def __init__(self,
weights='pascal_voc',
input_tensor=None,
input_shape=(512, 512, 3),
classes=21,
backbone='mobilenetv2',
OS=16,
alpha=1.,
activation=None,
**kwargs):
super().__init__(**kwargs)
if backbone == 'mobilenetv2':
self.backbone = MobileNetV2(alpha=alpha)
self.aspp = ASPP()
self.activation = activation
if input_tensor is None:
self.img_input = Input(shape=input_shape)
else:
self.img_input = input_tensor
if input_tensor is not None:
self.inputs = get_source_inputs(input_tensor)
else:
self.inputs = self.img_input
if (weights == 'pascal_voc'
and classes == 21) or (weights == 'cityscapes'
and classes == 19):
self.last_layer_name = 'logits_semantic'
else:
self.last_layer_name = 'custom_logits_semantic'
def __init__(self, include_top=True, input_tensor=None, input_shape=None, pooling=None, classes=8631):
super(ResNet50Model, self).__init__()
self.include_top = include_top
input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=32, data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = ResNet50Component(include_top=include_top)(img_input)
# x = AveragePooling2D((7, 7), name='avg_pool')(x)
x = Flatten()(x)
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
super(ResNet50Model, self).__init__(inputs, x, name='vggface_resnet50')
def model_mobilenet(input_tensor=None,
input_shape=None,
classes=1000,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
pooling=None,
weights=None,
data_format="channels_last"):
input_shape = deduce_input_shape(input_shape,
require_flatten=include_top,
weights=weights,
data_format=data_format)
if 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 input_tensor is not None:
if not backend.is_keras_tensor(input_tensor):
raise ValueError("input_tensor must be a Keras layer tensor.")
img_input = input_tensor
else:
img_input = layers.Input(shape=input_shape)
# construct the convolutional network
net = cnn_mobilenet(img_input,
alpha=alpha,
depth_multiplier=depth_multiplier,
data_format=data_format)
if include_top:
# add the classification network
net = top_block(net,
classes=classes,
alpha=alpha,
dropout=dropout,
data_format=data_format)
else:
# add global pooling if required
net = pool_block(net, pooling, data_format)
if input_tensor is not None:
inputs = utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model_name = 'mobilenet_%0.2f_%s' % (alpha, rows)
model = models.Model(inputs, net, name=model_name)
if weights == 'imagenet':
weight_path = get_weights_path(alpha, rows, include_top)
model.load_weights(weight_path)
elif weights is not None:
model.load_weights(weights)
return model
def model_resnet50(input_tensor=None,
input_shape=None,
classes=1000,
include_top=True,
pooling=None,
weights=None,
data_format="channels_last"):
ch_axis = 3 if data_format == 'channels_last' else 1
input_shape = deduce_input_shape(input_shape,
require_flatten=include_top,
weights=weights,
data_format=data_format)
if input_tensor is not None:
if not backend.is_keras_tensor(input_tensor):
raise ValueError("input_tensor must be a Keras layer tensor.")
img_input = input_tensor
else:
img_input = layers.Input(shape=input_shape)
net = cnn_resnet50(img_input, ch_axis=ch_axis)
if include_top:
net = top_resnet(net, classes)
else:
# add global pooling if required
net = pool_resnet(net, pooling, data_format)
if input_tensor is not None:
inputs = utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, net, name='resnet50')
if weights == 'imagenet':
resource = KERAS_TEAM['RESNET50']
resource = resource['WITH_TOP'] if include_top else resource['NO_TOP']
origin = resource.uri
resource_path = utils.get_file(resource.name,
origin,
cache_subdir="models",
file_hash=resource.file_hash)
model.load_weights(resource_path)
pass
elif weights is not None:
model.load_weights(weights)
return model
def model_vgg16(input_tensor=None,
input_shape=None,
classes=1000,
include_top=True,
pooling=None,
weights=None):
# provide a way to compute the default input shape
input_shape = deduce_input_shape(input_shape,
require_flatten=include_top,
weights=weights)
if input_tensor is not None:
if not backend.is_keras_tensor(input_tensor):
raise ValueError("input_tensor must be a Keras layer tensor.")
img_input = input_tensor
else:
img_input = layers.Input(shape=input_shape)
net = cnn_vgg16(img_input)
if include_top:
# add the top classification network
net = top_vgg(net, classes)
else:
# add global pooling if required
net = pool_cnn(net, pooling)
if input_tensor is not None:
inputs = utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, net, name='vgg16')
if weights == 'imagenet':
resource = FCHOLLET['VGG16']
resource = resource['WITH_TOP'] if include_top else resource['NO_TOP']
origin = resource.uri
resource_path = utils.get_file(resource.name,
origin,
cache_subdir="models",
file_hash=resource.file_hash)
model.load_weights(resource_path)
elif weights is not None:
model.load_weights(weights)
return model
def featurenet_3D_backbone(input_tensor=None,
input_shape=None,
n_filters=32,
**kwargs):
"""Construct the deepcell backbone with five convolutional units
Args:
input_tensor (tensor): Input tensor to specify input size
n_filters (int): Number of filters for convolutional layers
Returns:
tuple: List of backbone layers, list of backbone names
"""
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Build out backbone
c1 = featurenet_3D_block(img_input, n_filters) # 1/2 64x64
c2 = featurenet_3D_block(c1, n_filters) # 1/4 32x32
c3 = featurenet_3D_block(c2, n_filters) # 1/8 16x16
c4 = featurenet_3D_block(c3, n_filters) # 1/16 8x8
c5 = featurenet_3D_block(c4, n_filters) # 1/32 4x4
backbone_features = [c1, c2, c3, c4, c5]
backbone_names = ['C1', 'C2', 'C3', 'C4', 'C5']
output_dict = {}
for name, feature in zip(backbone_names, backbone_features):
output_dict[name] = feature
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs=inputs, outputs=backbone_features)
return model, output_dict
def ResNet50(input_tensor=None, input_shape=None):
model_name = 'resnet50'
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.Conv2D(64, 7, strides=2, use_bias=False,
name='conv1_conv')(img_input)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name='conv1_bn')(x)
p0 = layers.Activation('relu', name='conv1_relu')(x)
x = layers.MaxPooling2D(3, strides=2, padding='SAME',
name='pool1_pool')(p0)
p1 = stack1(x, 64, 3, stride1=1, name='conv2')
p2 = stack1(p1, 128, 4, stride1=2, name='conv3')
p3 = stack1(p2, 256, 6, stride1=1, dilation=2, name='conv4')
p4 = stack1(p3, 512, 3, stride1=1, name='conv5')
x = p4
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name=model_name)
return model
def InceptionV2(include_top=False,
weights=None,
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the InceptionV2 architecture.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: must be None.
input_tensor: Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: input tensor shape, which is used to create an
input tensor if `input_tensor` is not specified.
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 block.
- `avg` means that global average pooling will be applied
to the output of the last convolutional block, 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.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights is not None:
raise ValueError('weights is not currently supported')
if input_tensor is None:
if input_shape is None:
raise ValueError('neither input_tensor nor input_shape is given')
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = conv2d_bn(img_input, 64, (7, 7), strides=(2, 2)) # 1a: 112x112x64
x = layers.MaxPooling2D(pool_size=(3, 3), strides=(2, 2),
padding='same')(x) # 2a: 56x56x64
x = conv2d_bn(x, 64, (1, 1)) # 2b: 56x56x64
x = conv2d_bn(x, 192, (3, 3)) # 2c: 56x56x192
x = layers.MaxPooling2D(pool_size=(3, 3), strides=(2, 2),
padding='same')(x) # 3a: 28x28x192
x = inception(x, (64, (64, 64), (64, 96), 32)) # 3b: 28x28x256
x = inception(x, (64, (64, 96), (64, 96), 64)) # 3c: 28x28x320
x = inception_s2(x, ((128, 160), (64, 96))) # 4a: 14x14x576
x = inception(x, (224, (64, 96), (96, 128), 128)) # 4b: 14x14x576
x = inception(x, (192, (96, 128), (96, 128), 128)) # 4c: 14x14x576
x = inception(x, (160, (128, 160), (128, 160), 96)) # 4d: 14x14x576
x = inception(x, (96, (128, 192), (160, 192), 96)) # 4e: 14x14x576
x = inception_s2(x, ((128, 192), (192, 256))) # 5a: 7x7x1024
x = inception(x, (352, (192, 320), (160, 224), 128)) # 5b: 7x7x1024
x = inception(x, (352, (192, 320), (192, 224), 128)) # 5c: 7x7x1024
# NOTE: 'AveragePooling2D' in '5c' (was 'MaxPooling2D' in original slim)
if include_top:
# Classification block
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='global_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='global_pool')(x)
else:
raise ValueError('bad spec of global pooling')
x = layers.Dropout(0.4)(x)
x = layers.Dense(classes, activation='softmax', name='predictions')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name='inception_v2')
return model
def MobileNetV3(stack_fn,
last_point_ch,
input_shape=None,
alpha=1.0,
model_type='large',
minimalistic=False,
include_top=True,
weights='imagenet',
input_tensor=None,
classes=1000,
pooling=None,
dropout_rate=0.2,
**kwargs):
"""Instantiates the MobileNetV3 architecture.
# Arguments
stack_fn: a function that returns output tensor for the
stacked residual blocks.
last_point_ch: number channels at the last layer (before top)
input_shape: optional shape tuple, to be specified if you would
like to use a model with an input img resolution that is not
(224, 224, 3).
It should have exactly 3 inputs channels (224, 224, 3).
You can also omit this option if you would like
to infer input_shape from an input_tensor.
If you choose to include both input_tensor and input_shape then
input_shape will be used if they match, if the shapes
do not match then we will throw an error.
E.g. `(160, 160, 3)` would be one valid value.
alpha: controls the width of the network. This is known as the
depth multiplier in the MobileNetV3 paper, but the name is kept for
consistency with MobileNetV1 in Keras.
- 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.
model_type: MobileNetV3 is defined as two models: large and small. These
models are targeted at high and low resource use cases respectively.
minimalistic: In addition to large and small models this module also contains
so-called minimalistic models, these models have the same per-layer
dimensions characteristic as MobilenetV3 however, they don't utilize any
of the advanced blocks (squeeze-and-excite units, hard-swish, and 5x5
convolutions). While these models are less efficient on CPU, they are
much more performant on GPU/DSP.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
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.
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.
dropout_rate: fraction of the input units to drop on the last layer
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid model type, argument for `weights`,
or invalid input shape when weights='imagenet'
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
# If input_shape is None and input_tensor is None using standart shape
if input_shape is None and input_tensor is None:
input_shape = (None, None, 3)
if K.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 rows and cols and (rows < 32 or cols < 32):
raise ValueError(
'Input size must be at least 32x32; got `input_shape=' +
str(input_shape) + '`')
if weights == 'imagenet':
if minimalistic is False and alpha not in [0.75, 1.0] \
or minimalistic is True and alpha != 1.0:
raise ValueError(
'If imagenet weights are being loaded, '
'alpha can be one of `0.75`, `1.0` for non minimalistic'
' or `1.0` for minimalistic only.')
if rows != cols or rows != 224:
warnings.warn('`input_shape` is undefined or non-square, '
'or `rows` is not 224.'
' Weights for input shape (224, 224) will be'
' loaded as the default.')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
#if not K.is_keras_tensor(input_tensor):
#img_input = Input(tensor=input_tensor, shape=input_shape)
#else:
#img_input = input_tensor
img_input = input_tensor
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
if minimalistic:
kernel = 3
activation = relu
se_ratio = None
else:
kernel = 5
activation = hard_swish
se_ratio = 0.25
x = ZeroPadding2D(padding=correct_pad(K, img_input, 3),
name='Conv_pad')(img_input)
x = DeeplabConv2D(16,
kernel_size=3,
strides=(2, 2),
padding='valid',
use_bias=False,
name='Conv')(x)
x = CustomBatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='Conv/BatchNorm')(x)
x = Activation(activation)(x)
x, skip_feature = stack_fn(x, kernel, activation, se_ratio)
# keep end of the feature extrator as final feature map
final_feature = x
last_conv_ch = _depth(K.int_shape(x)[channel_axis] * 6)
# if the width multiplier is greater than 1 we
# increase the number of output channels
if alpha > 1.0:
last_point_ch = _depth(last_point_ch * alpha)
x = DeeplabConv2D(last_conv_ch,
kernel_size=1,
padding='same',
use_bias=False,
name='Conv_1')(x)
x = CustomBatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='Conv_1/BatchNorm')(x)
x = Activation(activation)(x)
if include_top:
x = GlobalAveragePooling2D()(x)
if channel_axis == 1:
x = Reshape((last_conv_ch, 1, 1))(x)
else:
x = Reshape((1, 1, last_conv_ch))(x)
x = DeeplabConv2D(last_point_ch,
kernel_size=1,
padding='same',
name='Conv_2')(x)
x = Activation(activation)(x)
if dropout_rate > 0:
x = Dropout(dropout_rate)(x)
x = DeeplabConv2D(classes,
kernel_size=1,
padding='same',
name='Logits')(x)
x = Flatten()(x)
x = Softmax(name='Predictions/Softmax')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(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='MobilenetV3' + model_type)
# Load weights.
if weights == 'imagenet':
model_name = "{}{}_224_{}_float".format(
model_type, '_minimalistic' if minimalistic else '', str(alpha))
if include_top:
file_name = 'weights_mobilenet_v3_' + model_name + '.h5'
file_hash = WEIGHTS_HASHES[model_name][0]
else:
file_name = 'weights_mobilenet_v3_' + model_name + '_no_top.h5'
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = get_file(file_name,
BASE_WEIGHT_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
#return model
return final_feature, skip_feature, len(model.layers) - 3
def SENET50(include_top=True,
weights='vggface',
input_tensor=None,
input_shape=None,
pooling=None,
classes=8631):
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
bn_eps = 0.0001
x = Conv2D(64, (7, 7),
use_bias=False,
strides=(2, 2),
padding='same',
name='conv1/7x7_s2')(img_input)
x = BatchNormalization(axis=bn_axis,
name='conv1/7x7_s2/bn',
epsilon=bn_eps)(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = senet_conv_block(x, 3, [64, 64, 256], stage=2, block=1, strides=(1, 1))
x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=2)
x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=3)
x = senet_conv_block(x, 3, [128, 128, 512], stage=3, block=1)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=2)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=3)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=4)
x = senet_conv_block(x, 3, [256, 256, 1024], stage=4, block=1)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=2)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=3)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=4)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=5)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=6)
x = senet_conv_block(x, 3, [512, 512, 2048], stage=5, block=1)
x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=2)
x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=3)
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='classifier')(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='vggface_senet50')
# load weights
if weights == 'vggface':
if include_top:
weights_path = get_file('rcmalli_vggface_tf_senet50.h5',
utils.SENET50_WEIGHTS_PATH,
cache_subdir=utils.VGGFACE_DIR)
else:
weights_path = get_file('rcmalli_vggface_tf_notop_senet50.h5',
utils.SENET50_WEIGHTS_PATH_NO_TOP,
cache_subdir=utils.VGGFACE_DIR)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def build_resnet(
repetitions=(2, 2, 2, 2),
include_top=True,
input_tensor=None,
input_shape=None,
classes=1000,
block_type='conv',
attention=None):
"""
TODO
"""
if input_tensor is None:
img_input = Input(shape=input_shape, name='data')
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# choose residual block type
if block_type == 'conv':
residual_block = residual_conv_block
elif block_type == 'bottleneck':
residual_block = residual_bottleneck_block
else:
raise ValueError('Block type "{}" not in ["conv", "bottleneck"]'.format(block_type))
# choose attention block type
if attention == 'sse':
attention_block = SpatialSE()
elif attention == 'cse':
attention_block = ChannelSE(reduction=16)
elif attention == 'csse':
attention_block = ChannelSpatialSE(reduction=2)
elif attention is None:
attention_block = None
else:
raise ValueError('Supported attention blocks are: sse, cse, csse. Got "{}".'.format(attention))
# get parameters for model layers
no_scale_bn_params = get_bn_params(scale=False)
bn_params = get_bn_params()
conv_params = get_conv_params()
init_filters = 64
# resnet bottom
x = BatchNormalization(name='bn_data', **no_scale_bn_params)(img_input)
x = ZeroPadding2D(padding=(3, 3))(x)
x = Conv2D(init_filters, (7, 7), strides=(2, 2), name='conv0', **conv_params)(x)
x = BatchNormalization(name='bn0', **bn_params)(x)
x = Activation('relu', name='relu0')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='valid', name='pooling0')(x)
# resnet body
for stage, rep in enumerate(repetitions):
for block in range(rep):
filters = init_filters * (2**stage)
# first block of first stage without strides because we have maxpooling before
if block == 0 and stage == 0:
x = residual_block(filters, stage, block, strides=(1, 1),
cut='post', attention=attention_block)(x)
elif block == 0:
x = residual_block(filters, stage, block, strides=(2, 2),
cut='post', attention=attention_block)(x)
else:
x = residual_block(filters, stage, block, strides=(1, 1),
cut='pre', attention=attention_block)(x)
x = BatchNormalization(name='bn1', **bn_params)(x)
x = Activation('relu', name='relu1')(x)
# resnet top
if include_top:
x = GlobalAveragePooling2D(name='pool1')(x)
x = Dense(classes, name='fc1')(x)
x = Activation('softmax', name='softmax')(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)
return model
def Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config 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),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
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 inputs 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 block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, 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 not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=71,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1
x = layers.Conv2D(32, (3, 3),
padding='same',
strides=(2, 2),
use_bias=False,
name='block1_conv1')(img_input)
x = layers.BatchNormalization(axis=channel_axis, name='block1_conv1_bn')(x)
x = layers.Activation('relu', name='block1_conv1_act')(x)
x = layers.Conv2D(64, (3, 3),
padding='same',
use_bias=False,
name='block1_conv2')(x)
x = layers.BatchNormalization(axis=channel_axis, name='block1_conv2_bn')(x)
x = layers.Activation('relu', name='block1_conv2_act')(x)
residual = layers.Conv2D(128, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = layers.BatchNormalization(axis=channel_axis)(residual)
x = layers.SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block2_sepconv1_bn')(x)
x = layers.Activation('relu', name='block2_sepconv2_act')(x)
x = layers.SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv2')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block2_sepconv2_bn')(x)
x = layers.MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block2_pool')(x)
x = layers.add([x, residual])
residual = layers.Conv2D(256, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = layers.BatchNormalization(axis=channel_axis)(residual)
x = layers.Activation('relu', name='block3_sepconv1_act')(x)
x = layers.SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block3_sepconv1_bn')(x)
x = layers.Activation('relu', name='block3_sepconv2_act')(x)
x = layers.SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv2')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block3_sepconv2_bn')(x)
x = layers.MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block3_pool')(x)
x = layers.add([x, residual])
residual = layers.Conv2D(728, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = layers.BatchNormalization(axis=channel_axis)(residual)
x = layers.Activation('relu', name='block4_sepconv1_act')(x)
x = layers.SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block4_sepconv1_bn')(x)
x = layers.Activation('relu', name='block4_sepconv2_act')(x)
x = layers.SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv2')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block4_sepconv2_bn')(x)
x = layers.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 = layers.Activation('relu', name=prefix + '_sepconv1_act')(x)
x = layers.SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
name=prefix + '_sepconv1_bn')(x)
x = layers.Activation('relu', name=prefix + '_sepconv2_act')(x)
x = layers.SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv2')(x)
x = layers.BatchNormalization(axis=channel_axis,
name=prefix + '_sepconv2_bn')(x)
x = layers.Activation('relu', name=prefix + '_sepconv3_act')(x)
x = layers.SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv3')(x)
x = layers.BatchNormalization(axis=channel_axis,
name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = layers.Conv2D(1024, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = layers.BatchNormalization(axis=channel_axis)(residual)
x = layers.Activation('relu', name='block13_sepconv1_act')(x)
x = layers.SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block13_sepconv1_bn')(x)
x = layers.Activation('relu', name='block13_sepconv2_act')(x)
x = layers.SeparableConv2D(1024, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv2')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block13_sepconv2_bn')(x)
x = layers.MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block13_pool')(x)
x = layers.add([x, residual])
x = layers.SeparableConv2D(1536, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block14_sepconv1_bn')(x)
x = layers.Activation('relu', name='block14_sepconv1_act')(x)
x = layers.SeparableConv2D(2048, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv2')(x)
x = layers.BatchNormalization(axis=channel_axis,
name='block14_sepconv2_bn')(x)
x = layers.Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.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 = models.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',
file_hash='0a58e3b7378bc2990ea3b43d5981f1f6')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='b0042744bf5b25fce3cb969f33bebb97')
model.load_weights(weights_path)
# if backend.backend() == 'theano':
# convert_all_kernels_in_model(model)
elif weights is not None:
model.load_weights(weights)
return model
def VGG16(include_top=True,
weights='vggface',
input_tensor=None,
input_shape=None,
pooling=None,
classes=2622):
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same',
name='conv1_1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same',
name='conv1_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same',
name='conv2_1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same',
name='conv2_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool5')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, name='fc6')(x)
x = Activation('relu', name='fc6/relu')(x)
x = Dense(4096, name='fc7')(x)
x = Activation('relu', name='fc7/relu')(x)
x = Dense(classes, name='fc8')(x)
x = Activation('softmax', name='fc8/softmax')(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='vggface_vgg16') # load weights
if weights == 'vggface':
if include_top:
weights_path = get_file('rcmalli_vggface_tf_vgg16.h5',
utils.VGG16_WEIGHTS_PATH,
cache_subdir=utils.VGGFACE_DIR)
else:
weights_path = get_file('rcmalli_vggface_tf_notop_vgg16.h5',
utils.VGG16_WEIGHTS_PATH_NO_TOP,
cache_subdir=utils.VGGFACE_DIR)
model.load_weights(weights_path, by_name=True)
return model
def SEDenseNet(input_shape=None,
depth=40,
nb_dense_block=3,
growth_rate=12,
nb_filter=-1,
nb_layers_per_block=-1,
bottleneck=False,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
subsample_initial_block=False,
include_top=True,
weights=None,
input_tensor=None,
classes=10,
activation='softmax'):
"""Instantiate the SE DenseNet architecture
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` dim ordering)
or `(3, 32, 32)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
depth: number or layers in the DenseNet
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. -1 indicates initial
number of filters is 2 * growth_rate
nb_layers_per_block: number of layers in each dense block.
Can be a -1, positive integer or a list.
If -1, calculates nb_layer_per_block from the network depth.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
bottleneck: flag to add bottleneck blocks in between dense blocks
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
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.
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.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
# Returns
A Keras model instance.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `cifar10` '
'(pre-training on CIFAR-10).')
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 activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError(
'sigmoid activation can only be used when classes = 1')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_dense_net(classes, img_input, include_top, depth,
nb_dense_block, growth_rate, nb_filter,
nb_layers_per_block, bottleneck, reduction,
dropout_rate, weight_decay, subsample_initial_block,
activation)
# 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='se-densenet')
return model
def build_resnext(repetitions=(2, 2, 2, 2),
include_top=True,
input_tensor=None,
input_shape=None,
classes=1000,
first_conv_filters=64,
first_block_filters=64):
"""
TODO
"""
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format='channels_last',
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape, name='data')
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# get parameters for model layers
no_scale_bn_params = get_bn_params(scale=False)
bn_params = get_bn_params()
conv_params = get_conv_params()
init_filters = first_block_filters
# resnext bottom
x = BatchNormalization(name='bn_data', **no_scale_bn_params)(img_input)
x = ZeroPadding2D(padding=(3, 3))(x)
x = Conv2D(first_conv_filters, (7, 7),
strides=(2, 2),
name='conv0',
**conv_params)(x)
x = BatchNormalization(name='bn0', **bn_params)(x)
x = Activation('relu', name='relu0')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='valid',
name='pooling0')(x)
# resnext body
for stage, rep in enumerate(repetitions):
for block in range(rep):
filters = init_filters * (2**stage)
# first block of first stage without strides because we have maxpooling before
if stage == 0 and block == 0:
x = conv_block(filters, stage, block, strides=(1, 1))(x)
elif block == 0:
x = conv_block(filters, stage, block, strides=(2, 2))(x)
else:
x = identity_block(filters, stage, block)(x)
# resnext top
if include_top:
x = GlobalAveragePooling2D(name='pool1')(x)
x = Dense(classes, name='fc1')(x)
x = Activation('softmax', name='softmax')(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)
return model
def ResNet(stack_fn,
preact,
use_bias,
model_name='resnet',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
norm_use="bn",
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
stack_fn: a function that returns output tensor for the
stacked residual blocks.
preact: whether to use pre-activation or not
(True for ResNetV2, False for ResNet and ResNeXt).
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
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 `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
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.
"""
global backend, layers, models, keras_utils
#backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)),
name='conv1_pad')(img_input)
x = layers.Conv2D(64,
7,
strides=2,
use_bias=use_bias,
name='conv1_conv',
kernel_initializer='he_normal')(x)
if preact is False:
x = normalize_layer(x, norm_use=norm_use, name='conv1_')
#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 = normalize_layer(x, norm_use=norm_use, name='post_')
#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 = layers.Dense(classes, activation='softmax', name='probs')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# 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)
elif weights is not None:
model.load_weights(weights, by_name=True)
return model
def ResNet50(include_top=True,
OS=8,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
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 `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 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 block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, 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.
"""
"""
Modified ResNet50 feature extractor body
with specified output stride and skip level feature
"""
if OS == 8:
origin_os16_stride = (1, 1)
origin_os16_block_rate = 2
origin_os32_stride = (1, 1)
origin_os32_block_rate = 4
elif OS == 16:
origin_os16_stride = (2, 2)
origin_os16_block_rate = 1
origin_os32_stride = (1, 1)
origin_os32_block_rate = 2
elif OS == 32:
origin_os16_stride = (2, 2)
origin_os16_block_rate = 1
origin_os32_stride = (2, 2)
origin_os32_block_rate = 1
else:
raise ValueError('invalid output stride', OS)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
#if not backend.is_keras_tensor(input_tensor):
#img_input = Input(tensor=input_tensor, shape=input_shape)
#else:
#img_input = input_tensor
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D(padding=(3, 3), name='conv1_pad')(img_input)
x = DeeplabConv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
kernel_initializer='he_normal',
name='conv1')(x)
x = CustomBatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = ReLU()(x)
x = ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
# skip level feature, with output stride = 4
skip = x
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
# original output stride changes to 16 from here, so we start to control block stride and dilation rate
x = conv_block(x,
3, [256, 256, 1024],
stage=4,
block='a',
strides=origin_os16_stride) # origin: stride=(2, 2)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='b',
rate=origin_os16_block_rate)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='c',
rate=origin_os16_block_rate)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='d',
rate=origin_os16_block_rate)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='e',
rate=origin_os16_block_rate)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='f',
rate=origin_os16_block_rate)
# original output stride changes to 32 from here
x = conv_block(x,
3, [512, 512, 2048],
stage=5,
block='a',
strides=origin_os32_stride,
rate=origin_os16_block_rate) # origin: stride=(2, 2)
x = identity_block(x,
3, [512, 512, 2048],
stage=5,
block='b',
rate=origin_os32_block_rate)
x = identity_block(x,
3, [512, 512, 2048],
stage=5,
block='c',
rate=origin_os32_block_rate)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
else:
warnings.warn('The output shape of `ResNet50(include_top=False)` '
'has been changed since Keras 2.2.0.')
# 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='resnet50')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
backbone_len = len(model.layers)
# need to return feature map and skip connection,
# not the whole "no top" model
return x, skip, backbone_len
def SqueezeNet(include_top=True,
input_shape=None,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the SqueezeNet architecture.
"""
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 classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
input_shape = _obtain_input_shape(input_shape,
default_size=227,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
#if not K.is_keras_tensor(input_tensor):
#img_input = Input(tensor=input_tensor, shape=input_shape)
#else:
#img_input = input_tensor
img_input = input_tensor
x = Conv2D(64, (3, 3), strides=(2, 2), padding='valid',
name='conv1')(img_input)
x = Activation('relu', name='relu_conv1')(x)
x = MaxPool2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x)
x = fire_module(x, fire_id=2, squeeze=16, expand=64)
x = fire_module(x, fire_id=3, squeeze=16, expand=64)
x = MaxPool2D(pool_size=(3, 3), strides=(2, 2), name='pool3')(x)
x = fire_module(x, fire_id=4, squeeze=32, expand=128)
x = fire_module(x, fire_id=5, squeeze=32, expand=128)
x = MaxPool2D(pool_size=(3, 3), strides=(2, 2), name='pool5')(x)
x = fire_module(x, fire_id=6, squeeze=48, expand=192)
x = fire_module(x, fire_id=7, squeeze=48, expand=192)
x = fire_module(x, fire_id=8, squeeze=64, expand=256)
x = fire_module(x, fire_id=9, squeeze=64, expand=256)
if include_top:
# It's not obvious where to cut the network...
# Could do the 8th or 9th layer... some work recommends cutting earlier layers.
x = Dropout(0.5, name='drop9')(x)
x = Conv2D(classes, (1, 1), padding='valid', name='conv10')(x)
x = Activation('relu', name='relu_conv10')(x)
x = GlobalAveragePooling2D()(x)
x = Activation('softmax', name='loss')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
elif pooling == None:
pass
else:
raise ValueError("Unknown argument for 'pooling'=" + pooling)
# 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
model = Model(inputs, x, name='squeezenet')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'squeezenet_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'squeezenet_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def EfficientNet(width_coefficient,
depth_coefficient,
default_size,
dropout_rate=0.2,
drop_connect_rate=0.2,
depth_divisor=8,
activation_fn=swish,
blocks_args=DEFAULT_BLOCKS_ARGS,
model_name='efficientnet',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the EfficientNet architecture using given scaling coefficients.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
width_coefficient: float, scaling coefficient for network width.
depth_coefficient: float, scaling coefficient for network depth.
default_size: integer, default input image size.
dropout_rate: float, dropout rate before final classifier layer.
drop_connect_rate: float, dropout rate at skip connections.
depth_divisor: integer, a unit of network width.
activation_fn: activation function.
blocks_args: list of dicts, parameters to construct block modules.
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
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.
It should have exactly 3 inputs channels.
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.
"""
#global backend, layers, models, keras_utils
#backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
#if not K.is_keras_tensor(input_tensor):
#img_input = Input(tensor=input_tensor, shape=input_shape)
#else:
#img_input = input_tensor
img_input = input_tensor
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
def round_filters(filters, divisor=depth_divisor):
"""Round number of filters based on depth multiplier."""
filters *= width_coefficient
new_filters = max(divisor,
int(filters + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_filters < 0.9 * filters:
new_filters += divisor
return int(new_filters)
def round_repeats(repeats):
"""Round number of repeats based on depth multiplier."""
return int(math.ceil(depth_coefficient * repeats))
# Build stem
x = img_input
x = ZeroPadding2D(padding=correct_pad(K, x, 3), name='stem_conv_pad')(x)
x = Conv2D(round_filters(32),
3,
strides=2,
padding='valid',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER,
name='stem_conv')(x)
x = BatchNormalization(axis=bn_axis, name='stem_bn')(x)
x = Activation(activation_fn, name='stem_activation')(x)
# Build blocks
from copy import deepcopy
blocks_args = deepcopy(blocks_args)
b = 0
blocks = float(sum(args['repeats'] for args in blocks_args))
for (i, args) in enumerate(blocks_args):
assert args['repeats'] > 0
# Update block input and output filters based on depth multiplier.
args['filters_in'] = round_filters(args['filters_in'])
args['filters_out'] = round_filters(args['filters_out'])
for j in range(round_repeats(args.pop('repeats'))):
# The first block needs to take care of stride and filter size increase.
if j > 0:
args['strides'] = 1
args['filters_in'] = args['filters_out']
x = block(x,
activation_fn,
drop_connect_rate * b / blocks,
name='block{}{}_'.format(i + 1, chr(j + 97)),
**args)
b += 1
# Build top
x = Conv2D(round_filters(1280),
1,
padding='same',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER,
name='top_conv')(x)
x = BatchNormalization(axis=bn_axis, name='top_bn')(x)
x = Activation(activation_fn, name='top_activation')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
if dropout_rate > 0:
x = Dropout(dropout_rate, name='top_dropout')(x)
x = Dense(classes,
activation='softmax',
kernel_initializer=DENSE_KERNEL_INITIALIZER,
name='probs')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(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=model_name)
# Load weights.
if weights == 'imagenet':
if include_top:
file_suff = '_weights_tf_dim_ordering_tf_kernels_autoaugment.h5'
file_hash = WEIGHTS_HASHES[model_name[-2:]][0]
else:
file_suff = '_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5'
file_hash = WEIGHTS_HASHES[model_name[-2:]][1]
file_name = model_name + file_suff
weights_path = get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def MobileNetV2(input_shape=None,
alpha=1.0,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the MobileNetV2 architecture.
# Arguments
input_shape: optional shape tuple, to be specified if you would
like to use a model with an input img resolution that is not
(224, 224, 3).
It should have exactly 3 inputs channels (224, 224, 3).
You can also omit this option if you would like
to infer input_shape from an input_tensor.
If you choose to include both input_tensor and input_shape then
input_shape will be used if they match, if the shapes
do not match then we will throw an error.
E.g. `(160, 160, 3)` would be one valid value.
alpha: controls the width of the network. This is known as the
width multiplier in the MobileNetV2 paper, but the name is kept for
consistency with MobileNetV1 in Keras.
- 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.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
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 block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, 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 or invalid alpha, rows when
weights='imagenet'
"""
# global backend, layers, models, keras_utils
# backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape and default size.
# If both input_shape and input_tensor are used, they should match
if input_shape is not None and input_tensor is not None:
try:
is_input_t_tensor = backend.is_keras_tensor(input_tensor)
except ValueError:
try:
is_input_t_tensor = backend.is_keras_tensor(
keras_utils.get_source_inputs(input_tensor))
except ValueError:
raise ValueError('input_tensor: ', input_tensor,
'is not type input_tensor')
if is_input_t_tensor:
if backend.image_data_format == 'channels_first':
if backend.int_shape(input_tensor)[1] != input_shape[1]:
raise ValueError(
'input_shape: ', input_shape, 'and input_tensor: ',
input_tensor,
'do not meet the same shape requirements')
else:
if backend.int_shape(input_tensor)[2] != input_shape[1]:
raise ValueError(
'input_shape: ', input_shape, 'and input_tensor: ',
input_tensor,
'do not meet the same shape requirements')
else:
raise ValueError('input_tensor specified: ', input_tensor,
'is not a keras tensor')
# If input_shape is None, infer shape from input_tensor
if input_shape is None and input_tensor is not None:
try:
backend.is_keras_tensor(input_tensor)
except ValueError:
raise ValueError('input_tensor: ', input_tensor, 'is type: ',
type(input_tensor), 'which is not a valid type')
if input_shape is None and not backend.is_keras_tensor(input_tensor):
default_size = 224
elif input_shape is None and backend.is_keras_tensor(input_tensor):
if backend.image_data_format() == 'channels_first':
rows = backend.int_shape(input_tensor)[2]
cols = backend.int_shape(input_tensor)[3]
else:
rows = backend.int_shape(input_tensor)[1]
cols = backend.int_shape(input_tensor)[2]
if rows == cols and rows in [96, 128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
# If input_shape is None and no input_tensor
elif input_shape is None:
default_size = 224
# If input_shape is not None, assume default size
else:
if backend.image_data_format() == 'channels_first':
rows = input_shape[1]
cols = input_shape[2]
else:
rows = input_shape[0]
cols = input_shape[1]
if rows == cols and rows in [96, 128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
input_shape = _obtain_input_shape(input_shape,
default_size=default_size,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
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 alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of `0.35`, `0.50`, `0.75`, '
'`1.0`, `1.3` or `1.4` only.')
if rows != cols or rows not in [96, 128, 160, 192, 224]:
rows = 224
warnings.warn('`input_shape` is undefined or non-square, '
'or `rows` is not in [96, 128, 160, 192, 224].'
' Weights for input shape (224, 224) will be'
' loaded as the default.')
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1
first_block_filters = _make_divisible(32 * alpha, 8)
x = layers.ZeroPadding2D(padding=correct_pad(backend, img_input, 3),
name='Conv1_pad')(img_input)
x = layers.Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='valid',
use_bias=False,
name='Conv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='bn_Conv1')(x)
x = layers.ReLU(6., name='Conv1_relu')(x)
x = _inverted_res_block(x,
filters=16,
alpha=alpha,
stride=1,
expansion=1,
block_id=0)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=2,
expansion=6,
block_id=1)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=1,
expansion=6,
block_id=2)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=2,
expansion=6,
block_id=3)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=4)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=5)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=2,
expansion=6,
block_id=6)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=7)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=8)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=9)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=10)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=11)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=12)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=2,
expansion=6,
block_id=13)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=14)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=15)
x = _inverted_res_block(x,
filters=320,
alpha=alpha,
stride=1,
expansion=6,
block_id=16)
# no alpha applied to last conv as stated in the paper:
# if the width multiplier is greater than 1 we
# increase the number of output channels
if alpha > 1.0:
last_block_filters = _make_divisible(1280 * alpha, 8)
else:
last_block_filters = 1280
x = layers.Conv2D(last_block_filters,
kernel_size=1,
use_bias=False,
name='Conv_1')(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='Conv_1_bn')(x)
x = layers.ReLU(6., name='out_relu')(x)
if include_top:
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(classes,
activation='softmax',
use_bias=True,
name='Logits')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = tf.keras.Model(inputs,
x,
name='mobilenetv2_%0.2f_%s' % (alpha, rows))
# Load weights.
if weights == 'imagenet':
if include_top:
model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
str(alpha) + '_' + str(rows) + '.h5')
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = keras_utils.get_file(model_name,
weight_path,
cache_subdir='models')
else:
model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
str(alpha) + '_' + str(rows) + '_no_top' + '.h5')
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
def NanoNet(input_shape=None,
input_tensor=None,
include_top=True,
weights='imagenet',
pooling=None,
classes=1000,
**kwargs):
"""Generate nano net model for Imagenet classification."""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=28,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = input_tensor
x = nano_net_body(img_input)
if include_top:
model_name = 'nano_net'
x = DarknetConv2D(classes, (1, 1))(x)
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Softmax()(x)
else:
model_name = 'nano_net_headless'
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(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=model_name)
# Load weights.
if weights == 'imagenet':
if include_top:
file_name = 'nanonet_weights_tf_dim_ordering_tf_kernels_224.h5'
weight_path = BASE_WEIGHT_PATH + file_name
else:
file_name = 'nanonet_weights_tf_dim_ordering_tf_kernels_224_no_top.h5'
weight_path = BASE_WEIGHT_PATH + file_name
weights_path = get_file(file_name, weight_path, cache_subdir='models')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception v3 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
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),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
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)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
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.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='same')
x = conv2d_bn(x, 32, 3, 3, padding='same')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = conv2d_bn(x, 80, 1, 1, padding='same')
x = conv2d_bn(x, 192, 3, 3, padding='same')
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='same')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl,
96,
3,
3,
strides=(2, 2),
padding='same')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = layers.concatenate([branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='same')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(branch7x7x3,
192,
3,
3,
strides=(2, 2),
padding='same')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = layers.concatenate([branch3x3, branch7x7x3, branch_pool],
axis=channel_axis,
name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2],
axis=channel_axis,
name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2],
axis=channel_axis)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
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='inception_v3')
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def SEResNet(input_shape=None,
initial_conv_filters=64,
depth=[3, 4, 6, 3],
filters=[64, 128, 256, 512],
width=1,
bottleneck=False,
weight_decay=1e-4,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=1000):
""" Instantiate the Squeeze and Excite ResNet architecture. Note that ,
when using TensorFlow for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
initial_conv_filters: number of features for the initial convolution
depth: number or layers in the each block, defined as a list.
ResNet-50 = [3, 4, 6, 3]
ResNet-101 = [3, 6, 23, 3]
ResNet-152 = [3, 8, 36, 3]
filter: number of filters per block, defined as a list.
filters = [64, 128, 256, 512
width: width multiplier for the network (for Wide ResNets)
bottleneck: adds a bottleneck conv to reduce computation
weight_decay: weight decay (l2 norm)
include_top: whether to include the fully-connected
layer at the top of the network.
weights: `None` (random initialization) or `imagenet` (trained
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 `(224, 224, 3)` (with `tf` dim ordering)
or `(3, 224, 224)` (with `th` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 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.
"""
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')
assert len(depth) == len(filters), "The length of filter increment list must match the length " \
"of the depth list."
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
require_flatten=False)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = _create_se_resnet(classes, img_input, include_top, initial_conv_filters,
filters, depth, width, bottleneck, weight_decay, pooling)
# 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='resnext')
# load weights
return model
def Deeplabv3(weights=None,
input_tensor=None,
input_shape=(256, 256, 3),
classes=23,
backbone='xception',
OS=16,
alpha=1.,
activation=None):
"""Instantiates the Deeplabv3+ architecture Optionally loads weights pre-
trained on PASCAL VOC or Cityscapes. This model is available for TensorFlow
only.
Arguments
weights: one of 'pascal_voc' (pre-trained on pascal voc),
'cityscapes' (pre-trained on cityscape) or None(random
initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: shape of input image. format HxWxC PASCAL VOC model was
trained on (512,512,3) images. None is allowed as shape/width
classes: number of desired classes. PASCAL VOC has 21 classes,
Cityscapes has 19 classes. If number of classes not aligned
with the weights used, last layer is initialized randomly
backbone: backbone to use. one of {'xception','mobilenetv2'}
activation: optional activation to add to the top of the network.
One of 'softmax', 'sigmoid' or None
OS: determines input_shape/feature_extractor_output ratio. One of
{8,16}. Used only for xception backbone.
alpha: controls the width of the MobileNetV2 network. This is known
as the width multiplier in the MobileNetV2 paper.
- 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.
Used only for mobilenetv2 backbone. Pretrained is only available
for alpha=1.
Returns
A Keras model instance.
Raises
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
ValueError: in case of invalid argument for `weights` or `backbone`
"""
if not (weights in {'pascal_voc', 'cityscapes', None}):
raise ValueError(
'The `weights` argument should be either '
'`None` (random initialization), `pascal_voc`, or `cityscapes` '
'(pre-trained on PASCAL VOC)')
if not (backbone in {'xception', 'mobilenetv2'}):
raise ValueError('The `backbone` argument should be either '
'`xception` or `mobilenetv2` ')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = input_tensor
if backbone == 'xception':
if OS == 8:
entry_block3_stride = 1
middle_block_rate = 2 # ! Not mentioned in paper, but required
exit_block_rates = (2, 4)
atrous_rates = (12, 24, 36)
else:
entry_block3_stride = 2
middle_block_rate = 1
exit_block_rates = (1, 2)
atrous_rates = (6, 12, 18)
x = Conv2D(32, (3, 3),
strides=(2, 2),
name='entry_flow_conv1_1',
use_bias=False,
padding='same')(img_input)
x = BatchNormalization(name='entry_flow_conv1_1_BN')(x)
x = Activation(tf.nn.relu)(x)
x = _conv2d_same(x, 64, 'entry_flow_conv1_2', kernel_size=3, stride=1)
x = BatchNormalization(name='entry_flow_conv1_2_BN')(x)
x = Activation(tf.nn.relu)(x)
x = _xception_block(x, [128, 128, 128],
'entry_flow_block1',
skip_connection_type='conv',
stride=2,
depth_activation=False)
x, skip1 = _xception_block(x, [256, 256, 256],
'entry_flow_block2',
skip_connection_type='conv',
stride=2,
depth_activation=False,
return_skip=True)
x = _xception_block(x, [728, 728, 728],
'entry_flow_block3',
skip_connection_type='conv',
stride=entry_block3_stride,
depth_activation=False)
for i in range(16):
x = _xception_block(x, [728, 728, 728],
'middle_flow_unit_{}'.format(i + 1),
skip_connection_type='sum',
stride=1,
rate=middle_block_rate,
depth_activation=False)
x = _xception_block(x, [728, 1024, 1024],
'exit_flow_block1',
skip_connection_type='conv',
stride=1,
rate=exit_block_rates[0],
depth_activation=False)
x = _xception_block(x, [1536, 1536, 2048],
'exit_flow_block2',
skip_connection_type='none',
stride=1,
rate=exit_block_rates[1],
depth_activation=True)
else:
OS = 8
first_block_filters = _make_divisible(32 * alpha, 8)
x = Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name='Conv')(img_input)
x = BatchNormalization(epsilon=1e-3, momentum=0.999, name='Conv_BN')(x)
x = Activation(tf.nn.relu6, name='Conv_Relu6')(x)
x = _inverted_res_block(x,
filters=16,
alpha=alpha,
stride=1,
expansion=1,
block_id=0,
skip_connection=False)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=2,
expansion=6,
block_id=1,
skip_connection=False)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=1,
expansion=6,
block_id=2,
skip_connection=True)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=2,
expansion=6,
block_id=3,
skip_connection=False)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=4,
skip_connection=True)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=5,
skip_connection=True)
# stride in block 6 changed from 2 -> 1, so we need to use rate = 2
x = _inverted_res_block(
x,
filters=64,
alpha=alpha,
stride=1, # 1!
expansion=6,
block_id=6,
skip_connection=False)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=7,
skip_connection=True)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=8,
skip_connection=True)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=9,
skip_connection=True)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=10,
skip_connection=False)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=11,
skip_connection=True)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=12,
skip_connection=True)
x = _inverted_res_block(
x,
filters=160,
alpha=alpha,
stride=1,
rate=2, # 1!
expansion=6,
block_id=13,
skip_connection=False)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
rate=4,
expansion=6,
block_id=14,
skip_connection=True)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
rate=4,
expansion=6,
block_id=15,
skip_connection=True)
x = _inverted_res_block(x,
filters=320,
alpha=alpha,
stride=1,
rate=4,
expansion=6,
block_id=16,
skip_connection=False)
# end of feature extractor
# branching for Atrous Spatial Pyramid Pooling
# Image Feature branch
# shape_before = tf.shape(x)
b4 = GlobalAveragePooling2D()(x)
# from (b_size, channels)->(b_size, 1, 1, channels)
b4 = Lambda(lambda x: K.expand_dims(x, 1))(b4)
b4 = Lambda(lambda x: K.expand_dims(x, 1))(b4)
b4 = Conv2D(256, (1, 1),
padding='same',
use_bias=False,
name='image_pooling')(b4)
b4 = BatchNormalization(name='image_pooling_BN', epsilon=1e-5)(b4)
b4 = Activation(tf.nn.relu)(b4)
# upsample. have to use compat because of the option align_corners
size_before = tf.keras.backend.int_shape(x)
b4 = Lambda(lambda x: tf.compat.v1.image.resize(
x, size_before[1:3], method='bilinear', align_corners=True))(b4)
# simple 1x1
b0 = Conv2D(256, (1, 1), padding='same', use_bias=False, name='aspp0')(x)
b0 = BatchNormalization(name='aspp0_BN', epsilon=1e-5)(b0)
b0 = Activation(tf.nn.relu, name='aspp0_activation')(b0)
# there are only 2 branches in mobilenetV2. not sure why
if backbone == 'xception':
# rate = 6 (12)
b1 = SepConv_BN(x,
256,
'aspp1',
rate=atrous_rates[0],
depth_activation=True,
epsilon=1e-5)
# rate = 12 (24)
b2 = SepConv_BN(x,
256,
'aspp2',
rate=atrous_rates[1],
depth_activation=True,
epsilon=1e-5)
# rate = 18 (36)
b3 = SepConv_BN(x,
256,
'aspp3',
rate=atrous_rates[2],
depth_activation=True,
epsilon=1e-5)
# concatenate ASPP branches & project
x = Concatenate()([b4, b0, b1, b2, b3])
else:
x = Concatenate()([b4, b0])
x = Conv2D(256, (1, 1),
padding='same',
use_bias=False,
name='concat_projection')(x) # noqa: E501
x = BatchNormalization(name='concat_projection_BN', epsilon=1e-5)(x)
x = Activation(tf.nn.relu)(x)
x = Dropout(0.1)(x)
# DeepLab v.3+ decoder
if backbone == 'xception':
# Feature projection
# x4 (x2) block
skip_size = tf.keras.backend.int_shape(skip1)
x = Lambda(lambda xx: tf.compat.v1.image.resize(
xx, skip_size[1:3], method='bilinear', align_corners=True))(x)
dec_skip1 = Conv2D(48, (1, 1),
padding='same',
use_bias=False,
name='feature_projection0')(skip1)
dec_skip1 = BatchNormalization(name='feature_projection0_BN',
epsilon=1e-5)(dec_skip1)
dec_skip1 = Activation(tf.nn.relu)(dec_skip1)
x = Concatenate()([x, dec_skip1])
x = SepConv_BN(x,
256,
'decoder_conv0',
depth_activation=True,
epsilon=1e-5)
x = SepConv_BN(x,
256,
'decoder_conv1',
depth_activation=True,
epsilon=1e-5)
last_layer_name = 'custom_logits_semantic'
x = Conv2D(classes, (1, 1), padding='same', name=last_layer_name)(x)
size_before3 = tf.keras.backend.int_shape(img_input)
x = Lambda(lambda xx: tf.compat.v1.image.resize(
xx, size_before3[1:3], method='bilinear', align_corners=True))(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
if activation in {'softmax', 'sigmoid'}:
x = tf.keras.layers.Activation(activation)(x)
model = Model(inputs, x, name='deeplabv3plus')
# load weights
if weights == 'pascal_voc':
if backbone == 'xception':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_X,
cache_subdir='models')
else:
weights_path = get_file(
'deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_MOBILE,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
elif weights == 'cityscapes':
if backbone == 'xception':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels_cityscapes.h5',
WEIGHTS_PATH_X_CS,
cache_subdir='models')
else:
weights_path = get_file(
'deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels_cityscapes.h5', # noqa: E501
WEIGHTS_PATH_MOBILE_CS,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model
def bn_feature_net_2D(receptive_field=61,
input_shape=(256, 256, 1),
inputs=None,
n_features=3,
n_channels=1,
reg=1e-5,
n_conv_filters=64,
n_dense_filters=200,
VGG_mode=False,
init='he_normal',
norm_method='std',
location=False,
dilated=False,
padding=False,
padding_mode='reflect',
multires=False,
include_top=True):
"""Creates a 2D featurenet.
Args:
receptive_field (int): the receptive field of the neural network.
input_shape (tuple): If no input tensor, create one with this shape.
inputs (tensor): optional input tensor
n_features (int): Number of output features
n_channels (int): number of input channels
reg (int): regularization value
n_conv_filters (int): number of convolutional filters
n_dense_filters (int): number of dense filters
VGG_mode (bool): If ``multires``, uses ``VGG_mode``
for multiresolution
init (str): Method for initalizing weights.
norm_method (str): Normalization method to use with the
:mod:`deepcell.layers.normalization.ImageNormalization2D` layer.
location (bool): Whether to include a
:mod:`deepcell.layers.location.Location2D` layer.
dilated (bool): Whether to use dilated pooling.
padding (bool): Whether to use padding.
padding_mode (str): Type of padding, one of 'reflect' or 'zero'
multires (bool): Enables multi-resolution mode
include_top (bool): Whether to include the final layer of the model
Returns:
tensorflow.keras.Model: 2D FeatureNet
"""
# Create layers list (x) to store all of the layers.
# We need to use the functional API to enable the multiresolution mode
x = []
win = (receptive_field - 1) // 2
if dilated:
padding = True
if K.image_data_format() == 'channels_first':
channel_axis = 1
row_axis = 2
col_axis = 3
if not dilated:
input_shape = (n_channels, receptive_field, receptive_field)
else:
row_axis = 1
col_axis = 2
channel_axis = -1
if not dilated:
input_shape = (receptive_field, receptive_field, n_channels)
if inputs is not None:
if not K.is_keras_tensor(inputs):
img_input = Input(tensor=inputs, shape=input_shape)
else:
img_input = inputs
x.append(img_input)
else:
x.append(Input(shape=input_shape))
x.append(
ImageNormalization2D(norm_method=norm_method,
filter_size=receptive_field)(x[-1]))
if padding:
if padding_mode == 'reflect':
x.append(ReflectionPadding2D(padding=(win, win))(x[-1]))
elif padding_mode == 'zero':
x.append(ZeroPadding2D(padding=(win, win))(x[-1]))
if location:
x.append(Location2D()(x[-1]))
x.append(Concatenate(axis=channel_axis)([x[-2], x[-1]]))
layers_to_concat = []
rf_counter = receptive_field
block_counter = 0
d = 1
while rf_counter > 4:
filter_size = 3 if rf_counter % 2 == 0 else 4
x.append(
Conv2D(n_conv_filters,
filter_size,
dilation_rate=d,
kernel_initializer=init,
padding='valid',
kernel_regularizer=l2(reg))(x[-1]))
x.append(BatchNormalization(axis=channel_axis)(x[-1]))
x.append(Activation('relu')(x[-1]))
block_counter += 1
rf_counter -= filter_size - 1
if block_counter % 2 == 0:
if dilated:
x.append(
DilatedMaxPool2D(dilation_rate=d, pool_size=(2, 2))(x[-1]))
d *= 2
else:
x.append(MaxPool2D(pool_size=(2, 2))(x[-1]))
if VGG_mode:
n_conv_filters *= 2
rf_counter = rf_counter // 2
if multires:
layers_to_concat.append(len(x) - 1)
if multires:
c = []
for l in layers_to_concat:
output_shape = x[l].get_shape().as_list()
target_shape = x[-1].get_shape().as_list()
row_crop = int(output_shape[row_axis] - target_shape[row_axis])
if row_crop % 2 == 0:
row_crop = (row_crop // 2, row_crop // 2)
else:
row_crop = (row_crop // 2, row_crop // 2 + 1)
col_crop = int(output_shape[col_axis] - target_shape[col_axis])
if col_crop % 2 == 0:
col_crop = (col_crop // 2, col_crop // 2)
else:
col_crop = (col_crop // 2, col_crop // 2 + 1)
cropping = (row_crop, col_crop)
c.append(Cropping2D(cropping=cropping)(x[l]))
if multires:
x.append(Concatenate(axis=channel_axis)(c))
x.append(
Conv2D(n_dense_filters, (rf_counter, rf_counter),
dilation_rate=d,
kernel_initializer=init,
padding='valid',
kernel_regularizer=l2(reg))(x[-1]))
x.append(BatchNormalization(axis=channel_axis)(x[-1]))
x.append(Activation('relu')(x[-1]))
if include_top:
x.append(
TensorProduct(n_dense_filters,
kernel_initializer=init,
kernel_regularizer=l2(reg))(x[-1]))
x.append(BatchNormalization(axis=channel_axis)(x[-1]))
x.append(Activation('relu')(x[-1]))
x.append(
TensorProduct(n_features,
kernel_initializer=init,
kernel_regularizer=l2(reg))(x[-1]))
if not dilated:
x.append(Flatten()(x[-1]))
x.append(Softmax(axis=channel_axis, dtype=K.floatx())(x[-1]))
if inputs is not None:
real_inputs = keras_utils.get_source_inputs(x[0])
else:
real_inputs = x[0]
model = Model(inputs=real_inputs, outputs=x[-1])
return model
def VGG16(include_top=True,
weights='vggface',
input_tensor=None,
input_shape=None,
pooling=None,
classes=2622):
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same',
name='conv1_1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same',
name='conv1_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same',
name='conv2_1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same',
name='conv2_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool5')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, name='fc6')(x)
x = Activation('relu', name='fc6/relu')(x)
x = Dense(4096, name='fc7')(x)
x = Activation('relu', name='fc7/relu')(x)
x = Dense(classes, name='fc8')(x)
x = Activation('softmax', name='fc8/softmax')(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='vggface_vgg16') # load weights
if weights == 'vggface':
if include_top:
weights_path = get_file('rcmalli_vggface_tf_vgg16.h5',
utils.VGG16_WEIGHTS_PATH,
cache_subdir=utils.VGGFACE_DIR)
else:
weights_path = get_file('rcmalli_vggface_tf_notop_vgg16.h5',
utils.VGG16_WEIGHTS_PATH_NO_TOP,
cache_subdir=utils.VGGFACE_DIR)
model.load_weights(weights_path, by_name=True)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='pool5')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc6')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def RESNET50(include_top=True,
weights='vggface',
input_tensor=None,
input_shape=None,
pooling=None,
classes=8631):
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(64, (7, 7),
use_bias=False,
strides=(2, 2),
padding='same',
name='conv1/7x7_s2')(img_input)
x = BatchNormalization(axis=bn_axis, name='conv1/7x7_s2/bn')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = resnet_conv_block(x,
3, [64, 64, 256],
stage=2,
block=1,
strides=(1, 1))
x = resnet_identity_block(x, 3, [64, 64, 256], stage=2, block=2)
x = resnet_identity_block(x, 3, [64, 64, 256], stage=2, block=3)
x = resnet_conv_block(x, 3, [128, 128, 512], stage=3, block=1)
x = resnet_identity_block(x, 3, [128, 128, 512], stage=3, block=2)
x = resnet_identity_block(x, 3, [128, 128, 512], stage=3, block=3)
x = resnet_identity_block(x, 3, [128, 128, 512], stage=3, block=4)
x = resnet_conv_block(x, 3, [256, 256, 1024], stage=4, block=1)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=2)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=3)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=4)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=5)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=6)
x = resnet_conv_block(x, 3, [512, 512, 2048], stage=5, block=1)
x = resnet_identity_block(x, 3, [512, 512, 2048], stage=5, block=2)
x = resnet_identity_block(x, 3, [512, 512, 2048], stage=5, block=3)
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='classifier')(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='vggface_resnet50')
# load weights
if weights == 'vggface':
# if include_top:
# weights_path = get_file('rcmalli_vggface_tf_resnet50.h5',
# utils.RESNET50_WEIGHTS_PATH,
# cache_subdir=utils.VGGFACE_DIR)
# else:
# weights_path = get_file('rcmalli_vggface_tf_notop_resnet50.h5',
# utils.RESNET50_WEIGHTS_PATH_NO_TOP,
# cache_subdir=utils.VGGFACE_DIR)
weights_path = os.path.join(WEIGHTS_DIR,
'rcmalli_vggface_tf_notop_resnet50.h5')
model.load_weights(weights_path)
# if K.backend() == 'theano':
# layer_utils.convert_all_kernels_in_model(model)
# if include_top:
# maxpool = model.get_layer(name='avg_pool')
# shape = maxpool.output_shape[1:]
# dense = model.get_layer(name='classifier')
# layer_utils.convert_dense_weights_data_format(dense, shape,
# 'channels_first')
if K.image_data_format() == 'channels_first' and K.backend(
) == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
elif weights is not None:
model.load_weights(weights)
return model
def return_model(x,
classes,
img_input,
input_tensor,
activation,
weights,
backbone,
dual_output=False):
if (weights == 'pascal_voc' and classes == 21) or (weights == 'cityscapes'
and classes == 19):
last_layer_name = 'logits_semantic'
else:
last_layer_name = 'custom_logits_semantic'
lung_output = None
if dual_output:
lung_output = Conv2D(2, (1, 1), padding='same', name='lung_layer')(x)
x = Conv2D(classes, (1, 1), padding='same', name=last_layer_name)(x)
size_before3 = img_input.shape
x = Resize(int(size_before3[1]), int(size_before3[2]))(x)
# x = Lambda(lambda xx: tf.compat.v1.image.resize(xx, (int(size_before3[1]), int(size_before3[2])),
# align_corners=True))(x)
if lung_output is not None:
lung_output = Resize(int(size_before3[1]),
int(size_before3[2]))(lung_output)
# lung_output = Lambda(lambda xx: tf.compat.v1.image.resize(xx, (),
# align_corners=True))(lung_output)
lung_output = Activation('softmax',
name='Lung_Prediction')(lung_output)
# 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
if activation in {'softmax', 'sigmoid'}:
x = Activation(activation, name='L_R_Lung_Prediction')(x)
# version_split = tf.__version__.split('.')
# if version_split[0] == '2' and int(version_split[1]) > 1:
# x = Activation('linear', dtype='float32')(x)
if lung_output is not None:
model = Model(inputs=[inputs],
outputs=[x, lung_output],
name='deeplabv3plus')
else:
model = Model(inputs=[inputs], outputs=x, name='deeplabv3plus')
# load weights
if weights == 'pascal_voc':
if backbone == 'xception':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_X,
cache_subdir='models')
else:
weights_path = get_file(
'deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_MOBILE,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
elif weights == 'cityscapes':
if backbone == 'xception':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels_cityscapes.h5',
WEIGHTS_PATH_X_CS,
cache_subdir='models')
else:
weights_path = get_file(
'deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels_cityscapes.h5',
WEIGHTS_PATH_MOBILE_CS,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model
def ResNet(stack_fn,
preact,
use_bias,
model_name='resnet',
include_top=True,
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
stack_fn: a function that returns output tensor for the
stacked residual blocks.
preact: whether to use pre-activation or not
(True for ResNetV2, False for ResNet and ResNeXt).
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
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 `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
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.
"""
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.ZeroPadding3D(padding=3, name='conv1_pad')(img_input)
x = layers.Conv3D(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.ZeroPadding3D(padding=1, name='pool1_pad')(x)
x = layers.MaxPooling3D(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.GlobalAveragePooling3D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='probs')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling3D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling3D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name=model_name)
return model
def ShuffleNetV2(input_shape=None,
include_top=True,
weights='imagenet',
input_tensor=None,
scale_factor=1.0,
pooling=None,
num_shuffle_units=[3, 7, 3],
bottleneck_ratio=1,
classes=1000,
**kwargs):
"""Instantiates the ShuffleNetV2 architecture.
# Arguments
input_shape: optional shape tuple, to be specified if you would
like to use a model with an input img resolution that is not
(224, 224, 3).
It should have exactly 3 inputs channels (224, 224, 3).
You can also omit this option if you would like
to infer input_shape from an input_tensor.
If you choose to include both input_tensor and input_shape then
input_shape will be used if they match, if the shapes
do not match then we will throw an error.
E.g. `(160, 160, 3)` would be one valid value.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
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 block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, 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 or invalid alpha, rows when
weights='imagenet'
"""
if K.backend() != 'tensorflow':
raise RuntimeError('Only tensorflow supported for now')
name = 'ShuffleNetV2_{}_{}_{}'.format(
scale_factor, bottleneck_ratio,
"".join([str(x) for x in num_shuffle_units]))
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=28,
require_flatten=include_top,
data_format=K.image_data_format())
out_dim_stage_two = {0.5: 48, 1: 116, 1.5: 176, 2: 244}
if pooling not in ['max', 'avg', None]:
raise ValueError('Invalid value for pooling')
if not (float(scale_factor) * 4).is_integer():
raise ValueError('Invalid value for scale_factor, should be x over 4')
exp = np.insert(np.arange(len(num_shuffle_units), dtype=np.float32), 0,
0) # [0., 0., 1., 2.]
out_channels_in_stage = 2**exp
out_channels_in_stage *= out_dim_stage_two[
bottleneck_ratio] # calculate output channels for each stage
out_channels_in_stage[0] = 24 # first stage has always 24 output channels
out_channels_in_stage *= scale_factor
out_channels_in_stage = out_channels_in_stage.astype(int)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
#if not K.is_keras_tensor(input_tensor):
#img_input = Input(tensor=input_tensor, shape=input_shape)
#else:
#img_input = input_tensor
img_input = input_tensor
# create shufflenet architecture
x = Conv2D(filters=out_channels_in_stage[0],
kernel_size=(3, 3),
padding='same',
use_bias=False,
strides=(2, 2),
activation='relu',
name='conv1')(img_input)
x = MaxPool2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='maxpool1')(x)
# create stages containing shufflenet units beginning at stage 2
for stage in range(len(num_shuffle_units)):
repeat = num_shuffle_units[stage]
x = block(x,
out_channels_in_stage,
repeat=repeat,
bottleneck_ratio=bottleneck_ratio,
stage=stage + 2)
if bottleneck_ratio < 2:
k = 1024
else:
k = 2048
x = Conv2D(k,
kernel_size=1,
padding='same',
strides=1,
name='1x1conv5_out',
activation='relu')(x)
if include_top:
x = GlobalAveragePooling2D(name='global_avg_pool')(x)
x = Dense(classes, activation='softmax', use_bias=True,
name='Logits')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='global_avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='global_max_pool')(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=name)
# Load weights.
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
raise ValueError('Weights for "channels_first" format '
'are not available.')
if include_top:
model_name = ('shufflenet_v2_weights_tf_dim_ordering_tf_kernels_' +
str(alpha) + '_' + str(rows) + '.h5')
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name,
weigh_path,
cache_subdir='models')
else:
model_name = ('shufflenet_v2_weights_tf_dim_ordering_tf_kernels_' +
str(alpha) + '_' + str(rows) + '_no_top' + '.h5')
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name,
weigh_path,
cache_subdir='models')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
