def _create_mini_batch_pipeline(self, wrapped: BaseStep) -> BaseStep:
"""
Add mini batching and batch metrics by wrapping the step with :class:`MetricsWrapper`, and :class:̀MiniBatchSequentialPipeline`.
:param wrapped: pipeline step
:type wrapped: BaseStep
:return: wrapped pipeline step
:rtype: MetricsWrapper
"""
if self.batch_size is not None:
wrapped = MetricsWrapper(wrapped=wrapped, metrics=self.batch_metrics, name=BATCH_METRICS_STEP_NAME, print_metrics=self.print_batch_metrics)
wrapped = MiniBatchSequentialPipeline(
[wrapped],
batch_size=self.batch_size
)
return wrapped
def _create_validation_split(self, wrapped: BaseStep) -> BaseStep:
"""
Add validation split and epoch metrics by wrapping the step with :class:`MetricsWrapper`, and :class:̀ValidationSplitWrapper`.
:param wrapped: pipeline step
:type wrapped: BaseStep
:return: wrapped pipeline step
:rtype: MetricsWrapper
"""
if self.validation_size != 0.0:
wrapped = MetricsWrapper(wrapped=wrapped, metrics=self.epochs_metrics, name=EPOCH_METRICS_STEP_NAME, print_metrics=self.print_epoch_metrics)
wrapped = ValidationSplitWrapper(
wrapped=wrapped,
test_size=self.validation_size,
scoring_function=self.final_scoring_metric
).set_name(VALIDATION_SPLIT_STEP_NAME)
return wrapped
def main(chosen_device):
exercice_number = 1
print('exercice {}\n=================='.format(exercice_number))
data_inputs, expected_outputs = generate_data(
# See: https://github.com/guillaume-chevalier/seq2seq-signal-prediction/blob/master/datasets.py
exercice_number=exercice_number,
n_samples=None,
window_size_past=None,
window_size_future=None)
print('data_inputs shape: {} => (n_samples, window_size_past, input_dim)'.
format(data_inputs.shape))
print(
'expected_outputs shape: {} => (n_samples, window_size_future, output_dim)'
.format(expected_outputs.shape))
sequence_length = data_inputs.shape[1]
input_dim = data_inputs.shape[2]
output_dim = expected_outputs.shape[2]
batch_size = 100
epochs = 3
validation_size = 0.15
max_plotted_validation_predictions = 10
seq2seq_pipeline_hyperparams = HyperparameterSamples({
'hidden_dim':
100,
'layers_stacked_count':
2,
'lambda_loss_amount':
0.0003,
'learning_rate':
0.006,
'window_size_future':
sequence_length,
'output_dim':
output_dim,
'input_dim':
input_dim
})
feature_0_metric = metric_3d_to_2d_wrapper(mean_squared_error)
metrics = {'mse': feature_0_metric}
signal_prediction_pipeline = Pipeline([
ForEachDataInput(MeanStdNormalizer()),
ToNumpy(),
PlotPredictionsWrapper(
Tensorflow2ModelStep(
# See: https://github.com/Neuraxio/Neuraxle-TensorFlow
create_model=create_model,
create_loss=create_loss,
create_optimizer=create_optimizer,
expected_outputs_dtype=tf.dtypes.float32,
data_inputs_dtype=tf.dtypes.float32,
print_loss=True).set_hyperparams(seq2seq_pipeline_hyperparams))
]).set_name('SignalPrediction')
pipeline = Pipeline([
EpochRepeater(ValidationSplitWrapper(
MetricsWrapper(Pipeline([
TrainOnlyWrapper(DataShuffler()),
MiniBatchSequentialPipeline([
MetricsWrapper(signal_prediction_pipeline,
metrics=metrics,
name='batch_metrics')
],
batch_size=batch_size)
]),
metrics=metrics,
name='epoch_metrics',
print_metrics=True),
test_size=validation_size,
scoring_function=feature_0_metric),
epochs=epochs)
])
pipeline, outputs = pipeline.fit_transform(data_inputs, expected_outputs)
plot_metrics(pipeline=pipeline, exercice_number=exercice_number)
plot_predictions(data_inputs, expected_outputs, pipeline,
max_plotted_validation_predictions)