

[trittsv]

[Required] Your device (RaspberryPi3, LaptopPC, or other device name):
Laptop (MacBook Pro 15" Early 2013 [Required] Your device's CPU architecture (armv7l, x86_64, or other architecture name):
x86_64 [Required] Your OS (Raspbian, Ubuntu1604, or other os name):
MacOS 10.14.6 [Required] Details of the work you did before the problem occurred:
Clone repository, and execute from_preprocessing_to_training.ipynb in jupiter-notebook [Required] Error message:

Total params: 719,034
Trainable params: 549,098
Non-trainable params: 169,936
__________________________________________________________________________________________________
x_target is 6000 samples
x_ref is 6000 samples
training...
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-3-bdce5d7b4ebd> in <module>
    117     return model_t
    118 
--> 119 model = train(X_train_s, X_ref, y_ref, 5)

<ipython-input-3-bdce5d7b4ebd> in train(x_target, x_ref, y_ref, epoch_num)
     94             #reference data
     95             #Get loss while learning
---> 96             ld.append(model_r.train_on_batch(batch_ref, batch_y))
     97 
     98         loss.append(np.mean(ld))

/usr/local/lib/python3.6/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
   1209             x, y,
   1210             sample_weight=sample_weight,
-> 1211             class_weight=class_weight)
   1212         if self._uses_dynamic_learning_phase():
   1213             ins = x + y + sample_weights + [1.]

/usr/local/lib/python3.6/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    787                 feed_output_shapes,
    788                 check_batch_axis=False,  # Don't enforce the batch size.
--> 789                 exception_prefix='target')
    790 
    791             # Generate sample-wise weight values given the `sample_weight` and

/usr/local/lib/python3.6/site-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    126                         ': expected ' + names[i] + ' to have ' +
    127                         str(len(shape)) + ' dimensions, but got array '
--> 128                         'with shape ' + str(data_shape))
    129                 if not check_batch_axis:
    130                     data_shape = data_shape[1:]

ValueError: Error when checking target: expected dense_1 to have 4 dimensions, but got array with shape (128, 10)

[Required] Overview of problems and questions:
How to solve this error? I didn't changed anything in the code, i just ran the example.

[PINTO0309]

@trittsv Can you tell me the version of Keras?

[shinmura0]

@trittsv

Modifications are required for MobileNet V2.

include_top=True

After all, MobileNet V2 is as follows.

mobile = MobileNetV2(include_top=True, input_shape=input_shape, alpha=alpha,  weights='imagenet')

Commit content a96658e4a217e737b37dfad0c619ac5bedecc43a