def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
shape = input_node.shape.as_list()
if len(shape) != 3:
raise ValueError('Expect the input tensor to have '
'at least 3 dimensions for rnn models, '
'but got {shape}'.format(shape=input_node.shape))
feature_size = shape[-1]
output_node = input_node
bidirectional = self.bidirectional
if bidirectional is None:
bidirectional = hp.Boolean('bidirectional', default=True)
layer_type = self.layer_type or hp.Choice(
'layer_type', ['gru', 'lstm'], default='lstm')
num_layers = self.num_layers or hp.Choice('num_layers', [1, 2, 3],
default=2)
rnn_layers = {'gru': layers.GRU, 'lstm': layers.LSTM}
in_layer = rnn_layers[layer_type]
for i in range(num_layers):
return_sequences = True
if i == num_layers - 1:
return_sequences = self.return_sequences
if bidirectional:
output_node = layers.Bidirectional(
in_layer(feature_size,
return_sequences=return_sequences))(output_node)
else:
output_node = in_layer(
feature_size,
return_sequences=return_sequences)(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
output_node = Flatten().build(hp, output_node)
layer_stack = hp.Choice('layer_stack', ['dense-bn-act', 'dense-act'],
default='dense-bn-act')
dropout_rate = hp.Choice('dropout_rate', [0, 0.25, 0.5], default=0.5)
for i in range(hp.Choice('num_layers', [1, 2, 3], default=2)):
units = hp.Choice('units_{i}'.format(i=i),
[16, 32, 64, 128, 256, 512, 1024],
default=32)
if layer_stack == 'dense-bn-act':
output_node = tf.keras.layers.Dense(units)(output_node)
output_node = tf.keras.layers.BatchNormalization()(output_node)
output_node = tf.keras.layers.ReLU()(output_node)
output_node = tf.keras.layers.Dropout(dropout_rate)(
output_node)
elif layer_stack == 'dense-act':
output_node = tf.keras.layers.Dense(units)(output_node)
output_node = tf.keras.layers.ReLU()(output_node)
output_node = tf.keras.layers.Dropout(dropout_rate)(
output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
kernel_size = hp.Choice('kernel_size', [3, 5, 7], default=3)
for i in range(hp.Choice('num_blocks', [1, 2, 3], default=2)):
output_node = tf.keras.layers.Conv2D(
hp.Choice('filters_{i}_1'.format(i=i), [16, 32, 64],
default=32),
kernel_size,
padding=self._get_padding(kernel_size,
output_node))(output_node)
output_node = tf.keras.layers.Conv2D(
hp.Choice('filters_{i}_2'.format(i=i), [16, 32, 64],
default=32),
kernel_size,
padding=self._get_padding(kernel_size,
output_node))(output_node)
output_node = tf.keras.layers.MaxPool2D(
kernel_size - 1,
padding=self._get_padding(kernel_size - 1,
output_node))(output_node)
return output_node
def build(self, hp, inputs=None):
if self.identity:
return IdentityLayer(name=self.name)(inputs)
if self.num_classes:
expected = self.num_classes if self.num_classes > 2 else 1
if self.output_shape[-1] != expected:
raise ValueError('The data doesn\'t match the expected shape. '
'Expecting {} but got {}'.format(
expected, self.output_shape[-1]))
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
dropout_rate = self.dropout_rate or hp.Choice(
'dropout_rate', [0.0, 0.25, 0.5], default=0)
if dropout_rate > 0:
output_node = tf.keras.layers.Dropout(dropout_rate)(output_node)
output_node = block_module.Flatten().build(hp, output_node)
output_node = tf.keras.layers.Dense(self.output_shape[-1])(output_node)
if self.loss == 'binary_crossentropy':
output_node = Sigmoid(name=self.name)(output_node)
else:
output_node = tf.keras.layers.Softmax(name=self.name)(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
output_node = reduction.Flatten().build(hp, output_node)
num_layers = self.num_layers or hp.Choice('num_layers', [1, 2, 3],
default=2)
use_batchnorm = self.use_batchnorm
if use_batchnorm is None:
use_batchnorm = hp.Boolean('use_batchnorm', default=False)
if self.dropout_rate is not None:
dropout_rate = self.dropout_rate
else:
dropout_rate = hp.Choice('dropout_rate', [0.0, 0.25, 0.5],
default=0)
for i in range(num_layers):
units = hp.Choice('units_{i}'.format(i=i),
[16, 32, 64, 128, 256, 512, 1024],
default=32)
output_node = layers.Dense(units)(output_node)
if use_batchnorm:
output_node = layers.BatchNormalization()(output_node)
output_node = layers.ReLU()(output_node)
if dropout_rate > 0:
output_node = layers.Dropout(dropout_rate)(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
# No need to reduce.
if len(output_node.shape) <= 2:
return output_node
reduction_type = self.reduction_type or hp.Choice('reduction_type',
['flatten',
'global_max',
'global_avg'],
default='global_avg')
if reduction_type == 'flatten':
output_node = Flatten().build(hp, output_node)
elif reduction_type == 'global_max':
output_node = tf.math.reduce_max(output_node, axis=-2)
elif reduction_type == 'global_avg':
output_node = tf.math.reduce_mean(output_node, axis=-2)
elif reduction_type == 'global_min':
output_node = tf.math.reduce_min(output_node, axis=-2)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
if len(input_node.shape) > 2:
return tf.keras.layers.Flatten()(input_node)
return input_node
def build(self, hp, inputs=None):
if self.num_classes:
expected = self.num_classes if self.num_classes > 2 else 1
if self.output_shape[-1] != expected:
raise ValueError('The data doesn\'t match the expected shape. '
'Expecting {} but got {}'.format(
expected, self.output_shape[-1]))
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
# Reduce the tensor to a vector.
if len(output_node.shape) > 2:
output_node = reduction.SpatialReduction().build(hp, output_node)
if self.dropout_rate is not None:
dropout_rate = self.dropout_rate
else:
dropout_rate = hp.Choice('dropout_rate', [0.0, 0.25, 0.5],
default=0)
if dropout_rate > 0:
output_node = layers.Dropout(dropout_rate)(output_node)
output_node = layers.Dense(self.output_shape[-1])(output_node)
if self.loss == 'binary_crossentropy':
output_node = keras_layers.Sigmoid(name=self.name)(output_node)
else:
output_node = layers.Softmax(name=self.name)(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
output_node = hyper_block.Flatten().build(hp, output_node)
output_node = tf.keras.layers.Dense(self.output_shape[-1])(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
output_node = hyper_block.Flatten().build(hp, output_node)
output_node = tf.keras.layers.Dense(self.output_shape[-1])(output_node)
if self.binary:
output_node = tf.keras.activations.sigmoid(output_node)
else:
output_node = tf.keras.layers.Softmax()(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
kernel_size = self.kernel_size or hp.Choice('kernel_size', [3, 5, 7],
default=3)
num_blocks = self.num_blocks or hp.Choice('num_blocks', [1, 2, 3],
default=2)
num_layers = self.num_layers or hp.Choice('num_layers', [1, 2],
default=2)
separable = self.separable
if separable is None:
separable = hp.Boolean('separable', default=False)
if separable:
conv = utils.get_sep_conv(input_node.shape)
else:
conv = utils.get_conv(input_node.shape)
max_pooling = self.max_pooling
if max_pooling is None:
max_pooling = hp.Boolean('max_pooling', default=True)
pool = utils.get_max_pooling(input_node.shape)
if self.dropout_rate is not None:
dropout_rate = self.dropout_rate
else:
dropout_rate = hp.Choice('dropout_rate', [0.0, 0.25, 0.5],
default=0)
for i in range(num_blocks):
for j in range(num_layers):
output_node = conv(hp.Choice('filters_{i}_{j}'.format(i=i,
j=j),
[16, 32, 64, 128, 256, 512],
default=32),
kernel_size,
padding=self._get_padding(
kernel_size, output_node),
activation='relu')(output_node)
if max_pooling:
output_node = pool(kernel_size - 1,
padding=self._get_padding(
kernel_size - 1,
output_node))(output_node)
if dropout_rate > 0:
output_node = layers.Dropout(dropout_rate)(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
block_type = hp.Choice('block_type', ['resnet', 'xception', 'vanilla'],
default='resnet')
if block_type == 'resnet':
output_node = ResNetBlock().build(hp, output_node)
elif block_type == 'xception':
output_node = XceptionBlock().build(hp, output_node)
elif block_type == 'vanilla':
output_node = ConvBlock().build(hp, output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
shape = input_node.shape.as_list()
if len(shape) < 3:
raise ValueError("Expect the input tensor to have "
"at least 3 dimensions for rnn models, "
"but got {shape}".format(shape=input_node.shape))
# Flatten feature_list to a single dimension.
# Final shape 3-D (num_sample , time_steps , features)
feature_size = np.prod(shape[2:])
input_node = tf.reshape(input_node, [-1, shape[1], feature_size])
output_node = input_node
in_layer = const.Constant.RNN_LAYERS[hp.Choice('rnn_type',
['gru', 'lstm'],
default='lstm')]
choice_of_layers = hp.Choice('num_layers', [1, 2, 3], default=2)
bidirectional = self.bidirectional
if bidirectional is None:
bidirectional = hp.Choice('bidirectional', [True, False],
default=True)
return_sequences = self.return_sequences
if return_sequences is None:
return_sequences = hp.Choice('return_sequences', [True, False],
default=True)
for i in range(choice_of_layers):
temp_return_sequences = True
if i == choice_of_layers - 1:
temp_return_sequences = return_sequences
if bidirectional:
output_node = tf.keras.layers.Bidirectional(
in_layer(
feature_size,
return_sequences=temp_return_sequences))(output_node)
else:
output_node = in_layer(feature_size,
return_sequences=return_sequences)
return output_node
def build(self, hp, inputs=None):
if self.output_dim and self.output_shape[-1] != self.output_dim:
raise ValueError('The data doesn\'t match the output_dim. '
'Expecting {} but got {}'.format(
self.output_dim, self.output_shape[-1]))
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
dropout_rate = self.dropout_rate or hp.Choice(
'dropout_rate', [0.0, 0.25, 0.5], default=0)
if dropout_rate > 0:
output_node = tf.keras.layers.Dropout(dropout_rate)(output_node)
output_node = block.Flatten().build(hp, output_node)
output_node = tf.keras.layers.Dense(self.output_shape[-1])(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
channel_axis = 1 \
if tf.keras.backend.image_data_format() == 'channels_first' else -1
# Parameters
# [general]
kernel_size = hp.Range("kernel_size", 3, 5)
initial_strides = (2, 2)
activation = hp.Choice("activation", ["relu", "selu"])
# [Entry Flow]
conv2d_filters = hp.Choice("conv2d_num_filters", [32, 64, 128])
sep_filters = hp.Range("sep_num_filters", 128, 768)
# [Middle Flow]
residual_blocks = hp.Range("num_residual_blocks", 2, 8)
# [Exit Flow]
# Model
# Initial conv2d
dims = conv2d_filters
output_node = self._conv(dims,
kernel_size=(kernel_size, kernel_size),
activation=activation,
strides=initial_strides)(output_node)
# Separable convs
dims = sep_filters
for _ in range(residual_blocks):
output_node = self._residual(
dims,
activation=activation,
max_pooling=False,
channel_axis=channel_axis)(output_node)
# Exit
dims *= 2
output_node = self._residual(dims,
activation=activation,
max_pooling=True,
channel_axis=channel_axis)(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
kernel_size = self.kernel_size or hp.Choice('kernel_size',
[3, 5, 7],
default=3)
num_blocks = self.num_blocks or hp.Choice('num_blocks',
[1, 2, 3],
default=2)
separable = self.separable
if separable is None:
separable = hp.Choice('separable', [True, False], default=False)
if separable:
conv = utils.get_sep_conv(input_node.shape)
else:
conv = utils.get_conv(input_node.shape)
pool = utils.get_max_pooling(input_node.shape)
for i in range(num_blocks):
output_node = conv(
hp.Choice('filters_{i}_1'.format(i=i),
[16, 32, 64],
default=32),
kernel_size,
padding=self._get_padding(kernel_size, output_node),
activation='relu')(output_node)
output_node = conv(
hp.Choice('filters_{i}_2'.format(i=i),
[16, 32, 64],
default=32),
kernel_size,
padding=self._get_padding(kernel_size, output_node),
activation='relu')(output_node)
output_node = pool(
kernel_size - 1,
padding=self._get_padding(kernel_size - 1, output_node))(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
separable = self.separable
if separable is None:
separable = hp.Choice('separable', [True, False], default=False)
if separable:
conv = utils.get_sep_conv(input_node.shape)
else:
conv = utils.get_conv(input_node.shape)
pool = utils.get_max_pooling(input_node.shape)
dropout = utils.get_dropout(input_node.shape)
kernel_size = hp.Choice('kernel_size', [3, 5, 7], default=3)
dropout_rate = hp.Choice('dropout_rate', [0, 0.25, 0.5], default=0.5)
for i in range(hp.Choice('num_blocks', [1, 2, 3], default=2)):
if dropout_rate > 0:
output_node = dropout(dropout_rate)(output_node)
output_node = conv(hp.Choice('filters_{i}_1'.format(i=i),
[16, 32, 64],
default=32),
kernel_size,
padding=self._get_padding(
kernel_size, output_node))(output_node)
output_node = conv(hp.Choice('filters_{i}_2'.format(i=i),
[16, 32, 64],
default=32),
kernel_size,
padding=self._get_padding(
kernel_size, output_node))(output_node)
output_node = pool(kernel_size - 1,
padding=self._get_padding(
kernel_size - 1, output_node))(output_node)
return output_node
def build(self, hp, inputs=None):
if self.num_classes and self.output_shape[-1] != self.num_classes:
raise ValueError('The data doesn\'t match the num_classes. '
'Expecting {} but got {}'.format(
self.num_classes, self.output_shape[-1]))
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
dropout_rate = self.dropout_rate or hp.Choice(
'dropout_rate', [0.0, 0.25, 0.5], default=0)
if dropout_rate > 0:
output_node = tf.keras.layers.Dropout(dropout_rate)(output_node)
output_node = block.Flatten().build(hp, output_node)
output_node = tf.keras.layers.Dense(self.output_shape[-1])(output_node)
if self.loss == 'binary_crossentropy':
output_node = tf.keras.activations.sigmoid(output_node)
else:
output_node = tf.keras.layers.Softmax()(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
# No need to reduce.
if len(output_node.shape) <= 2:
return output_node
reduction_type = self.reduction_type or hp.Choice(
'reduction_type', ['flatten', 'global_max', 'global_avg'],
default='global_avg')
if reduction_type == 'flatten':
output_node = Flatten().build(hp, output_node)
elif reduction_type == 'global_max':
output_node = utils.get_global_max_pooling(
output_node.shape)()(output_node)
elif reduction_type == 'global_avg':
output_node = utils.get_global_average_pooling(
output_node.shape)()(output_node)
return output_node
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
output_node = Flatten().build(hp, output_node)
num_layers = self.num_layers or hp.Choice('num_layers', [1, 2, 3],
default=2)
use_bn = self.use_batchnorm or hp.Choice(
'use_batchnorm', [True, False], default=False)
dropout_rate = self.dropout_rate or hp.Choice(
'dropout_rate', [0.0, 0.25, 0.5], default=0)
for i in range(num_layers):
units = hp.Choice('units_{i}'.format(i=i),
[16, 32, 64, 128, 256, 512, 1024],
default=32)
output_node = tf.keras.layers.Dense(units)(output_node)
if use_bn:
output_node = tf.keras.layers.BatchNormalization()(output_node)
output_node = tf.keras.layers.ReLU()(output_node)
output_node = tf.keras.layers.Dropout(dropout_rate)(output_node)
return output_node
