class CNNBase(NeuralNetMaster, ABC):
"""Top-level class for a convolutional neural network"""
def __init__(self):
"""
NAME:
__init__
PURPOSE:
To define astroNN convolutional neural network
HISTORY:
2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
super().__init__()
self.name = 'Convolutional Neural Network'
self._model_type = 'CNN'
self._model_identifier = None
self.initializer = None
self.activation = None
self._last_layer_activation = None
self.num_filters = None
self.filter_len = None
self.pool_length = None
self.num_hidden = None
self.reduce_lr_epsilon = None
self.reduce_lr_min = None
self.reduce_lr_patience = None
self.l1 = None
self.l2 = None
self.maxnorm = None
self.dropout_rate = 0.0
self.val_size = 0.1
self.early_stopping_min_delta = 0.0001
self.early_stopping_patience = 4
self.input_norm_mode = 1
self.labels_norm_mode = 2
def compile(self, optimizer=None,
loss=None,
metrics=None,
weighted_metrics=None,
loss_weights=None,
sample_weight_mode=None):
if optimizer is not None:
self.optimizer = optimizer
elif self.optimizer is None or self.optimizer == 'adam':
self.optimizer = Adam(lr=self.lr, beta_1=self.beta_1, beta_2=self.beta_2, epsilon=self.optimizer_epsilon,
decay=0.0)
if metrics is not None:
self.metrics = metrics
if self.task == 'regression':
self._last_layer_activation = 'linear'
loss_func = mean_squared_error if not loss else loss
self.metrics = [mean_absolute_error, mean_error] if not self.metrics else self.metrics
elif self.task == 'classification':
self._last_layer_activation = 'softmax'
loss_func = categorical_crossentropy if not loss else loss
self.metrics = [categorical_accuracy] if not self.metrics else self.metrics
elif self.task == 'binary_classification':
self._last_layer_activation = 'sigmoid'
loss_func = binary_crossentropy if not loss else loss
self.metrics = [binary_accuracy] if not self.metrics else self.metrics
else:
raise RuntimeError('Only "regression", "classification" and "binary_classification" are supported')
self.keras_model = self.model()
self.keras_model.compile(loss=loss_func,
optimizer=self.optimizer,
metrics=self.metrics,
weighted_metrics=weighted_metrics,
loss_weights=loss_weights,
sample_weight_mode=sample_weight_mode)
return None
def pre_training_checklist_child(self, input_data, labels):
# on top of checklist, convert input_data/labels to dict
input_data, labels = self.pre_training_checklist_master(input_data, labels)
# check if exists (existing means the model has already been trained (e.g. fine-tuning)
# so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
if self.keras_model is None: # only compile if there is no keras_model, e.g. fine-tuning does not required
self.compile()
self.train_idx, self.val_idx = train_test_split(np.arange(self.num_train + self.val_num),
test_size=self.val_size)
norm_data_training = {}
norm_data_val = {}
norm_labels_training = {}
norm_labels_val = {}
for name in norm_data.keys():
norm_data_training.update({name: norm_data[name][self.train_idx]})
norm_data_val.update({name: norm_data[name][self.val_idx]})
for name in norm_labels.keys():
norm_labels_training.update({name: norm_labels[name][self.train_idx]})
norm_labels_val.update({name: norm_labels[name][self.val_idx]})
self.training_generator = CNNDataGenerator(
batch_size=self.batch_size,
shuffle=True,
steps_per_epoch=self.num_train // self.batch_size,
data=[norm_data_training, norm_labels_training],
manual_reset=False)
val_batchsize = self.batch_size if len(self.val_idx) > self.batch_size else len(self.val_idx)
self.validation_generator = CNNDataGenerator(
batch_size=val_batchsize,
shuffle=False,
steps_per_epoch=max(self.val_num // self.batch_size, 1),
data=[norm_data_val, norm_labels_val],
manual_reset=True)
return input_data, labels
def train(self, input_data, labels):
"""
Train a Convolutional neural network
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:return: None
:rtype: NoneType
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
# Call the checklist to create astroNN folder and save parameters
self.pre_training_checklist_child(input_data, labels)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5,
min_delta=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience, min_lr=self.reduce_lr_min, mode='min',
verbose=2)
early_stopping = EarlyStopping(monitor='val_loss', min_delta=self.early_stopping_min_delta,
patience=self.early_stopping_patience, verbose=2, mode='min')
self.virtual_cvslogger = VirutalCSVLogger()
self.__callbacks = [reduce_lr, self.virtual_cvslogger] # default must have unchangeable callbacks
if self.callbacks is not None:
if isinstance(self.callbacks, list):
self.__callbacks.extend(self.callbacks)
else:
self.__callbacks.append(self.callbacks)
start_time = time.time()
self.history = self.keras_model.fit_generator(generator=self.training_generator,
validation_data=self.validation_generator,
epochs=self.max_epochs, verbose=self.verbose,
workers=os.cpu_count(),
callbacks=self.__callbacks,
use_multiprocessing=MULTIPROCESS_FLAG)
print(f'Completed Training, {(time.time() - start_time):.{2}f}s in total')
if self.autosave is True:
# Call the post training checklist to save parameters
self.save()
return None
def train_on_batch(self, input_data, labels):
"""
Train a neural network by running a single gradient update on all of your data, suitable for fine-tuning
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:return: None
:rtype: NoneType
:History: 2018-Aug-22 - Written - Henry Leung (University of Toronto)
"""
input_data, labels = self.pre_training_checklist_master(input_data, labels)
# check if exists (existing means the model has already been trained (e.g. fine-tuning),
# so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
start_time = time.time()
fit_generator = CNNDataGenerator(batch_size=input_data['input'].shape[0],
shuffle=False,
steps_per_epoch=1,
data=[norm_data, norm_labels])
scores = self.keras_model.fit_generator(generator=fit_generator,
epochs=1,
verbose=self.verbose,
workers=os.cpu_count(),
use_multiprocessing=MULTIPROCESS_FLAG)
print(f'Completed Training on Batch, {(time.time() - start_time):.{2}f}s in total')
return None
def post_training_checklist_child(self):
self.keras_model.save(self.fullfilepath + _astroNN_MODEL_NAME)
print(_astroNN_MODEL_NAME + f' saved to {(self.fullfilepath + _astroNN_MODEL_NAME)}')
self.hyper_txt.write(f"Dropout Rate: {self.dropout_rate} \n")
self.hyper_txt.flush()
self.hyper_txt.close()
data = {'id': self.__class__.__name__ if self._model_identifier is None else self._model_identifier,
'pool_length': self.pool_length,
'filterlen': self.filter_len,
'filternum': self.num_filters,
'hidden': self.num_hidden,
'input': self._input_shape,
'labels': self._labels_shape,
'task': self.task,
'last_layer_activation': self._last_layer_activation,
'activation': self.activation,
'input_mean': dict_np_to_dict_list(self.input_mean),
'labels_mean': dict_np_to_dict_list(self.labels_mean),
'input_std': dict_np_to_dict_list(self.input_std),
'labels_std': dict_np_to_dict_list(self.labels_std),
'valsize': self.val_size,
'targetname': self.targetname,
'dropout_rate': self.dropout_rate,
'l1': self.l1,
'l2': self.l2,
'maxnorm': self.maxnorm,
'input_norm_mode': self.input_normalizer.normalization_mode,
'labels_norm_mode': self.labels_normalizer.normalization_mode,
'input_names': self.input_names,
'output_names': self.output_names,
'batch_size': self.batch_size}
with open(self.fullfilepath + '/astroNN_model_parameter.json', 'w') as f:
json.dump(data, f, indent=4, sort_keys=True)
def test(self, input_data):
"""
Use the neural network to do inference
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:return: prediction and prediction uncertainty
:rtype: ndarry
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
input_data = self.pre_testing_checklist_master(input_data)
input_array = self.input_normalizer.normalize(input_data, calc=False)
total_test_num = input_data['input'].shape[0] # Number of testing data
# for number of training data smaller than batch_size
if total_test_num < self.batch_size:
self.batch_size = total_test_num
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
# TODO: named output????
predictions = np.zeros((total_test_num, self._labels_shape['output']))
norm_data_main = {}
norm_data_remainder = {}
for name in input_array.keys():
norm_data_main.update({name: input_array[name][:data_gen_shape]})
norm_data_remainder.update({name: input_array[name][data_gen_shape:]})
start_time = time.time()
print("Starting Inference")
# Data Generator for prediction
prediction_generator = CNNPredDataGenerator(batch_size=self.batch_size,
shuffle=False,
steps_per_epoch=total_test_num // self.batch_size,
data=[norm_data_main])
predictions[:data_gen_shape] = np.asarray(self.keras_model.predict_generator(prediction_generator))
if remainder_shape != 0:
# assume its caused by mono images, so need to expand dim by 1
for name in input_array.keys():
if len(norm_data_remainder[name][0].shape) != len(self._input_shape[name]):
norm_data_remainder.update({name: np.expand_dims(norm_data_remainder[name], axis=-1)})
result = self.keras_model.predict(norm_data_remainder)
predictions[data_gen_shape:] = result.reshape((remainder_shape, self._labels_shape['output']))
if self.labels_normalizer is not None:
predictions = self.labels_normalizer.denormalize(list_to_dict(self.keras_model.output_names, predictions))
else:
predictions *= self.labels_std
predictions += self.labels_mean
print(f'Completed Inference, {(time.time() - start_time):.{2}f}s elapsed')
return predictions['output']
def evaluate(self, input_data, labels):
"""
Evaluate neural network by provided input data and labels and get back a metrics score
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:param labels: labels
:type labels: ndarray
:return: metrics score dictionary
:rtype: dict
:History: 2018-May-20 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
input_data = list_to_dict(self.keras_model.input_names, input_data)
labels = list_to_dict(self.keras_model.output_names, labels)
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
total_num = input_data['input'].shape[0]
eval_batchsize = self.batch_size if total_num > self.batch_size else total_num
steps = total_num // self.batch_size if total_num > self.batch_size else 1
start_time = time.time()
print("Starting Evaluation")
evaluate_generator = CNNDataGenerator(batch_size=eval_batchsize,
shuffle=False,
steps_per_epoch=steps,
data=[norm_data, norm_labels])
scores = self.keras_model.evaluate_generator(evaluate_generator)
if isinstance(scores, float): # make sure scores is iterable
scores = list(str(scores))
outputname = self.keras_model.output_names
funcname = self.keras_model.metrics_names
print(f'Completed Evaluation, {(time.time() - start_time):.{2}f}s elapsed')
return list_to_dict(funcname, scores)
class ConvVAEBase(NeuralNetMaster, ABC):
"""
Top-level class for a Convolutional Variational Autoencoder
:History: 2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
def __init__(self):
super().__init__()
self.name = 'Convolutional Variational Autoencoder'
self._model_type = 'CVAE'
self.initializer = None
self.activation = None
self._last_layer_activation = None
self.num_filters = None
self.filter_len = None
self.pool_length = None
self.num_hidden = None
self.reduce_lr_epsilon = None
self.reduce_lr_min = None
self.reduce_lr_patience = None
self.l1 = None
self.l2 = None
self.maxnorm = None
self.latent_dim = None
self.val_size = 0.1
self.dropout_rate = 0.0
self.keras_vae = None
self.keras_encoder = None
self.keras_decoder = None
self.loss = None
self._input_shape = None
self.input_norm_mode = 255
self.labels_norm_mode = 255
self.input_mean = None
self.input_std = None
self.labels_mean = None
self.labels_std = None
def compile(self,
optimizer=None,
loss=None,
metrics=None,
weighted_metrics=None,
loss_weights=None,
sample_weight_mode=None):
self.keras_model, self.keras_encoder, self.keras_decoder = self.model()
if optimizer is not None:
self.optimizer = optimizer
elif self.optimizer is None or self.optimizer == 'adam':
self.optimizer = Adam(lr=self.lr,
beta_1=self.beta_1,
beta_2=self.beta_2,
epsilon=self.optimizer_epsilon,
decay=0.0)
if metrics is not None:
self.metrics = metrics
self.loss = mean_squared_error if not (loss and self.loss) else loss
self.metrics = [mean_absolute_error, mean_error
] if not self.metrics else self.metrics
self.keras_model.compile(loss=self.loss,
optimizer=self.optimizer,
metrics=self.metrics,
weighted_metrics=weighted_metrics,
loss_weights=loss_weights,
sample_weight_mode=sample_weight_mode)
return None
def pre_training_checklist_child(self, input_data, input_recon_target):
if self.task == 'classification':
raise RuntimeError(
'astroNN VAE does not support classification task')
elif self.task == 'binary_classification':
raise RuntimeError(
'astroNN VAE does not support binary classification task')
self.pre_training_checklist_master(input_data, input_recon_target)
if isinstance(input_data, H5Loader):
self.targetname = input_data.target
input_data, input_recon_target = input_data.load()
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(input_recon_target)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(input_recon_target,
calc=False)
if self.keras_model is None: # only compile if there is no keras_model, e.g. fine-tuning does not required
self.compile()
self.train_idx, self.val_idx = train_test_split(
np.arange(self.num_train + self.val_num), test_size=self.val_size)
self.training_generator = CVAEDataGenerator(
batch_size=self.batch_size,
shuffle=True,
steps_per_epoch=self.num_train // self.batch_size,
data=[norm_data[self.train_idx], norm_labels[self.train_idx]],
manual_reset=False)
val_batchsize = self.batch_size if len(
self.val_idx) > self.batch_size else len(self.val_idx)
self.validation_generator = CVAEDataGenerator(
batch_size=val_batchsize,
shuffle=True,
steps_per_epoch=max(self.val_num // self.batch_size, 1),
data=[norm_data[self.val_idx], norm_labels[self.val_idx]],
manual_reset=True)
return input_data, input_recon_target
def train(self, input_data, input_recon_target):
"""
Train a Convolutional Autoencoder
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param input_recon_target: Data to be reconstructed
:type input_recon_target: ndarray
:return: None
:rtype: NoneType
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
# Call the checklist to create astroNN folder and save parameters
self.pre_training_checklist_child(input_data, input_recon_target)
reduce_lr = ReduceLROnPlateau(monitor='val_output_loss',
factor=0.5,
min_delta=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience,
min_lr=self.reduce_lr_min,
mode='min',
verbose=2)
self.virtual_cvslogger = VirutalCSVLogger()
self.__callbacks = [reduce_lr, self.virtual_cvslogger
] # default must have unchangeable callbacks
if self.callbacks is not None:
if isinstance(self.callbacks, list):
self.__callbacks.extend(self.callbacks)
else:
self.__callbacks.append(self.callbacks)
start_time = time.time()
self.keras_model.fit_generator(
generator=self.training_generator,
validation_data=self.validation_generator,
epochs=self.max_epochs,
verbose=self.verbose,
workers=os.cpu_count(),
callbacks=self.__callbacks,
use_multiprocessing=MULTIPROCESS_FLAG)
print(
f'Completed Training, {(time.time() - start_time):.{2}f}s in total'
)
if self.autosave is True:
# Call the post training checklist to save parameters
self.save()
return None
def train_on_batch(self, input_data, input_recon_target):
"""
Train a AutoEncoder by running a single gradient update on all of your data, suitable for fine-tuning
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param input_recon_target: Data to be reconstructed
:type input_recon_target: ndarray
:return: None
:rtype: NoneType
:History: 2018-Aug-25 - Written - Henry Leung (University of Toronto)
"""
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(input_recon_target)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(input_recon_target,
calc=False)
steps = input_data.shape[0] // self.batch_size if input_data.shape[
0] > self.batch_size else 1
start_time = time.time()
fit_generator = CVAEDataGenerator(batch_size=input_data.shape[0],
shuffle=False,
steps_per_epoch=1,
data=[norm_data, norm_labels])
scores = self.keras_model.fit_generator(
generator=fit_generator,
epochs=1,
verbose=self.verbose,
workers=os.cpu_count(),
use_multiprocessing=MULTIPROCESS_FLAG)
print(
f'Completed Training on Batch, {(time.time() - start_time):.{2}f}s in total'
)
return None
def post_training_checklist_child(self):
self.keras_model.save(self.fullfilepath + _astroNN_MODEL_NAME)
print(_astroNN_MODEL_NAME +
f' saved to {(self.fullfilepath + _astroNN_MODEL_NAME)}')
self.hyper_txt.write(f"Dropout Rate: {self.dropout_rate} \n")
self.hyper_txt.flush()
self.hyper_txt.close()
data = {
'id': self.__class__.__name__,
'pool_length': self.pool_length,
'filterlen': self.filter_len,
'filternum': self.num_filters,
'hidden': self.num_hidden,
'input': self._input_shape,
'labels': self._labels_shape,
'task': self.task,
'activation': self.activation,
'input_mean': self.input_mean.tolist(),
'labels_mean': self.labels_mean.tolist(),
'input_std': self.input_std.tolist(),
'labels_std': self.labels_std.tolist(),
'valsize': self.val_size,
'targetname': self.targetname,
'dropout_rate': self.dropout_rate,
'l1': self.l1,
'l2': self.l2,
'maxnorm': self.maxnorm,
'input_norm_mode': self.input_norm_mode,
'labels_norm_mode': self.labels_norm_mode,
'batch_size': self.batch_size,
'latent': self.latent_dim
}
with open(self.fullfilepath + '/astroNN_model_parameter.json',
'w') as f:
json.dump(data, f, indent=4, sort_keys=True)
def test(self, input_data):
"""
Use the neural network to do inference and get reconstructed data
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:return: reconstructed data
:rtype: ndarry
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
self.pre_testing_checklist_master()
input_data = np.atleast_2d(input_data)
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if input_data.shape[0] < self.batch_size:
self.batch_size = input_data.shape[0]
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
predictions = np.zeros((total_test_num, self._labels_shape, 1))
start_time = time.time()
print("Starting Inference")
# Data Generator for prediction
prediction_generator = CVAEPredDataGenerator(
batch_size=self.batch_size,
shuffle=False,
steps_per_epoch=input_array.shape[0] // self.batch_size,
data=[input_array[:data_gen_shape]])
predictions[:data_gen_shape] = np.asarray(
self.keras_model.predict_generator(prediction_generator))
if remainder_shape != 0:
remainder_data = input_array[data_gen_shape:]
# assume its caused by mono images, so need to expand dim by 1
if len(input_array[0].shape) != len(self._input_shape):
remainder_data = np.expand_dims(remainder_data, axis=-1)
result = self.keras_model.predict(remainder_data)
predictions[data_gen_shape:] = result
if self.labels_normalizer is not None:
predictions[:, :, 0] = self.labels_normalizer.denormalize(
predictions[:, :, 0])
else:
predictions[:, :, 0] *= self.labels_std
predictions[:, :, 0] += self.labels_mean
print(
f'Completed Inference, {(time.time() - start_time):.{2}f}s elapsed'
)
return predictions
def test_encoder(self, input_data):
"""
Use the neural network to do inference and get the hidden layer encoding/representation
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:return: hidden layer encoding/representation
:rtype: ndarray
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
self.pre_testing_checklist_master()
# Prevent shallow copy issue
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if input_data.shape[0] < self.batch_size:
self.batch_size = input_data.shape[0]
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
encoding = np.zeros((total_test_num, self.latent_dim))
start_time = time.time()
print("Starting Inference on Encoder")
# Data Generator for prediction
prediction_generator = CVAEPredDataGenerator(
batch_size=self.batch_size,
shuffle=False,
steps_per_epoch=input_array.shape[0] // self.batch_size,
data=[input_array[:data_gen_shape]])
encoding[:data_gen_shape] = np.asarray(
self.keras_encoder.predict_generator(prediction_generator))
if remainder_shape != 0:
remainder_data = input_array[data_gen_shape:]
# assume its caused by mono images, so need to expand dim by 1
if len(input_array[0].shape) != len(self._input_shape):
remainder_data = np.expand_dims(remainder_data, axis=-1)
result = self.keras_encoder.predict(remainder_data)
encoding[data_gen_shape:] = result
print(
f'Completed Inference on Encoder, {(time.time() - start_time):.{2}f}s elapsed'
)
return encoding
def evaluate(self, input_data, labels):
"""
Evaluate neural network by provided input data and labels/reconstruction target to get back a metrics score
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:param labels: labels
:type labels: ndarray
:return: metrics score
:rtype: float
:History: 2018-May-20 - Written - Henry Leung (University of Toronto)
"""
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
eval_batchsize = self.batch_size if input_data.shape[
0] > self.batch_size else input_data.shape[0]
steps = input_data.shape[0] // self.batch_size if input_data.shape[
0] > self.batch_size else 1
start_time = time.time()
print("Starting Evaluation")
evaluate_generator = CVAEDataGenerator(batch_size=eval_batchsize,
shuffle=False,
steps_per_epoch=steps,
data=[norm_data, norm_labels])
scores = self.keras_model.evaluate_generator(evaluate_generator)
if isinstance(scores, float): # make sure scores is iterable
scores = list(str(scores))
outputname = self.keras_model.output_names
funcname = []
if isinstance(self.keras_model.metrics, dict):
func_list = self.keras_model.metrics[outputname[0]]
else:
func_list = self.keras_model.metrics
for func in func_list:
if hasattr(func, __name__):
funcname.append(func.__name__)
else:
funcname.append(func.__class__.__name__)
# funcname = [func.__name__ for func in self.keras_model.metrics]
output_funcname = [outputname[0] + '_' + name for name in funcname]
list_names = ['loss', *output_funcname]
print(
f'Completed Evaluation, {(time.time() - start_time):.{2}f}s elapsed'
)
return {name: score for name, score in zip(list_names, scores)}
class BayesianCNNBase(NeuralNetMaster, ABC):
"""
Top-level class for a Bayesian convolutional neural network
:History: 2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
def __init__(self):
super().__init__()
self.name = 'Bayesian Convolutional Neural Network'
self._model_type = 'BCNN'
self.initializer = None
self.activation = None
self._last_layer_activation = None
self.num_filters = None
self.filter_len = None
self.pool_length = None
self.num_hidden = None
self.reduce_lr_epsilon = None
self.reduce_lr_min = None
self.reduce_lr_patience = None
self.l1 = None
self.l2 = None
self.maxnorm = None
self.inv_model_precision = None # inverse model precision
self.dropout_rate = 0.2
self.length_scale = 3 # prior length scale
self.mc_num = 100 # increased to 100 due to high performance VI on GPU implemented on 14 April 2018 (Henry)
self.val_size = 0.1
self.disable_dropout = False
self.input_norm_mode = 1
self.labels_norm_mode = 2
self.keras_model_predict = None
def pre_training_checklist_child(self, input_data, labels, input_err,
labels_err):
self.pre_training_checklist_master(input_data, labels)
if isinstance(input_data, H5Loader):
self.targetname = input_data.target
input_data, labels = input_data.load()
# check if exists (exists mean fine-tuning, so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
# No need to care about Magic number as loss function looks for magic num in y_true only
norm_input_err = input_err / self.input_std
norm_labels_err = labels_err / self.labels_std
if self.keras_model is None: # only compiler if there is no keras_model, e.g. fine-tuning does not required
self.compile()
self.train_idx, self.val_idx = train_test_split(
np.arange(self.num_train + self.val_num), test_size=self.val_size)
self.inv_model_precision = (2 * self.num_train *
self.l2) / (self.length_scale**2 *
(1 - self.dropout_rate))
self.training_generator = BayesianCNNDataGenerator(
batch_size=self.batch_size,
shuffle=True,
steps_per_epoch=self.num_train // self.batch_size,
data=[
norm_data[self.train_idx], norm_labels[self.train_idx],
norm_input_err[self.train_idx], norm_labels_err[self.train_idx]
])
val_batchsize = self.batch_size if len(
self.val_idx) > self.batch_size else len(self.val_idx)
self.validation_generator = BayesianCNNDataGenerator(
batch_size=val_batchsize,
shuffle=False,
steps_per_epoch=max(self.val_num // self.batch_size, 1),
data=[
norm_data[self.val_idx], norm_labels[self.val_idx],
norm_input_err[self.val_idx], norm_labels_err[self.val_idx]
])
return norm_data, norm_labels, norm_input_err, norm_labels_err
def compile(self,
optimizer=None,
loss=None,
metrics=None,
loss_weights=None,
sample_weight_mode=None):
if optimizer is not None:
self.optimizer = optimizer
elif self.optimizer is None or self.optimizer == 'adam':
self.optimizer = Adam(lr=self.lr,
beta_1=self.beta_1,
beta_2=self.beta_2,
epsilon=self.optimizer_epsilon,
decay=0.0)
if self.task == 'regression':
if self._last_layer_activation is None:
self._last_layer_activation = 'linear'
elif self.task == 'classification':
if self._last_layer_activation is None:
self._last_layer_activation = 'softmax'
elif self.task == 'binary_classification':
if self._last_layer_activation is None:
self._last_layer_activation = 'sigmoid'
else:
raise RuntimeError(
'Only "regression", "classification" and "binary_classification" are supported'
)
self.keras_model, self.keras_model_predict, output_loss, variance_loss = self.model(
)
if self.task == 'regression':
if self.metrics is None:
self.metrics = [mean_absolute_error, mean_error]
self.keras_model.compile(loss={
'output': output_loss,
'variance_output': variance_loss
},
optimizer=self.optimizer,
loss_weights={
'output': .5,
'variance_output': .5
},
metrics={'output': self.metrics})
elif self.task == 'classification':
if self.metrics is None:
self.metrics = [categorical_accuracy]
self.keras_model.compile(loss={
'output': output_loss,
'variance_output': variance_loss
},
optimizer=self.optimizer,
loss_weights={
'output': .5,
'variance_output': .5
},
metrics={'output': self.metrics})
elif self.task == 'binary_classification':
if self.metrics is None:
self.metrics = [binary_accuracy(from_logits=True)]
self.keras_model.compile(loss={
'output': output_loss,
'variance_output': variance_loss
},
optimizer=self.optimizer,
loss_weights={
'output': .5,
'variance_output': .5
},
metrics={'output': self.metrics})
return None
def train(self, input_data, labels, inputs_err=None, labels_err=None):
"""
Train a Bayesian neural network
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:param inputs_err: Error for input_data (if any), same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:param labels_err: Labels error (if any)
:type labels_err: Union([NoneType, ndarray])
:return: None
:rtype: NoneType
:History:
| 2018-Jan-06 - Written - Henry Leung (University of Toronto)
| 2018-Apr-12 - Updated - Henry Leung (University of Toronto)
"""
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
if labels_err is None:
labels_err = np.zeros_like(labels)
# Call the checklist to create astroNN folder and save parameters
self.pre_training_checklist_child(input_data, labels, inputs_err,
labels_err)
reduce_lr = ReduceLROnPlateau(monitor='val_output_loss',
factor=0.5,
min_delta=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience,
min_lr=self.reduce_lr_min,
mode='min',
verbose=2)
self.virtual_cvslogger = VirutalCSVLogger()
self.__callbacks = [reduce_lr, self.virtual_cvslogger
] # default must have unchangeable callbacks
if self.callbacks is not None:
if isinstance(self.callbacks, list):
self.__callbacks.extend(self.callbacks)
else:
self.__callbacks.append(self.callbacks)
start_time = time.time()
self.history = self.keras_model.fit_generator(
generator=self.training_generator,
validation_data=self.validation_generator,
epochs=self.max_epochs,
verbose=self.verbose,
workers=os.cpu_count(),
callbacks=self.__callbacks,
use_multiprocessing=MULTIPROCESS_FLAG)
print(
f'Completed Training, {(time.time() - start_time):.{2}f}s in total'
)
if self.autosave is True:
# Call the post training checklist to save parameters
self.save()
return None
def train_on_batch(self,
input_data,
labels,
inputs_err=None,
labels_err=None):
"""
Train a Bayesian neural network by running a single gradient update on all of your data, suitable for fine-tuning
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:param inputs_err: Error for input_data (if any), same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:param labels_err: Labels error (if any)
:type labels_err: Union([NoneType, ndarray])
:return: None
:rtype: NoneType
:History:
| 2018-Aug-25 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
if labels_err is None:
labels_err = np.zeros_like(labels)
# check if exists (exists mean fine-tuning, so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
# No need to care about Magic number as loss function looks for magic num in y_true only
norm_input_err = inputs_err / self.input_std
norm_labels_err = labels_err / self.labels_std
start_time = time.time()
fit_generator = BayesianCNNDataGenerator(
batch_size=input_data.shape[0],
shuffle=False,
steps_per_epoch=1,
data=[norm_data, norm_labels, norm_input_err, norm_labels_err])
score = self.keras_model.fit_generator(
fit_generator,
epochs=1,
verbose=self.verbose,
workers=os.cpu_count(),
use_multiprocessing=MULTIPROCESS_FLAG)
print(
f'Completed Training on Batch, {(time.time() - start_time):.{2}f}s in total'
)
return None
def post_training_checklist_child(self):
self.keras_model.save(self.fullfilepath + _astroNN_MODEL_NAME)
print(_astroNN_MODEL_NAME +
f' saved to {(self.fullfilepath + _astroNN_MODEL_NAME)}')
self.hyper_txt.write(f"Dropout Rate: {self.dropout_rate} \n")
self.hyper_txt.flush()
self.hyper_txt.close()
data = {
'id':
self.__class__.__name__
if self._model_identifier is None else self._model_identifier,
'pool_length':
self.pool_length,
'filterlen':
self.filter_len,
'filternum':
self.num_filters,
'hidden':
self.num_hidden,
'input':
self._input_shape,
'labels':
self._labels_shape,
'task':
self.task,
'last_layer_activation':
self._last_layer_activation,
'activation':
self.activation,
'input_mean':
self.input_mean.tolist(),
'inv_tau':
self.inv_model_precision,
'length_scale':
self.length_scale,
'labels_mean':
self.labels_mean.tolist(),
'input_std':
self.input_std.tolist(),
'labels_std':
self.labels_std.tolist(),
'valsize':
self.val_size,
'targetname':
self.targetname,
'dropout_rate':
self.dropout_rate,
'l1':
self.l1,
'l2':
self.l2,
'maxnorm':
self.maxnorm,
'input_norm_mode':
self.input_norm_mode,
'labels_norm_mode':
self.labels_norm_mode,
'batch_size':
self.batch_size
}
with open(self.fullfilepath + '/astroNN_model_parameter.json',
'w') as f:
json.dump(data, f, indent=4, sort_keys=True)
def test(self, input_data, inputs_err=None):
"""
Test model, High performance version designed for fast variational inference on GPU
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:param inputs_err: Error for input_data, same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:return: prediction and prediction uncertainty
:History:
| 2018-Jan-06 - Written - Henry Leung (University of Toronto)
| 2018-Apr-12 - Updated - Henry Leung (University of Toronto)
"""
self.has_model_check()
if gpu_availability() is False and self.mc_num > 25:
warnings.warn(
f'You are using CPU version Tensorflow, doing {self.mc_num} times Monte Carlo Inference can '
f'potentially be very slow! \n '
f'A possible fix is to decrease the mc_num parameter of the model to do less MC Inference \n'
f'This is just a warning, and will not shown if mc_num < 25 on CPU'
)
if self.mc_num < 2:
raise AttributeError("mc_num cannot be smaller than 2")
self.pre_testing_checklist_master()
input_data = np.atleast_2d(input_data)
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
# if no error array then just zeros
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
else:
inputs_err = np.atleast_2d(inputs_err)
inputs_err /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if total_test_num < self.batch_size:
batch_size = total_test_num
else:
batch_size = self.batch_size
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // batch_size) * batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
start_time = time.time()
print("Starting Dropout Variational Inference")
# Data Generator for prediction
prediction_generator = BayesianCNNPredDataGenerator(
batch_size=batch_size,
shuffle=False,
steps_per_epoch=data_gen_shape // batch_size,
data=[input_array[:data_gen_shape], inputs_err[:data_gen_shape]])
new = FastMCInference(self.mc_num)(self.keras_model_predict)
result = np.asarray(new.predict_generator(prediction_generator))
if remainder_shape != 0: # deal with remainder
remainder_generator = BayesianCNNPredDataGenerator(
batch_size=remainder_shape,
shuffle=False,
steps_per_epoch=1,
data=[
input_array[data_gen_shape:], inputs_err[data_gen_shape:]
])
remainder_result = np.asarray(
new.predict_generator(remainder_generator))
if remainder_shape == 1:
remainder_result = np.expand_dims(remainder_result, axis=0)
result = np.concatenate((result, remainder_result))
# in case only 1 test data point, in such case we need to add a dimension
if result.ndim < 3 and batch_size == 1:
result = np.expand_dims(result, axis=0)
half_first_dim = result.shape[
1] // 2 # result.shape[1] is guarantee an even number, otherwise sth is wrong
predictions = result[:, :half_first_dim, 0] # mean prediction
mc_dropout_uncertainty = result[:, :half_first_dim, 1] * (
self.labels_std**2) # model uncertainty
predictions_var = np.exp(result[:, half_first_dim:, 0]) * (
self.labels_std**2) # predictive uncertainty
print(
f'Completed Dropout Variational Inference with {self.mc_num} forward passes, '
f'{(time.time() - start_time):.{2}f}s elapsed')
if self.labels_normalizer is not None:
predictions = self.labels_normalizer.denormalize(predictions)
else:
predictions *= self.labels_std
predictions += self.labels_mean
if self.task == 'regression':
# Predictive variance
pred_var = predictions_var + mc_dropout_uncertainty # epistemic plus aleatoric uncertainty
pred_uncertainty = np.sqrt(pred_var) # Convert back to std error
# final correction from variance to standard derivation
mc_dropout_uncertainty = np.sqrt(mc_dropout_uncertainty)
predictive_uncertainty = np.sqrt(predictions_var)
elif self.task == 'classification':
# we want entropy for classification uncertainty
predicted_class = np.argmax(predictions, axis=1)
mc_dropout_uncertainty = np.ones_like(predicted_class, dtype=float)
predictive_uncertainty = np.ones_like(predicted_class, dtype=float)
# center variance
predictions_var -= 1.
for i in range(predicted_class.shape[0]):
all_prediction = np.array(predictions[i, :])
mc_dropout_uncertainty[i] = -np.sum(
all_prediction * np.log(all_prediction))
predictive_uncertainty[i] = predictions_var[i,
predicted_class[i]]
pred_uncertainty = mc_dropout_uncertainty + predictive_uncertainty
# We only want the predicted class back
predictions = predicted_class
elif self.task == 'binary_classification':
# we want entropy for classification uncertainty, so need prediction in logits space
mc_dropout_uncertainty = -np.sum(predictions * np.log(predictions),
axis=0)
# need to activate before round to int so that the prediction is always 0 or 1
predictions = np.rint(sigmoid(predictions))
predictive_uncertainty = predictions_var
pred_uncertainty = mc_dropout_uncertainty + predictions_var
else:
raise AttributeError('Unknown Task')
return predictions, {
'total': pred_uncertainty,
'model': mc_dropout_uncertainty,
'predictive': predictive_uncertainty
}
@deprecated
def test_old(self, input_data, inputs_err=None):
"""
Tests model, it is recommended to use the new test() instead of this deprecated method
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:param inputs_err: Error for input_data, same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:return: prediction and prediction uncertainty
:History: 2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
self.pre_testing_checklist_master()
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
# if no error array then just zeros
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
else:
inputs_err /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if total_test_num < self.batch_size:
self.batch_size = total_test_num
predictions = np.zeros(
(self.mc_num, total_test_num, self._labels_shape))
predictions_var = np.zeros(
(self.mc_num, total_test_num, self._labels_shape))
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
start_time = time.time()
print("Starting Dropout Variational Inference")
for i in range(self.mc_num):
if i % 5 == 0:
print(
f'Completed {i} of {self.mc_num} Monte Carlo Dropout, {(time.time() - start_time):.{2}f}s '
f'elapsed')
# Data Generator for prediction
prediction_generator = BayesianCNNPredDataGenerator(
batch_size=self.batch_size,
shuffle=False,
steps_per_epoch=data_gen_shape // self.batch_size,
data=[
input_array[:data_gen_shape], inputs_err[:data_gen_shape]
])
result = np.asarray(
self.keras_model_predict.predict_generator(
prediction_generator))
if result.ndim < 2: # in case only 1 test data point, in such case we need to add a dimension
result = np.expand_dims(result, axis=0)
half_first_dim = result.shape[
1] // 2 # result.shape[1] is guarantee an even number, otherwise sth is wrong
predictions[
i, :data_gen_shape] = result[:, :half_first_dim].reshape(
(data_gen_shape, self._labels_shape))
predictions_var[
i, :data_gen_shape] = result[:, half_first_dim:].reshape(
(data_gen_shape, self._labels_shape))
if remainder_shape != 0:
remainder_data = input_array[data_gen_shape:]
remainder_data_err = inputs_err[data_gen_shape:]
# assume its caused by mono images, so need to expand dim by 1
if len(input_array[0].shape) != len(self._input_shape):
remainder_data = np.expand_dims(remainder_data, axis=-1)
remainder_data_err = np.expand_dims(remainder_data_err,
axis=-1)
result = self.keras_model_predict.predict({
'input':
remainder_data,
'input_err':
remainder_data_err
})
predictions[
i, data_gen_shape:] = result[:, :half_first_dim].reshape(
(remainder_shape, self._labels_shape))
predictions_var[
i, data_gen_shape:] = result[:, half_first_dim:].reshape(
(remainder_shape, self._labels_shape))
print(
f'Completed Dropout Variational Inference, {(time.time() - start_time):.{2}f}s in total'
)
if self.labels_normalizer is not None:
predictions = self.labels_normalizer.denormalize(predictions)
else:
predictions *= self.labels_std
predictions += self.labels_mean
pred = np.mean(predictions, axis=0)
if self.task == 'regression':
# Predictive variance
mc_dropout_uncertainty = np.var(predictions, axis=0) # var
predictive_uncertainty = np.mean(np.exp(predictions_var) *
(np.array(self.labels_std)**2),
axis=0)
pred_var = predictive_uncertainty + mc_dropout_uncertainty # epistemic plus aleatoric uncertainty
pred_uncertainty = np.sqrt(pred_var) # Convert back to std error
# final correction from variance to standard derivation
mc_dropout_uncertainty = np.sqrt(mc_dropout_uncertainty)
predictive_uncertainty = np.sqrt(predictive_uncertainty)
elif self.task == 'classification':
# we want entropy for classification uncertainty
pred_shape = pred.shape[0]
pred = np.argmax(pred, axis=1)
predictions_var = np.mean(predictions_var, axis=0)
mc_dropout_uncertainty = np.ones_like(pred, dtype=float)
predictive_uncertainty = np.ones_like(pred, dtype=float)
for i in range(pred_shape):
all_prediction = np.array(predictions[:, i, pred[i]])
mc_dropout_uncertainty[i] = -np.sum(
all_prediction * np.log(all_prediction))
predictive_uncertainty[i] = np.array(predictions_var[i,
pred[i]])
pred_uncertainty = mc_dropout_uncertainty + predictive_uncertainty
elif self.task == 'binary_classification':
# we want entropy for classification uncertainty
mc_dropout_uncertainty = -np.sum(
pred * np.log(pred),
axis=0) # need to use raw prediction for uncertainty
pred = np.rint(pred)
predictive_uncertainty = np.mean(predictions_var, axis=0)
pred_uncertainty = mc_dropout_uncertainty + predictive_uncertainty
else:
raise AttributeError('Unknown Task')
return pred, {
'total': pred_uncertainty,
'model': mc_dropout_uncertainty,
'predictive': predictive_uncertainty
}
def evaluate(self, input_data, labels, inputs_err=None, labels_err=None):
"""
Evaluate neural network by provided input data and labels and get back a metrics score
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:param inputs_err: Error for input_data (if any), same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:param labels_err: Labels error (if any)
:type labels_err: Union([NoneType, ndarray])
:return: metrics score dictionary
:rtype: dict
:History: 2018-May-20 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
if labels_err is None:
labels_err = np.zeros_like(labels)
# check if exists (exists mean fine-tuning, so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
# No need to care about Magic number as loss function looks for magic num in y_true only
norm_input_err = inputs_err / self.input_std
norm_labels_err = labels_err / self.labels_std
eval_batchsize = self.batch_size if input_data.shape[
0] > self.batch_size else input_data.shape[0]
steps = input_data.shape[0] // self.batch_size if input_data.shape[
0] > self.batch_size else 1
start_time = time.time()
print("Starting Evaluation")
evaluate_generator = BayesianCNNDataGenerator(
batch_size=eval_batchsize,
shuffle=False,
steps_per_epoch=steps,
data=[norm_data, norm_labels, norm_input_err, norm_labels_err])
scores = self.keras_model.evaluate_generator(evaluate_generator)
outputname = self.keras_model.output_names
funcname = []
if isinstance(self.keras_model.metrics, dict):
func_list = self.keras_model.metrics[outputname[0]]
else:
func_list = self.keras_model.metrics
for func in func_list:
if hasattr(func, __name__):
funcname.append(func.__name__)
else:
funcname.append(func.__class__.__name__)
# funcname = [func.__name__ for func in self.keras_model.metrics[outputname[0]]]
loss_outputname = ['loss_' + name for name in outputname]
output_funcname = [outputname[0] + '_' + name for name in funcname]
list_names = ['loss', *loss_outputname, *output_funcname]
print(
f'Completed Evaluation, {(time.time() - start_time):.{2}f}s elapsed'
)
return {name: score for name, score in zip(list_names, scores)}
class CNNBase(NeuralNetMaster, ABC):
"""Top-level class for a convolutional neural network"""
def __init__(self):
"""
NAME:
__init__
PURPOSE:
To define astroNN convolutional neural network
HISTORY:
2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
super().__init__()
self.name = 'Convolutional Neural Network'
self._model_type = 'CNN'
self._model_identifier = None
self.initializer = None
self.activation = None
self._last_layer_activation = None
self.num_filters = None
self.filter_len = None
self.pool_length = None
self.num_hidden = None
self.reduce_lr_epsilon = None
self.reduce_lr_min = None
self.reduce_lr_patience = None
self.l1 = None
self.l2 = None
self.maxnorm = None
self.dropout_rate = 0.0
self.val_size = 0.1
self.early_stopping_min_delta = 0.0001
self.early_stopping_patience = 4
self.input_norm_mode = 1
self.labels_norm_mode = 2
def compile(self,
optimizer=None,
loss=None,
metrics=None,
loss_weights=None,
sample_weight_mode=None):
if optimizer is not None:
self.optimizer = optimizer
elif self.optimizer is None or self.optimizer == 'adam':
self.optimizer = Adam(lr=self.lr,
beta_1=self.beta_1,
beta_2=self.beta_2,
epsilon=self.optimizer_epsilon,
decay=0.0)
if self.task == 'regression':
self._last_layer_activation = 'linear'
loss_func = mean_squared_error
if self.metrics is None:
self.metrics = [mean_absolute_error, mean_error]
elif self.task == 'classification':
self._last_layer_activation = 'softmax'
loss_func = categorical_crossentropy
if self.metrics is None:
self.metrics = [categorical_accuracy]
elif self.task == 'binary_classification':
self._last_layer_activation = 'sigmoid'
loss_func = binary_crossentropy
if self.metrics is None:
self.metrics = [binary_accuracy(from_logits=False)]
else:
raise RuntimeError(
'Only "regression", "classification" and "binary_classification" are supported'
)
self.keras_model = self.model()
self.keras_model.compile(loss=loss_func,
optimizer=self.optimizer,
metrics=self.metrics,
loss_weights=None)
return None
def pre_training_checklist_child(self, input_data, labels):
self.pre_training_checklist_master(input_data, labels)
# check if exists (exists mean fine-tuning, so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
if self.keras_model is None: # only compiler if there is no keras_model, e.g. fine-tuning does not required
self.compile()
self.train_idx, self.val_idx = train_test_split(
np.arange(self.num_train), test_size=self.val_size)
self.training_generator = CNNDataGenerator(self.batch_size).generate(
norm_data[self.train_idx], norm_labels[self.train_idx])
self.validation_generator = CNNDataGenerator(self.batch_size if len(
self.val_idx) > self.batch_size else len(self.val_idx)).generate(
norm_data[self.val_idx], norm_labels[self.val_idx])
return input_data, labels
def train(self, input_data, labels):
"""
Train a Convolutional neural network
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:return: None
:rtype: NoneType
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
# Call the checklist to create astroNN folder and save parameters
self.pre_training_checklist_child(input_data, labels)
try:
reduce_lr = ReduceLROnPlateau(monitor='val_mean_absolute_error',
factor=0.5,
min_delta=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience,
min_lr=self.reduce_lr_min,
mode='min',
verbose=2)
except TypeError:
reduce_lr = ReduceLROnPlateau(monitor='val_mean_absolute_error',
factor=0.5,
epsilon=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience,
min_lr=self.reduce_lr_min,
mode='min',
verbose=2)
early_stopping = EarlyStopping(monitor='val_mean_absolute_error',
min_delta=self.early_stopping_min_delta,
patience=self.early_stopping_patience,
verbose=2,
mode='min')
self.virtual_cvslogger = VirutalCSVLogger()
self.__callbacks = [reduce_lr, self.virtual_cvslogger
] # default must have unchangeable callbacks
if self.callbacks is not None:
if isinstance(self.callbacks, list):
self.__callbacks.extend(self.callbacks)
else:
self.__callbacks.append(self.callbacks)
start_time = time.time()
self.history = self.keras_model.fit_generator(
generator=self.training_generator,
steps_per_epoch=self.num_train // self.batch_size,
validation_data=self.validation_generator,
validation_steps=max(self.val_num // self.batch_size, 1),
epochs=self.max_epochs,
verbose=self.verbose,
workers=os.cpu_count(),
callbacks=self.__callbacks,
use_multiprocessing=MULTIPROCESS_FLAG)
print(
f'Completed Training, {(time.time() - start_time):.{2}f}s in total'
)
if self.autosave is True:
# Call the post training checklist to save parameters
self.save()
return None
def post_training_checklist_child(self):
self.keras_model.save(self.fullfilepath + _astroNN_MODEL_NAME)
print(_astroNN_MODEL_NAME +
f' saved to {(self.fullfilepath + _astroNN_MODEL_NAME)}')
self.hyper_txt.write(f"Dropout Rate: {self.dropout_rate} \n")
self.hyper_txt.flush()
self.hyper_txt.close()
data = {
'id':
self.__class__.__name__
if self._model_identifier is None else self._model_identifier,
'pool_length':
self.pool_length,
'filterlen':
self.filter_len,
'filternum':
self.num_filters,
'hidden':
self.num_hidden,
'input':
self._input_shape,
'labels':
self._labels_shape,
'task':
self.task,
'input_mean':
self.input_mean.tolist(),
'labels_mean':
self.labels_mean.tolist(),
'input_std':
self.input_std.tolist(),
'labels_std':
self.labels_std.tolist(),
'valsize':
self.val_size,
'targetname':
self.targetname,
'dropout_rate':
self.dropout_rate,
'l1':
self.l1,
'l2':
self.l2,
'maxnorm':
self.maxnorm,
'input_norm_mode':
self.input_norm_mode,
'labels_norm_mode':
self.labels_norm_mode,
'batch_size':
self.batch_size
}
with open(self.fullfilepath + '/astroNN_model_parameter.json',
'w') as f:
json.dump(data, f, indent=4, sort_keys=True)
def test(self, input_data):
"""
Use the neural network to do inference
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:return: prediction and prediction uncertainty
:rtype: ndarry
:History: 2017-Dec-06 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
self.pre_testing_checklist_master()
input_data = np.atleast_2d(input_data)
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if input_data.shape[0] < self.batch_size:
self.batch_size = input_data.shape[0]
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
predictions = np.zeros((total_test_num, self._labels_shape))
# Data Generator for prediction
prediction_generator = CNNPredDataGenerator(self.batch_size).generate(
input_array[:data_gen_shape])
predictions[:data_gen_shape] = np.asarray(
self.keras_model.predict_generator(prediction_generator,
steps=input_array.shape[0] //
self.batch_size))
if remainder_shape != 0:
remainder_data = input_array[data_gen_shape:]
# assume its caused by mono images, so need to expand dim by 1
if len(input_array[0].shape) != len(self._input_shape):
remainder_data = np.expand_dims(remainder_data, axis=-1)
result = self.keras_model.predict(remainder_data)
predictions[data_gen_shape:] = result.reshape(
(remainder_shape, self._labels_shape))
if self.labels_normalizer is not None:
predictions = self.labels_normalizer.denormalize(predictions)
else:
predictions *= self.labels_std
predictions += self.labels_mean
return predictions
def evaluate(self, input_data, labels):
"""
Evaluate neural network by provided input data and labels and get back a metrics score
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:param labels: labels
:type labels: ndarray
:return: metrics score dictionary
:rtype: dict
:History: 2018-May-20 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
# check if exists (exists mean fine-tuning, so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
eval_batchsize = self.batch_size if input_data.shape[
0] > self.batch_size else input_data.shape[0]
steps = input_data.shape[0] // self.batch_size if input_data.shape[
0] > self.batch_size else 1
evaluate_generator = CNNDataGenerator(eval_batchsize,
shuffle=False).generate(
norm_data, norm_labels)
scores = self.keras_model.evaluate_generator(evaluate_generator,
steps=steps)
outputname = self.keras_model.output_names
funcname = [func.__name__ for func in self.keras_model.metrics]
loss_outputname = ['loss_' + name for name in outputname]
output_funcname = [outputname[0] + '_' + name for name in funcname]
list_names = ['loss', *loss_outputname, *output_funcname]
return {name: score for name, score in zip(list_names, scores)}
class BayesianCNNBase(NeuralNetMaster, ABC):
"""
Top-level class for a Bayesian convolutional neural network
:History: 2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
def __init__(self):
super().__init__()
self.name = 'Bayesian Convolutional Neural Network'
self._model_type = 'BCNN'
self.initializer = None
self.activation = None
self._last_layer_activation = None
self.num_filters = None
self.filter_len = None
self.pool_length = None
self.num_hidden = None
self.reduce_lr_epsilon = None
self.reduce_lr_min = None
self.reduce_lr_patience = None
self.l1 = None
self.l2 = None
self.maxnorm = None
self.inv_model_precision = None # inverse model precision
self.dropout_rate = 0.2
self.length_scale = 3 # prior length scale
self.mc_num = 100 # increased to 100 due to high performance VI on GPU implemented on 14 April 2018 (Henry)
self.val_size = 0.1
self.disable_dropout = False
self.output_loss = None
self.variance_loss = None
self.input_norm_mode = 1
self.labels_norm_mode = 2
self.keras_model_predict = None
def pre_training_checklist_child(self, input_data, labels):
input_data, labels = self.pre_training_checklist_master(input_data, labels)
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
# No need to care about Magic number as loss function looks for magic num in y_true only
norm_data.update({"input_err": (input_data['input_err'] / self.input_std['input']),
"labels_err": input_data['labels_err'] / self.labels_std['output']})
norm_labels.update({"variance_output": norm_labels['output']})
if self.keras_model is None: # only compile if there is no keras_model, e.g. fine-tuning does not required
self.compile()
self.train_idx, self.val_idx = train_test_split(np.arange(self.num_train + self.val_num),
test_size=self.val_size)
norm_data_training = {}
norm_data_val = {}
norm_labels_training = {}
norm_labels_val = {}
for name in norm_data.keys():
norm_data_training.update({name: norm_data[name][self.train_idx]})
norm_data_val.update({name: norm_data[name][self.val_idx]})
for name in norm_labels.keys():
norm_labels_training.update({name: norm_labels[name][self.train_idx]})
norm_labels_val.update({name: norm_labels[name][self.val_idx]})
self.inv_model_precision = (2 * self.num_train * self.l2) / (self.length_scale ** 2 * (1 - self.dropout_rate))
self.training_generator = BayesianCNNDataGenerator(batch_size=self.batch_size,
shuffle=True,
steps_per_epoch=self.num_train // self.batch_size,
data=[norm_data_training,
norm_labels_training],
manual_reset=False)
val_batchsize = self.batch_size if len(self.val_idx) > self.batch_size else len(self.val_idx)
self.validation_generator = BayesianCNNDataGenerator(batch_size=val_batchsize,
shuffle=False,
steps_per_epoch=max(self.val_num // self.batch_size, 1),
data=[norm_data_val,
norm_labels_val],
manual_reset=True)
return norm_data, norm_labels
def compile(self, optimizer=None,
loss=None,
metrics=None,
weighted_metrics=None,
loss_weights=None,
sample_weight_mode=None):
if optimizer is not None:
self.optimizer = optimizer
elif self.optimizer is None or self.optimizer == 'adam':
self.optimizer = Adam(lr=self.lr, beta_1=self.beta_1, beta_2=self.beta_2, epsilon=self.optimizer_epsilon,
decay=0.0)
if metrics is not None:
self.metrics = metrics
if self.task == 'regression':
if self._last_layer_activation is None:
self._last_layer_activation = 'linear'
elif self.task == 'classification':
if self._last_layer_activation is None:
self._last_layer_activation = 'softmax'
elif self.task == 'binary_classification':
if self._last_layer_activation is None:
self._last_layer_activation = 'sigmoid'
else:
raise RuntimeError('Only "regression", "classification" and "binary_classification" are supported')
self.keras_model, self.keras_model_predict, self.output_loss, self.variance_loss = self.model()
# all mse losss as dummy lose
if self.task == 'regression':
self.metrics = [mean_absolute_error, mean_error] if not self.metrics else self.metrics
self.keras_model.compile(loss={'output': mean_squared_error, 'variance_output': mean_squared_error},
optimizer=self.optimizer,
metrics={'output': self.metrics},
weighted_metrics=weighted_metrics,
loss_weights={'output': .5,
'variance_output': .5} if not loss_weights else loss_weights,
sample_weight_mode=sample_weight_mode)
elif self.task == 'classification':
self.metrics = [categorical_accuracy] if not self.metrics else self.metrics
self.keras_model.compile(loss={'output': mean_squared_error, 'variance_output': mean_squared_error},
optimizer=self.optimizer,
metrics={'output': self.metrics},
weighted_metrics=weighted_metrics,
loss_weights={'output': .5,
'variance_output': .5} if not loss_weights else loss_weights,
sample_weight_mode=sample_weight_mode)
elif self.task == 'binary_classification':
self.metrics = [binary_accuracy] if not self.metrics else self.metrics
self.keras_model.compile(loss={'output': mean_squared_error, 'variance_output': mean_squared_error},
optimizer=self.optimizer,
metrics={'output': self.metrics},
weighted_metrics=weighted_metrics,
loss_weights={'output': .5,
'variance_output': .5} if not loss_weights else loss_weights,
sample_weight_mode=sample_weight_mode)
# inject custom training step if needed
try:
self.custom_train_step()
except NotImplementedError:
pass
except TypeError:
self.keras_model.train_step = self.custom_train_step
return None
def custom_train_step(self, data):
"""
Custom training logic
:param data:
:return:
"""
data = data_adapter.expand_1d(data)
x, y, sample_weight = data_adapter.unpack_x_y_sample_weight(data)
with tf.python.eager.backprop.GradientTape() as tape:
y_pred = self.keras_model(x, training=True)
loss = self.keras_model.compiled_loss(y, y_pred, sample_weight, regularization_losses=self.keras_model.losses)
if self.task == 'regression':
variance_loss = mse_var_wrapper(y_pred[0], x['labels_err'])
output_loss = mse_lin_wrapper(y_pred[1], x['labels_err'])
elif self.task == 'classification':
output_loss = bayesian_categorical_crossentropy_wrapper(y_pred[1])
variance_loss = bayesian_categorical_crossentropy_var_wrapper(y_pred[0])
elif self.task == 'binary_classification':
output_loss = bayesian_binary_crossentropy_wrapper(y_pred[1])
variance_loss = bayesian_binary_crossentropy_var_wrapper(y_pred[0])
else:
raise RuntimeError('Only "regression", "classification" and "binary_classification" are supported')
loss = output_loss(y['output'], y_pred[0]) + variance_loss(y['variance_output'], y_pred[1])
# apply gradient here
tf.python.keras.engine.training._minimize(self.keras_model.distribute_strategy,
tape,
self.keras_model.optimizer,
loss,
self.keras_model.trainable_variables)
self.keras_model.compiled_metrics.update_state(y, y_pred, sample_weight)
return {m.name: m.result() for m in self.keras_model.metrics}
def train(self, input_data, labels, inputs_err=None, labels_err=None):
"""
Train a Bayesian neural network
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:param inputs_err: Error for input_data (if any), same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:param labels_err: Labels error (if any)
:type labels_err: Union([NoneType, ndarray])
:return: None
:rtype: NoneType
:History:
| 2018-Jan-06 - Written - Henry Leung (University of Toronto)
| 2018-Apr-12 - Updated - Henry Leung (University of Toronto)
"""
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
if labels_err is None:
labels_err = np.zeros_like(labels)
# TODO: allow named inputs too??
input_data = {"input": input_data, "input_err": inputs_err, "labels_err": labels_err}
labels = {"output": labels, "variance_output": labels}
# Call the checklist to create astroNN folder and save parameters
input_data, labels = self.pre_training_checklist_child(input_data, labels)
reduce_lr = ReduceLROnPlateau(monitor='val_output_loss', factor=0.5, min_delta=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience, min_lr=self.reduce_lr_min, mode='min',
verbose=2)
self.virtual_cvslogger = VirutalCSVLogger()
self.__callbacks = [reduce_lr, self.virtual_cvslogger] # default must have unchangeable callbacks
if self.callbacks is not None:
if isinstance(self.callbacks, list):
self.__callbacks.extend(self.callbacks)
else:
self.__callbacks.append(self.callbacks)
start_time = time.time()
self.history = self.keras_model.fit(self.training_generator,
validation_data=self.validation_generator,
epochs=self.max_epochs, verbose=self.verbose,
workers=os.cpu_count(),
callbacks=self.__callbacks,
use_multiprocessing=MULTIPROCESS_FLAG)
print(f'Completed Training, {(time.time() - start_time):.{2}f}s in total')
if self.autosave is True:
# Call the post training checklist to save parameters
self.save()
return None
def train_on_batch(self, input_data, labels, inputs_err=None, labels_err=None):
"""
Train a Bayesian neural network by running a single gradient update on all of your data, suitable for fine-tuning
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:param inputs_err: Error for input_data (if any), same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:param labels_err: Labels error (if any)
:type labels_err: Union([NoneType, ndarray])
:return: None
:rtype: NoneType
:History:
| 2018-Aug-25 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
if labels_err is None:
labels_err = np.zeros_like(labels)
input_data = {"input": input_data, "input_err": inputs_err, "labels_err": labels_err}
labels = {"output": labels, "variance_output": labels}
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
# No need to care about Magic number as loss function looks for magic num in y_true only
norm_data.update({"input_err": (input_data['input_err'] / self.input_std['input']),
"labels_err": input_data['labels_err'] / self.labels_std['output']})
norm_labels.update({"variance_output": norm_labels['output']})
start_time = time.time()
fit_generator = BayesianCNNDataGenerator(batch_size=input_data['input'].shape[0],
shuffle=False,
steps_per_epoch=1,
data=[norm_data,
norm_labels])
score = self.keras_model.fit(fit_generator,
epochs=1,
verbose=self.verbose,
workers=os.cpu_count(),
use_multiprocessing=MULTIPROCESS_FLAG)
print(f'Completed Training on Batch, {(time.time() - start_time):.{2}f}s in total')
return None
def post_training_checklist_child(self):
self.keras_model.save(self.fullfilepath + _astroNN_MODEL_NAME)
print(_astroNN_MODEL_NAME + f' saved to {(self.fullfilepath + _astroNN_MODEL_NAME)}')
self.hyper_txt.write(f"Dropout Rate: {self.dropout_rate} \n")
self.hyper_txt.flush()
self.hyper_txt.close()
data = {'id': self.__class__.__name__ if self._model_identifier is None else self._model_identifier,
'pool_length': self.pool_length,
'filterlen': self.filter_len,
'filternum': self.num_filters,
'hidden': self.num_hidden,
'input': self._input_shape,
'labels': self._labels_shape,
'task': self.task,
'last_layer_activation': self._last_layer_activation,
'activation': self.activation,
'input_mean': dict_np_to_dict_list(self.input_mean),
'inv_tau': self.inv_model_precision,
'length_scale': self.length_scale,
'labels_mean': dict_np_to_dict_list(self.labels_mean),
'input_std': dict_np_to_dict_list(self.input_std),
'labels_std': dict_np_to_dict_list(self.labels_std),
'valsize': self.val_size,
'targetname': self.targetname,
'dropout_rate': self.dropout_rate,
'l1': self.l1,
'l2': self.l2,
'maxnorm': self.maxnorm,
'input_norm_mode': self.input_normalizer.normalization_mode,
'labels_norm_mode': self.labels_normalizer.normalization_mode,
'input_names': self.input_names,
'output_names': self.output_names,
'batch_size': self.batch_size}
with open(self.fullfilepath + '/astroNN_model_parameter.json', 'w') as f:
json.dump(data, f, indent=4, sort_keys=True)
def test(self, input_data, inputs_err=None):
"""
Test model, High performance version designed for fast variational inference on GPU
:param input_data: Data to be inferred with neural network
:type input_data: ndarray
:param inputs_err: Error for input_data, same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:return: prediction and prediction uncertainty
:History:
| 2018-Jan-06 - Written - Henry Leung (University of Toronto)
| 2018-Apr-12 - Updated - Henry Leung (University of Toronto)
"""
self.has_model_check()
if gpu_availability() is False and self.mc_num > 25:
warnings.warn(f'You are using CPU version Tensorflow, doing {self.mc_num} times Monte Carlo Inference can '
f'potentially be very slow! \n '
f'A possible fix is to decrease the mc_num parameter of the model to do less MC Inference \n'
f'This is just a warning, and will not shown if mc_num < 25 on CPU')
if self.mc_num < 2:
raise AttributeError("mc_num cannot be smaller than 2")
# if no error array then just zeros
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
else:
inputs_err = np.atleast_2d(inputs_err)
inputs_err /= self.input_std['input']
input_data = {"input": input_data, "input_err": inputs_err}
input_data = self.pre_testing_checklist_master(input_data)
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data, calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean['input']
input_array /= self.input_std['input']
total_test_num = input_data['input'].shape[0] # Number of testing data
# for number of training data smaller than batch_size
if total_test_num < self.batch_size:
batch_size = total_test_num
else:
batch_size = self.batch_size
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // batch_size) * batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
norm_data_main = {}
norm_data_remainder = {}
for name in input_array.keys():
norm_data_main.update({name: input_array[name][:data_gen_shape]})
norm_data_remainder.update({name: input_array[name][data_gen_shape:]})
start_time = time.time()
print("Starting Dropout Variational Inference")
# Data Generator for prediction
prediction_generator = BayesianCNNPredDataGenerator(batch_size=batch_size,
shuffle=False,
steps_per_epoch=data_gen_shape // batch_size,
data=[norm_data_main])
new = FastMCInference(self.mc_num)(self.keras_model_predict)
result = np.asarray(new.predict(prediction_generator))
if remainder_shape != 0: # deal with remainder
remainder_generator = BayesianCNNPredDataGenerator(batch_size=remainder_shape,
shuffle=False,
steps_per_epoch=1,
data=[norm_data_remainder])
remainder_result = np.asarray(new.predict(remainder_generator))
if remainder_shape == 1:
remainder_result = np.expand_dims(remainder_result, axis=0)
result = np.concatenate((result, remainder_result))
# in case only 1 test data point, in such case we need to add a dimension
if result.ndim < 3 and batch_size == 1:
result = np.expand_dims(result, axis=0)
half_first_dim = result.shape[1] // 2 # result.shape[1] is guarantee an even number, otherwise sth is wrong
predictions = result[:, :half_first_dim, 0] # mean prediction
mc_dropout_uncertainty = result[:, :half_first_dim, 1] * (self.labels_std['output'] ** 2) # model uncertainty
predictions_var = np.exp(result[:, half_first_dim:, 0]) * (
self.labels_std['output'] ** 2) # predictive uncertainty
print(f'Completed Dropout Variational Inference with {self.mc_num} forward passes, '
f'{(time.time() - start_time):.{2}f}s elapsed')
if self.labels_normalizer is not None:
predictions = self.labels_normalizer.denormalize(
list_to_dict([self.keras_model.output_names[0]], predictions))
predictions = predictions['output']
else:
predictions *= self.labels_std['output']
predictions += self.labels_mean['output']
if self.task == 'regression':
# Predictive variance
pred_var = predictions_var + mc_dropout_uncertainty # epistemic plus aleatoric uncertainty
pred_uncertainty = np.sqrt(pred_var) # Convert back to std error
# final correction from variance to standard derivation
mc_dropout_uncertainty = np.sqrt(mc_dropout_uncertainty)
predictive_uncertainty = np.sqrt(predictions_var)
elif self.task == 'classification':
# we want entropy for classification uncertainty
predicted_class = np.argmax(predictions, axis=1)
mc_dropout_uncertainty = np.ones_like(predicted_class, dtype=float)
predictive_uncertainty = np.ones_like(predicted_class, dtype=float)
# center variance
predictions_var -= 1.
for i in range(predicted_class.shape[0]):
all_prediction = np.array(predictions[i, :])
mc_dropout_uncertainty[i] = - np.sum(all_prediction * np.log(all_prediction))
predictive_uncertainty[i] = predictions_var[i, predicted_class[i]]
pred_uncertainty = mc_dropout_uncertainty + predictive_uncertainty
# We only want the predicted class back
predictions = predicted_class
elif self.task == 'binary_classification':
# we want entropy for classification uncertainty, so need prediction in logits space
mc_dropout_uncertainty = - np.sum(predictions * np.log(predictions), axis=0)
# need to activate before round to int so that the prediction is always 0 or 1
predictions = np.rint(sigmoid(predictions))
predictive_uncertainty = predictions_var
pred_uncertainty = mc_dropout_uncertainty + predictions_var
else:
raise AttributeError('Unknown Task')
return predictions, {'total': pred_uncertainty, 'model': mc_dropout_uncertainty,
'predictive': predictive_uncertainty}
def evaluate(self, input_data, labels, inputs_err=None, labels_err=None):
"""
Evaluate neural network by provided input data and labels and get back a metrics score
:param input_data: Data to be trained with neural network
:type input_data: ndarray
:param labels: Labels to be trained with neural network
:type labels: ndarray
:param inputs_err: Error for input_data (if any), same shape with input_data.
:type inputs_err: Union([NoneType, ndarray])
:param labels_err: Labels error (if any)
:type labels_err: Union([NoneType, ndarray])
:return: metrics score dictionary
:rtype: dict
:History: 2018-May-20 - Written - Henry Leung (University of Toronto)
"""
self.has_model_check()
if inputs_err is None:
inputs_err = np.zeros_like(input_data)
if labels_err is None:
labels_err = np.zeros_like(labels)
input_data = {"input": input_data}
labels = {"output": labels}
# check if exists (existing means the model has already been trained (e.g. fine-tuning), so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(labels)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(labels, calc=False)
# No need to care about Magic number as loss function looks for magic num in y_true only
norm_input_err = inputs_err / self.input_std['input']
norm_labels_err = labels_err / self.labels_std['output']
norm_data.update({"input_err": norm_input_err, "labels_err": norm_labels_err})
norm_labels.update({"variance_output": norm_labels["output"]})
total_num = input_data['input'].shape[0]
eval_batchsize = self.batch_size if total_num > self.batch_size else total_num
steps = total_num // self.batch_size if total_num > self.batch_size else 1
start_time = time.time()
print("Starting Evaluation")
evaluate_generator = BayesianCNNDataGenerator(batch_size=eval_batchsize,
shuffle=False,
steps_per_epoch=steps,
data=[norm_data,
norm_labels])
scores = self.keras_model.evaluate(evaluate_generator)
if isinstance(scores, float): # make sure scores is iterable
scores = list(str(scores))
outputname = self.keras_model.output_names
funcname = self.keras_model.metrics_names
print(f'Completed Evaluation, {(time.time() - start_time):.{2}f}s elapsed')
return list_to_dict(funcname, scores)
class ConvVAEBase(NeuralNetMaster, ABC):
"""Top-level class for a Convolutional Variational Autoencoder"""
def __init__(self):
"""
NAME:
__init__
PURPOSE:
To define astroNN Convolutional Variational Autoencoder
HISTORY:
2018-Jan-06 - Written - Henry Leung (University of Toronto)
"""
super().__init__()
self.name = 'Convolutional Variational Autoencoder'
self._model_type = 'CVAE'
self.initializer = None
self.activation = None
self._last_layer_activation = None
self.num_filters = None
self.filter_len = None
self.pool_length = None
self.num_hidden = None
self.reduce_lr_epsilon = None
self.reduce_lr_min = None
self.reduce_lr_patience = None
self.l2 = None
self.latent_dim = None
self.val_size = 0.1
self.dropout_rate = 0.0
self.keras_vae = None
self.keras_encoder = None
self.keras_decoder = None
self.loss = None
self.input_shape = None
self.input_norm_mode = 255
self.labels_norm_mode = 255
self.input_mean = None
self.input_std = None
self.labels_mean = None
self.labels_std = None
def compile(self,
optimizer=None,
loss=None,
metrics=None,
loss_weights=None,
sample_weight_mode=None):
self.keras_model, self.keras_encoder, self.keras_decoder = self.model()
if optimizer is not None:
self.optimizer = optimizer
elif self.optimizer is None or self.optimizer == 'adam':
self.optimizer = Adam(lr=self.lr,
beta_1=self.beta_1,
beta_2=self.beta_2,
epsilon=self.optimizer_epsilon,
decay=0.0)
if self.loss is None:
self.loss = mean_squared_error
self.keras_model.compile(loss=self.loss, optimizer=self.optimizer)
return None
def pre_training_checklist_child(self, input_data, input_recon_target):
if self.task == 'classification':
raise RuntimeError(
'astroNN VAE does not support classification task')
elif self.task == 'binary_classification':
raise RuntimeError(
'astroNN VAE does not support binary classification task')
self.pre_training_checklist_master(input_data, input_recon_target)
if isinstance(input_data, H5Loader):
self.targetname = input_data.target
input_data, input_recon_target = input_data.load()
# check if exists (exists mean fine-tuning, so we do not need calculate mean/std again)
if self.input_normalizer is None:
self.input_normalizer = Normalizer(mode=self.input_norm_mode)
self.labels_normalizer = Normalizer(mode=self.labels_norm_mode)
norm_data = self.input_normalizer.normalize(input_data)
self.input_mean, self.input_std = self.input_normalizer.mean_labels, self.input_normalizer.std_labels
norm_labels = self.labels_normalizer.normalize(input_recon_target)
self.labels_mean, self.labels_std = self.labels_normalizer.mean_labels, self.labels_normalizer.std_labels
else:
norm_data = self.input_normalizer.normalize(input_data, calc=False)
norm_labels = self.labels_normalizer.normalize(input_recon_target,
calc=False)
if self.keras_model is None: # only compiler if there is no keras_model, e.g. fine-tuning does not required
self.compile()
self.train_idx, self.val_idx = train_test_split(
np.arange(self.num_train), test_size=self.val_size)
self.training_generator = CVAEDataGenerator(self.batch_size).generate(
norm_data[self.train_idx], norm_labels[self.train_idx])
self.validation_generator = CVAEDataGenerator(
self.batch_size).generate(norm_data[self.val_idx],
norm_labels[self.val_idx])
return input_data, input_recon_target
def train(self, input_data, input_recon_target):
# Call the checklist to create astroNN folder and save parameters
self.pre_training_checklist_child(input_data, input_recon_target)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.5,
min_delta=self.reduce_lr_epsilon,
patience=self.reduce_lr_patience,
min_lr=self.reduce_lr_min,
mode='min',
verbose=2)
self.virtual_cvslogger = VirutalCSVLogger()
self.__callbacks = [reduce_lr, self.virtual_cvslogger
] # default must have unchangeable callbacks
if self.callbacks is not None:
if isinstance(self.callbacks, list):
self.__callbacks.extend(self.callbacks)
else:
self.__callbacks.append(self.callbacks)
start_time = time.time()
self.keras_model.fit_generator(
generator=self.training_generator,
steps_per_epoch=self.num_train // self.batch_size,
validation_data=self.validation_generator,
validation_steps=self.val_num // self.batch_size,
epochs=self.max_epochs,
verbose=self.verbose,
workers=os.cpu_count(),
callbacks=self.__callbacks,
use_multiprocessing=MULTIPROCESS_FLAG)
print(
f'Completed Training, {(time.time() - start_time):.{2}f}s in total'
)
if self.autosave is True:
# Call the post training checklist to save parameters
self.save()
return None
def post_training_checklist_child(self):
astronn_model = 'model_weights.h5'
self.keras_model.save(self.fullfilepath + astronn_model)
print(astronn_model +
f' saved to {(self.fullfilepath + astronn_model)}')
self.hyper_txt.write(f"Dropout Rate: {self.dropout_rate} \n")
self.hyper_txt.flush()
self.hyper_txt.close()
data = {
'id': self.__class__.__name__,
'pool_length': self.pool_length,
'filterlen': self.filter_len,
'filternum': self.num_filters,
'hidden': self.num_hidden,
'input': self.input_shape,
'labels': self.labels_shape,
'task': self.task,
'input_mean': self.input_mean.tolist(),
'labels_mean': self.labels_mean.tolist(),
'input_std': self.input_std.tolist(),
'labels_std': self.labels_std.tolist(),
'valsize': self.val_size,
'targetname': self.targetname,
'dropout_rate': self.dropout_rate,
'l2': self.l2,
'input_norm_mode': self.input_norm_mode,
'labels_norm_mode': self.labels_norm_mode,
'batch_size': self.batch_size,
'latent': self.latent_dim
}
with open(self.fullfilepath + '/astroNN_model_parameter.json',
'w') as f:
json.dump(data, f, indent=4, sort_keys=True)
def test(self, input_data):
self.pre_testing_checklist_master()
input_data = np.atleast_2d(input_data)
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if input_data.shape[0] < self.batch_size:
self.batch_size = input_data.shape[0]
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
predictions = np.zeros((total_test_num, self.labels_shape, 1))
# Data Generator for prediction
prediction_generator = CVAEPredDataGenerator(self.batch_size).generate(
input_array[:data_gen_shape])
predictions[:data_gen_shape] = np.asarray(
self.keras_model.predict_generator(prediction_generator,
steps=input_array.shape[0] //
self.batch_size))
if remainder_shape != 0:
remainder_data = input_array[data_gen_shape:]
# assume its caused by mono images, so need to expand dim by 1
if len(input_array[0].shape) != len(self.input_shape):
remainder_data = np.expand_dims(remainder_data, axis=-1)
result = self.keras_model.predict(remainder_data)
predictions[data_gen_shape:] = result
if self.labels_normalizer is not None:
predictions[:, :, 0] = self.labels_normalizer.denormalize(
predictions[:, :, 0])
else:
predictions[:, :, 0] *= self.labels_std
predictions[:, :, 0] += self.labels_mean
return predictions
def test_encoder(self, input_data):
self.pre_testing_checklist_master()
# Prevent shallow copy issue
if self.input_normalizer is not None:
input_array = self.input_normalizer.normalize(input_data,
calc=False)
else:
# Prevent shallow copy issue
input_array = np.array(input_data)
input_array -= self.input_mean
input_array /= self.input_std
total_test_num = input_data.shape[0] # Number of testing data
# for number of training data smaller than batch_size
if input_data.shape[0] < self.batch_size:
self.batch_size = input_data.shape[0]
# Due to the nature of how generator works, no overlapped prediction
data_gen_shape = (total_test_num // self.batch_size) * self.batch_size
remainder_shape = total_test_num - data_gen_shape # Remainder from generator
encoding = np.zeros((total_test_num, self.latent_dim))
# Data Generator for prediction
prediction_generator = CVAEPredDataGenerator(self.batch_size).generate(
input_array[:data_gen_shape])
encoding[:data_gen_shape] = np.asarray(
self.keras_encoder.predict_generator(prediction_generator,
steps=input_array.shape[0] //
self.batch_size))
if remainder_shape != 0:
remainder_data = input_array[data_gen_shape:]
# assume its caused by mono images, so need to expand dim by 1
if len(input_array[0].shape) != len(self.input_shape):
remainder_data = np.expand_dims(remainder_data, axis=-1)
result = self.keras_encoder.predict(remainder_data)
encoding[data_gen_shape:] = result
return encoding
