def build_model(self, filters, filter_length, optimizer='rmsprop', loss='mse'):
input_ = Input(shape=(self.time_step, self.input_size))
conv_h1 = Conv1D(filters, filter_length, padding='causal', activation='relu')(input_)
conv_h2 = Conv1D(filters, filter_length, padding='causal', activation='relu')(conv_h1)
conv_h3 = Conv1D(filters, filter_length, padding='causal', activation='relu')(conv_h2)
conv_g3 = Conv1D(filters, filter_length, padding='causal', activation='relu')(conv_h3)
merge_h2_g3 = add([conv_h2, conv_g3])
conv_g2 = Conv1D(filters, filter_length, padding='causal', activation='relu')(merge_h2_g3)
merge_h1_g2 = add([conv_h1, conv_g2])
conv_g1 = Conv1D(filters, filter_length, padding='causal', activation='relu')(merge_h1_g2)
conv_g0 = Conv1D(self.output_size, filter_length, padding='causal', activation='relu')(conv_g1)
model = Model(input_, conv_g0)
model.compile(optimizer, loss)
model.summary()
return model
def atari_qnet(input_shape, num_actions, net_name, net_size):
net_name = net_name.lower()
# input state
state = Input(shape=input_shape)
# convolutional layers
conv1_32 = Conv2D(32, (8, 8), strides=(4, 4), activation='relu')
conv2_64 = Conv2D(64, (4, 4), strides=(2, 2), activation='relu')
conv3_64 = Conv2D(64, (3, 3), strides=(1, 1), activation='relu')
# if recurrent net then change input shape
if 'drqn' in net_name:
# recurrent net (drqn)
lambda_perm_state = lambda x: K.permute_dimensions(x, [0, 3, 1, 2])
perm_state = Lambda(lambda_perm_state)(state)
dist_state = Lambda(lambda x: K.stack([x], axis=4))(perm_state)
# extract features with `TimeDistributed` wrapped convolutional layers
dist_conv1 = TimeDistributed(conv1_32)(dist_state)
dist_conv2 = TimeDistributed(conv2_64)(dist_conv1)
dist_convf = TimeDistributed(conv3_64)(dist_conv2)
feature = TimeDistributed(Flatten())(dist_convf)
elif 'dqn' in net_name:
# fully connected net (dqn)
# extract features with convolutional layers
conv1 = conv1_32(state)
conv2 = conv2_64(conv1)
convf = conv3_64(conv2)
feature = Flatten()(convf)
# network type. Dense for dqn; LSTM or GRU for drqn
if 'lstm' in net_name:
net_type = LSTM
elif 'gru' in net_name:
net_type = GRU
else:
net_type = Dense
# dueling or regular dqn/drqn
if 'dueling' in net_name:
value1 = net_type(net_size, activation='relu')(feature)
adv1 = net_type(net_size, activation='relu')(feature)
value2 = Dense(1)(value1)
adv2 = Dense(num_actions)(adv1)
mean_adv2 = Lambda(lambda x: K.mean(x, axis=1))(adv2)
ones = K.ones([1, num_actions])
lambda_exp = lambda x: K.dot(K.expand_dims(x, axis=1), -ones)
exp_mean_adv2 = Lambda(lambda_exp)(mean_adv2)
sum_adv = add([exp_mean_adv2, adv2])
exp_value2 = Lambda(lambda x: K.dot(x, ones))(value2)
q_value = add([exp_value2, sum_adv])
else:
hid = net_type(net_size, activation='relu')(feature)
q_value = Dense(num_actions)(hid)
# build model
return Model(inputs=state, outputs=q_value)
def encoder_block(input_layer, filters):
x = separable_conv2d_batchnorm(input_layer, filters, strides=1, kernel=1)
x = separable_conv2d_batchnorm(x, filters, strides=1, kernel=3)
p1 = average_pool(x)
r1 = separable_conv2d_batchnorm(input_layer, filters, strides=2, kernel=3)
return layers.add([r1, p1])
def conv_block(input_tensor,
kernel_size,
filters,
stage,
block,
strides=(2, 2)):
"""conv_block is the block that has a conv layer at shortcut.
Arguments:
input_tensor: input tensor
kernel_size: default 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
strides: Tuple of integers.
Returns:
Output tensor for the block.
Note that from stage 3, the first conv layer at main path is with
strides=(2,2)
And the shortcut should have strides=(2,2) as well
"""
filters1, filters2, filters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Conv2D(filters1, (1, 1), strides=strides,
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(filters2,
kernel_size,
padding='same',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
shortcut = Conv2D(filters3, (1, 1),
strides=strides,
name=conv_name_base + '1')(input_tensor)
shortcut = BatchNormalization(axis=bn_axis,
name=bn_name_base + '1')(shortcut)
x = layers.add([x, shortcut])
x = Activation('relu')(x)
return x
def res_block(init, nb_filter, k=1):
x = Activation('relu')(init)
x = Conv2D(nb_filter * k, (3, 3), padding='same', use_bias=False)(x)
x = BN(x)
x = Activation('relu')(x)
x = Conv2D(nb_filter * k, (3, 3), padding='same', use_bias=False)(x)
x = BN(x)
x = Squeeze_excitation_layer(x)
x = layers.add([init, x])
return x
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2,
2)):
"""conv_block is the block that has a conv layer at shortcut.
Arguments:
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
strides: Tuple of integers.
Returns:
Output tensor for the block.
Note that from stage 3, the first conv layer at main path is with
strides=(2,2)
And the shortcut should have strides=(2,2) as well
"""
filters1, filters2, filters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Conv2D(
filters1, (1, 1), strides=strides,
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(
filters2, kernel_size, padding='same', name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
shortcut = Conv2D(
filters3, (1, 1), strides=strides,
name=conv_name_base + '1')(input_tensor)
shortcut = BatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)
x = layers.add([x, shortcut])
x = Activation('relu')(x)
return x
def dw_conv(init, nb_filter, k):
residual = Conv2D(nb_filter * k, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(init)
residual = BN(residual)
x = Conv2D(nb_filter * k, (3, 3), padding='same', use_bias=False)(init)
x = BN(x)
x = Activation('relu')(x)
x = Conv2D(nb_filter * k, (3, 3), padding='same', use_bias=False)(x)
x = BN(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = layers.add([x, residual])
return x
def identity_block(self, input, kernel, filters, stage, block):
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = input
x = Conv3D(filters[0], (1, 1, 1), name=conv_name_base + '2a')(x)
x = BatchNormalization(axis=4, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv3D(filters[1],
kernel,
padding='same',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=4, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv3D(filters[2], (1, 1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=4, name=bn_name_base + '2c')(x)
x = layers.add([x, input])
x = Activation('relu')(x)
return x
def identity_block(input_tensor, kernel_size, filters, stage, block):
"""The identity block is the block that has no conv layer at shortcut.
Arguments:
input_tensor: input tensor
kernel_size: default 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
Returns:
Output tensor for the block.
"""
filters1, filters2, filters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(filters2,
kernel_size,
padding='same',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
x = layers.add([x, input_tensor])
x = Activation('relu')(x)
return x
def conv_block(self,
input,
kernel,
filters,
stage,
block,
strides=(2, 2, 2)):
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = input
x = Conv3D(filters[0], (1, 1, 1),
strides=strides,
name=conv_name_base + '2a')(x)
x = BatchNormalization(axis=4, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv3D(filters[1],
kernel,
padding='same',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=4, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv3D(filters[2], (1, 1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=4, name=bn_name_base + '2c')(x)
shortcut = input
shortcut = Conv3D(filters[2], (1, 1, 1),
strides=strides,
name=conv_name_base + '1')(shortcut)
shortcut = BatchNormalization(axis=3,
name=bn_name_base + '1')(shortcut)
x = layers.add([x, shortcut])
x = Activation('relu')(x)
return x
def identity_block(input_tensor, kernel_size, filters, stage, block):
"""The identity block is the block that has no conv layer at shortcut.
Arguments:
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
Returns:
Output tensor for the block.
"""
filters1, filters2, filters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(
filters2, kernel_size, padding='same', name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
x = layers.add([x, input_tensor])
x = Activation('relu')(x)
return x
def Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format="channels_last"` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)`.
It should have exactly 3 input channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if K.backend() != 'tensorflow':
raise RuntimeError('The Xception model is only available with '
'the TensorFlow backend.')
if K.image_data_format() != 'channels_last':
logging.warning(
'The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False,
name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(128, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block2_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(256, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block3_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(728, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block4_pool')(x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(1024, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(1024, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block13_pool')(x)
x = layers.add([x, residual])
x = SeparableConv2D(1536, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(2048, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format="channels_last"` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)`.
It should have exactly 3 input channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if K.backend() != 'tensorflow':
raise RuntimeError('The Xception model is only available with '
'the TensorFlow backend.')
if K.image_data_format() != 'channels_last':
logging.warning(
'The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
x = Conv2D(
32, (3, 3), strides=(2, 2), use_bias=False,
name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(
128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(
128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(
128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block2_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(
256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(
256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(
256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block3_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(
728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block4_pool')(x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False,
name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False,
name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False,
name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(
1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(
1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block13_pool')(x)
x = layers.add([x, residual])
x = SeparableConv2D(
1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(
2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
"""
### Residual connection on a convolution layer
For more information about residual networks, see [Deep Residual Learning for Image Recognition](http://arxiv.org/abs/1512.03385).
"""
from tensorflow.contrib.keras.python.keras.layers import add, Input, Conv2D
from tensorflow.contrib.keras.python.keras.models import Model
# input tensor for a 3-channel 256x256 image
# x = Input(shape=(3, 256, 256)) will cause error
x = Input(shape=(256, 256, 3))
# due to keras.backend._config uses channels_last
# 3x3 conv with 3 output channels (same as input channels)
y = Conv2D(3, (3, 3), padding='same')(x)
# this returns x + y.
z = add(
[x, y]
) # take in same shape input tensor list, return same shape tensor, in order words, add([x,y]) is row-bind
model = Model(x, z)
model.summary()
def up_conv(init, skip, nb_filter, k):
x = Conv2DTranspose(nb_filter * k, (3, 3), padding='same',
strides=(2, 2))(init)
x = BN(x)
x = layers.add([x, skip])
return x
def create_model(embeddings, config=get_config(), sentence_length=100):
config['sentence_length'] = sentence_length
# sentence attention
attention_input = Input(shape=(config['sentence_length'], config['embedding_size'],), dtype='float32')
x = Permute((2, 1))(attention_input)
x = Reshape((config['embedding_size'], config['sentence_length']))(x)
x = Dense(config['sentence_length'], activation='softmax', bias=True)(x)
x = Lambda(lambda x: K.mean(x, axis=1), name='attention_vector_sentence')(x)
x = RepeatVector(config['embedding_size'])(x)
# x = Lambda(lambda x: x, name='attention_vector_sentence')(x)
attention_probabilities = Permute((2, 1))(x)
x = merge.multiply([attention_input, attention_probabilities], name='attention_mul')
x = Lambda(lambda x: K.sum(x, axis=1))(x)
sentence_attention = Model(attention_input, x, name='sentence_attention')
embedding_layer = Embedding(
embeddings.shape[0],
embeddings.shape[1],
input_length=config['sentence_length'],
trainable=False,
weights=[embeddings],
)
pos_mbedding_layer = Embedding(
15,
config['embedding_size'],
input_length=config['sentence_length'],
trainable=True,
# weights=[embeddings],
)
input = Input(shape=(config['sentence_length'],), dtype='int32', name='input_1')
x = embedding_layer(input)
x = SpatialDropout1D(config['embedding_dropout'])(x)
x1 = Attention()(x)
input2 = Input(shape=(config['sentence_length'],), dtype='int32', name='input_2')
x2 = pos_mbedding_layer(input2)
x2 = sentence_attention(x2)
# res
x_sum = Lambda(lambda x: K.mean(x, axis=1))(x)
x1 = add([x1, x_sum])
x = concatenate([x1, x2])
if config['dense_layer']:
x = Dense(config['dense_layer'], activation='relu')(x)
x = Dropout(config['dropout_prob'])(x)
output = Dense(1, activation='sigmoid',)(x)
model = Model(inputs=[input, input2], outputs=output)
return model, config
