Logisti c Регрессия координат (flow_from_dataframe)

Question

Я пытаюсь запустить изображение через простой Conv net и получить x и ay (координаты) в качестве выходных данных. У меня есть pandas Dataframe, состоящий из трех списков:

df = pd.DataFrame({'filename':full_path_list, 'x_coordinate': x_coordinate,'y_coordinate': y_coordinate})

full_path_list: список строк, которые являются путями к изображениям

x_coordinate: координата x, которую я пытаюсь предсказать позже

y_coordinate: координата y, которую я пытаюсь предсказать позже

здесь data_generators:

train_datagen = ImageDataGenerator(
    validation_split = 0.2,
    rescale = 1./255,)

train_generator = train_datagen.flow_from_dataframe(df, class_mode = 'multi_output', y_col = ['x_coordinate', 'y_coordinate'], target_size = (172, 172))

это модель, которую я использую:

IMG_HEIGHT = 172
IMG_WIDTH = 172

model = Sequential([
    Conv2D(16, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH ,3)),
    MaxPooling2D(),
    Conv2D(32, 3, padding='same', activation='relu'),
    MaxPooling2D(),
    Conv2D(64, 3, padding='same', activation='relu'),
    MaxPooling2D(),
    Flatten(),
    Dense(512, activation='relu'),
    Dense(2, activation='relu')
])

model.compile(optimizer='adam',
              loss='mean_squared_error',
              metrics=['mean_absolute_error'], '[mean_squared_error'])

model.fit_generator(generator=train_generator,
                    epochs=15
)

Ошибка, которую я получаю, исправляется, если я изменяю:

y_col = ['x_coordinate', 'y_coordinate']

на

y_col = ['x_coordinate']

и пытаюсь предсказать только одно значение, но я не хочу использовать 2 сети для каждого значения, которое я хочу предсказать. Что-то должно быть не так в способе ввода данных. Вот точная ошибка:

Epoch 1/15
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-129-9becd295e855> in <module>
      4 #                     validation_data=valid_generator,
      5 #                     validation_steps=STEP_SIZE_VALID,
----> 6                     epochs=15
      7 )

~\Anaconda3\envs\Eternium\lib\site-packages\tensorflow_core\python\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   1295         shuffle=shuffle,
   1296         initial_epoch=initial_epoch,
-> 1297         steps_name='steps_per_epoch')
   1298 
   1299   def evaluate_generator(self,

~\Anaconda3\envs\Eternium\lib\site-packages\tensorflow_core\python\keras\engine\training_generator.py in model_iteration(model, data, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch, mode, batch_size, steps_name, **kwargs)
    263 
    264       is_deferred = not model._is_compiled
--> 265       batch_outs = batch_function(*batch_data)
    266       if not isinstance(batch_outs, list):
    267         batch_outs = [batch_outs]

~\Anaconda3\envs\Eternium\lib\site-packages\tensorflow_core\python\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics)
    971       outputs = training_v2_utils.train_on_batch(
    972           self, x, y=y, sample_weight=sample_weight,
--> 973           class_weight=class_weight, reset_metrics=reset_metrics)
    974       outputs = (outputs['total_loss'] + outputs['output_losses'] +
    975                  outputs['metrics'])

~\Anaconda3\envs\Eternium\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics)
    251   x, y, sample_weights = model._standardize_user_data(
    252       x, y, sample_weight=sample_weight, class_weight=class_weight,
--> 253       extract_tensors_from_dataset=True)
    254   batch_size = array_ops.shape(nest.flatten(x, expand_composites=True)[0])[0]
    255   # If `model._distribution_strategy` is True, then we are in a replica context

~\Anaconda3\envs\Eternium\lib\site-packages\tensorflow_core\python\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset)
   2517           shapes=None,
   2518           check_batch_axis=False,  # Don't enforce the batch size.
-> 2519           exception_prefix='target')
   2520 
   2521       # Generate sample-wise weight values given the `sample_weight` and

~\Anaconda3\envs\Eternium\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    529                        'Expected to see ' + str(len(names)) + ' array(s), '
    530                        'but instead got the following list of ' +
--> 531                        str(len(data)) + ' arrays: ' + str(data)[:200] + '...')
    532     elif len(names) > 1:
    533       raise ValueError('Error when checking model ' + exception_prefix +

ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 2 arrays: [array([[1144],
       [ 820],
       [ 428],
       [ 525],
       [ 478],
       [1365],
       [ 479],
       [ 260],
       [ 763],
       [ 519],
       [ 949],
       [ 626],
       [ 703],
    ...