def block2(x,
filters,
kernel_size=3,
stride=1,
conv_shortcut=False,
name=None):
"""A residual block.
# Arguments
x: input tensor.
filters: integer, filters of the bottleneck layer.
kernel_size: default 3, kernel size of the bottleneck layer.
stride: default 1, stride of the first layer.
conv_shortcut: default False, use convolution shortcut if True,
otherwise identity shortcut.
name: string, block label.
# Returns
Output tensor for the residual block.
"""
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
preact = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_preact_bn')(x)
preact = layers.Activation('relu', name=name + '_preact_relu')(preact)
if conv_shortcut is True:
shortcut = Conv2D_Initialize(4 * filters,
1,
strides=stride,
name=name + '_0_conv')(preact)
else:
shortcut = layers.MaxPooling2D(1,
strides=stride)(x) if stride > 1 else x
x = Conv2D_Initialize(filters,
1,
strides=1,
use_bias=False,
name=name + '_1_conv')(preact)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_1_bn')(x)
x = layers.Activation('relu', name=name + '_1_relu')(x)
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name=name + '_2_pad')(x)
x = Conv2D_Initialize(filters,
kernel_size,
strides=stride,
use_bias=False,
name=name + '_2_conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_2_bn')(x)
x = layers.Activation('relu', name=name + '_2_relu')(x)
x = Conv2D_Initialize(4 * filters, 1, name=name + '_3_conv')(x)
x = layers.Add(name=name + '_out')([shortcut, x])
return x
def block1(x, filters, kernel_size=3, stride=1, conv_shortcut=True, name=None):
"""A residual block.
# Arguments
x: input tensor.
filters: integer, filters of the bottleneck layer.
kernel_size: default 3, kernel size of the bottleneck layer.
stride: default 1, stride of the first layer.
conv_shortcut: default True, use convolution shortcut if True,
otherwise identity shortcut.
name: string, block label.
# Returns
Output tensor for the residual block.
"""
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
if conv_shortcut is True:
shortcut = Conv2D_Initialize(4 * filters,
1,
strides=stride,
name=name + '_0_conv')(x)
shortcut = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_0_bn')(shortcut)
else:
shortcut = x
x = Conv2D_Initialize(filters, 1, strides=stride, name=name + '_1_conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_1_bn')(x)
x = layers.Activation('relu', name=name + '_1_relu')(x)
x = Conv2D_Initialize(filters,
kernel_size,
padding='SAME',
name=name + '_2_conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_2_bn')(x)
x = layers.Activation('relu', name=name + '_2_relu')(x)
x = Conv2D_Initialize(4 * filters, 1, name=name + '_3_conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_3_bn')(x)
x = layers.Add(name=name + '_add')([shortcut, x])
x = layers.Activation('relu', name=name + '_out')(x)
return x
def _conv_block(inputs, filters, alpha, kernel=(3, 3), strides=(1, 1)):
"""Adds an initial convolution layer (with batch normalization and relu6).
# Arguments
inputs: Input tensor of shape `(rows, cols, 3)`
(with `channels_last` data format) or
(3, rows, cols) (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(224, 224, 3)` would be one valid value.
filters: Integer, the dimensionality of the output space
(i.e. the number of output filters in the convolution).
alpha: controls the width of the network.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
kernel: An integer or tuple/list of 2 integers, specifying the
width and height of the 2D convolution window.
Can be a single integer to specify the same value for
all spatial dimensions.
strides: An integer or tuple/list of 2 integers,
specifying the strides of the convolution
along the width and height.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
# Input shape
4D tensor with shape:
`(samples, channels, rows, cols)` if data_format='channels_first'
or 4D tensor with shape:
`(samples, rows, cols, channels)` if data_format='channels_last'.
# Output shape
4D tensor with shape:
`(samples, filters, new_rows, new_cols)`
if data_format='channels_first'
or 4D tensor with shape:
`(samples, new_rows, new_cols, filters)`
if data_format='channels_last'.
`rows` and `cols` values might have changed due to stride.
# Returns
Output tensor of block.
"""
channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1
filters = int(filters * alpha)
x = layers.ZeroPadding2D(padding=((0, 1), (0, 1)), name='conv1_pad')(inputs)
x = Conv2D_Initialize(filters, kernel,
padding='valid',
use_bias=False,
strides=strides,
name='conv1')(x)
x = layers.BatchNormalization(axis=channel_axis, name='conv1_bn')(x)
return layers.ReLU(6., name='conv1_relu')(x)
def conv2d_bn(x,
filters,
kernel_size,
strides=1,
padding='same',
activation='relu',
use_bias=False,
name=None):
"""Utility function to apply conv + BN.
# Arguments
x: input tensor.
filters: filters in `Conv2D`.
kernel_size: kernel size as in `Conv2D`.
strides: strides in `Conv2D`.
padding: padding mode in `Conv2D`.
activation: activation in `Conv2D`.
use_bias: whether to use a bias in `Conv2D`.
name: name of the ops; will become `name + '_ac'` for the activation
and `name + '_bn'` for the batch norm layer.
# Returns
Output tensor after applying `Conv2D` and `BatchNormalization`.
"""
x = Conv2D_Initialize(filters,
kernel_size,
strides=strides,
padding=padding,
use_bias=use_bias,
name=name)(x)
if not use_bias:
bn_axis = 1 if backend.image_data_format() == 'channels_first' else 3
bn_name = None if name is None else name + '_bn'
x = layers.BatchNormalization(axis=bn_axis, scale=False,
name=bn_name)(x)
if activation is not None:
ac_name = None if name is None else name + '_ac'
x = layers.Activation(activation, name=ac_name)(x)
return x
def VGG16(input_shape,
include_top=True,
weights='imagenet',
pooling=None,
classes=1000,
final_activation='sigmoid'):
input = Input(input_shape)
# Block 1
x = Conv2D_Initialize(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1',
bias_initializer='zero')(input)
x = Conv2D_Initialize(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D_Initialize(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D_Initialize(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = Dense_Initialize(4096, activation='relu', name='fc1')(x)
x = Dense_Initialize(4096, activation='relu', name='fc2')(x)
x = Dense_Initialize(classes,
activation=final_activation,
name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Create model.
weights_path = None
if weights == 'imagenet':
if include_top:
weights_path = keras_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='64373286793e3c8b2b4e3219cbf3544b')
else:
weights_path = keras_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='6d6bbae143d832006294945121d1f1fc')
model = Model(input, x, name='vgg16')
if weights_path and weights:
model.load_weights(weights_path, by_name=True, skip_mismatch=True)
return model
def VGG19(input_shape, include_top=True,
weights='imagenet',
pooling=None,
classes=1000,
final_activation = 'sigmoid',
**kwargs):
input = Input(input_shape)
# Block 1
x = Conv2D_Initialize(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1', bias_initializer='zero')(input)
x = Conv2D_Initialize(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D_Initialize(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D_Initialize(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = Conv2D_Initialize(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = Conv2D_Initialize(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = Dense_Initialize(4096, activation='relu', name='fc1')(x)
x = Dense_Initialize(4096, activation='relu', name='fc2')(x)
x = Dense_Initialize(classes, activation=final_activation, name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Load weights.
weights_path = None
if weights == 'imagenet':
if include_top:
weights_path = keras_utils.get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='cbe5617147190e668d6c5d5026f83318')
else:
weights_path = keras_utils.get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='253f8cb515780f3b799900260a226db6')
model = Model(input, x, name = 'vgg19')
if weights_path and weights:
model.load_weights(weights_path, by_name=True, skip_mismatch=True)
return model
def base_middle_siamese(input_shape, final_activation='sigmoid', **kwargs):
input = Input(shape=input_shape)
x = Conv2D_Initialize(64, (10, 10),
activation='relu',
bias_initializer='zero')(input)
x = MaxPooling2D()(x)
x = Conv2D_Initialize(128, (7, 7), activation='relu')(x)
x = MaxPooling2D()(x)
x = Conv2D_Initialize(128, (4, 4), activation='relu')(x)
x = MaxPooling2D()(x)
x = Conv2D_Initialize(256, (4, 4), activation='relu')(x)
x = Flatten()(x)
out = Dense_Initialize(4096, activation=final_activation)(x)
model = Model(input, out, name='siamese')
return model
# def get_siamese_model(input_shape):
# """
# Model architecture based on the one provided in: http://www.cs.utoronto.ca/~gkoch/files/msc-thesis.pdf
# """
#
# # Define the tensors for the two input images
# left_input = Input(input_shape)
# right_input = Input(input_shape)
#
# # Convolutional Neural Network
# model = Sequential()
# model.add(Conv2D(64, (10, 10), activation='relu', input_shape=input_shape,
# kernel_initializer=initialize_weights,
# kernel_regularizer=l2(2e-4)))
# model.add(MaxPooling2D())
# model.add(Conv2D(128, (7, 7), activation='relu',
# kernel_initializer=initialize_weights,
# bias_initializer=initialize_bias,
# kernel_regularizer=l2(2e-4)))
# model.add(MaxPooling2D())
# model.add(Conv2D(128, (4, 4), activation='relu',
# kernel_initializer=initialize_weights,
# bias_initializer=initialize_bias,
# kernel_regularizer=l2(2e-4)))
# model.add(MaxPooling2D())
# model.add(Conv2D(256, (4, 4), activation='relu',
# kernel_initializer=initialize_weights,
# bias_initializer=initialize_bias,
# kernel_regularizer=l2(2e-4)))
# model.add(Flatten())
# model.add(Dense(4096, activation='sigmoid', kernel_regularizer=l2(1e-3),
# kernel_initializer=initialize_weights,
# bias_initializer=initialize_bias))
#
# # Generate the encodings (feature vectors) for the two images
# encoded_l = model(left_input)
# encoded_r = model(right_input)
#
# # Add a customized layer to compute the absolute difference between the encodings
# L1_layer = Lambda(lambda tensors: K.abs(tensors[0] - tensors[1]))
# L1_distance = L1_layer([encoded_l, encoded_r])
# print(L1_distance.shape)
# # Add a dense layer with a sigmoid unit to generate the similarity score
# prediction = Dense(1, activation='sigmoid',
# bias_initializer=initialize_bias)(L1_distance)
#
# # Connect the inputs with the outputs
# siamese_net = Model(inputs=[left_input, right_input], outputs=prediction)
#
# # return the model
# return siamese_net
def ResNet(stack_fn,
preact,
use_bias,
model_name='resnet',
include_top=True,
weights='imagenet',
input_shape=None,
pooling=None,
classes=1000,
final_activation='sigmoid',
**kwargs):
inputs = Input(input_shape)
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)),
name='conv1_pad')(inputs)
x = Conv2D_Initialize(64,
7,
strides=2,
use_bias=use_bias,
name='conv1_conv')(x)
if preact is False:
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name='conv1_bn')(x)
x = layers.Activation('relu', name='conv1_relu')(x)
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)
x = stack_fn(x)
if preact is True:
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name='post_bn')(x)
x = layers.Activation('relu', name='post_relu')(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense_Initialize(classes,
activation=final_activation,
name='probs')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
# Create model.
model = models.Model(inputs, x, name=model_name)
# Load weights.
if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES):
if include_top:
file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5'
file_hash = WEIGHTS_HASHES[model_name][0]
else:
file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5'
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = keras_utils.get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path, by_name=True, skip_mismatch=True)
elif weights is not None:
model.load_weights(weights, by_name=True, skip_mismatch=True)
return model
def block3(x,
filters,
kernel_size=3,
stride=1,
groups=32,
conv_shortcut=True,
name=None):
"""A residual block.
# Arguments
x: input tensor.
filters: integer, filters of the bottleneck layer.
kernel_size: default 3, kernel size of the bottleneck layer.
stride: default 1, stride of the first layer.
groups: default 32, group size for grouped convolution.
conv_shortcut: default True, use convolution shortcut if True,
otherwise identity shortcut.
name: string, block label.
# Returns
Output tensor for the residual block.
"""
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
if conv_shortcut is True:
shortcut = Conv2D_Initialize((64 // groups) * filters,
1,
strides=stride,
use_bias=False,
name=name + '_0_conv')(x)
shortcut = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_0_bn')(shortcut)
else:
shortcut = x
x = Conv2D_Initialize(filters, 1, use_bias=False, name=name + '_1_conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_1_bn')(x)
x = layers.Activation('relu', name=name + '_1_relu')(x)
c = filters // groups
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name=name + '_2_pad')(x)
x = layers.DepthwiseConv2D(kernel_size,
strides=stride,
depth_multiplier=c,
use_bias=False,
name=name + '_2_conv')(x)
x_shape = backend.int_shape(x)[1:-1]
x = layers.Reshape(x_shape + (groups, c, c))(x)
output_shape = x_shape + (groups,
c) if backend.backend() == 'theano' else None
x = layers.Lambda(lambda x: sum([x[:, :, :, :, i] for i in range(c)]),
output_shape=output_shape,
name=name + '_2_reduce')(x)
x = layers.Reshape(x_shape + (filters, ))(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_2_bn')(x)
x = layers.Activation('relu', name=name + '_2_relu')(x)
x = Conv2D_Initialize((64 // groups) * filters,
1,
use_bias=False,
name=name + '_3_conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_3_bn')(x)
x = layers.Add(name=name + '_add')([shortcut, x])
x = layers.Activation('relu', name=name + '_out')(x)
return x
def _depthwise_conv_block(inputs, pointwise_conv_filters, alpha,
depth_multiplier=1, strides=(1, 1), block_id=1):
"""Adds a depthwise convolution block.
A depthwise convolution block consists of a depthwise conv,
batch normalization, relu6, pointwise convolution,
batch normalization and relu6 activation.
# Arguments
inputs: Input tensor of shape `(rows, cols, channels)`
(with `channels_last` data format) or
(channels, rows, cols) (with `channels_first` data format).
pointwise_conv_filters: Integer, the dimensionality of the output space
(i.e. the number of output filters in the pointwise convolution).
alpha: controls the width of the network.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
depth_multiplier: The number of depthwise convolution output channels
for each input channel.
The total number of depthwise convolution output
channels will be equal to `filters_in * depth_multiplier`.
strides: An integer or tuple/list of 2 integers,
specifying the strides of the convolution
along the width and height.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
block_id: Integer, a unique identification designating
the block number.
# Input shape
4D tensor with shape:
`(batch, channels, rows, cols)` if data_format='channels_first'
or 4D tensor with shape:
`(batch, rows, cols, channels)` if data_format='channels_last'.
# Output shape
4D tensor with shape:
`(batch, filters, new_rows, new_cols)`
if data_format='channels_first'
or 4D tensor with shape:
`(batch, new_rows, new_cols, filters)`
if data_format='channels_last'.
`rows` and `cols` values might have changed due to stride.
# Returns
Output tensor of block.
"""
channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1
pointwise_conv_filters = int(pointwise_conv_filters * alpha)
if strides == (1, 1):
x = inputs
else:
x = layers.ZeroPadding2D(((0, 1), (0, 1)),
name='conv_pad_%d' % block_id)(inputs)
x = layers.DepthwiseConv2D((3, 3),
padding='same' if strides == (1, 1) else 'valid',
depth_multiplier=depth_multiplier,
strides=strides,
use_bias=False,
name='conv_dw_%d' % block_id)(x)
x = layers.BatchNormalization(
axis=channel_axis, name='conv_dw_%d_bn' % block_id)(x)
x = layers.ReLU(6., name='conv_dw_%d_relu' % block_id)(x)
x = Conv2D_Initialize(pointwise_conv_filters, (1, 1),
padding='same',
use_bias=False,
strides=(1, 1),
name='conv_pw_%d' % block_id)(x)
x = layers.BatchNormalization(axis=channel_axis,
name='conv_pw_%d_bn' % block_id)(x)
return layers.ReLU(6., name='conv_pw_%d_relu' % block_id)(x)
def MobileNet(input_shape=None,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights='imagenet',
pooling=None,
classes=1000,
final_activation = 'sigmoid',
**kwargs):
if backend.image_data_format() == 'channels_last':
row_axis, col_axis = (0, 1)
else:
row_axis, col_axis = (1, 2)
rows = input_shape[row_axis]
cols = input_shape[col_axis]
if weights == 'imagenet':
if depth_multiplier != 1:
raise ValueError('If imagenet weights are being loaded, '
'depth multiplier must be 1')
if alpha not in [0.25, 0.50, 0.75, 1.0]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of'
'`0.25`, `0.50`, `0.75` or `1.0` only.')
if rows != cols or rows not in [128, 160, 192, 224]:
rows = 224
warnings.warn('`input_shape` is undefined or non-square, '
'or `rows` is not in [128, 160, 192, 224]. '
'Weights for input shape (224, 224) will be'
' loaded as the default.')
img_input = Input(input_shape)
x = _conv_block(img_input, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier,
strides=(2, 2), block_id=2)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier,
strides=(2, 2), block_id=4)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier,
strides=(2, 2), block_id=6)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier,
strides=(2, 2), block_id=12)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)
if include_top:
if backend.image_data_format() == 'channels_first':
shape = (int(1024 * alpha), 1, 1)
else:
shape = (1, 1, int(1024 * alpha))
x = layers.GlobalAveragePooling2D()(x)
x = layers.Reshape(shape, name='reshape_1')(x)
x = layers.Dropout(dropout, name='dropout')(x)
x = Conv2D_Initialize(classes, (1, 1),
padding='same',
name='conv_preds')(x)
x = layers.Reshape((classes,), name='reshape_2')(x)
x = layers.Activation(final_activation, name='act_softmax')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Create model.
model = models.Model(img_input, x, name='mobilenet_%0.2f_%s' % (alpha, rows))
# Load weights.
if weights == 'imagenet':
if alpha == 1.0:
alpha_text = '1_0'
elif alpha == 0.75:
alpha_text = '7_5'
elif alpha == 0.50:
alpha_text = '5_0'
else:
alpha_text = '2_5'
if include_top:
model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = keras_utils.get_file(model_name,
weight_path,
cache_subdir='models')
else:
model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = keras_utils.get_file(model_name,
weight_path,
cache_subdir='models')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model