def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
**kwargs):
"""Instantiates the Inception-ResNet v2 architecture.
Reference:
- [Inception-v4, Inception-ResNet and the Impact of
Residual Connections on Learning](https://arxiv.org/abs/1602.07261)
(AAAI 2017)
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: each Keras Application expects a specific kind of input preprocessing.
For InceptionResNetV2, call
`tf.keras.applications.inception_resnet_v2.preprocess_input`
on your inputs before passing them to the model.
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 75.
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
global layers
if 'layers' in kwargs:
layers = kwargs.pop('layers')
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
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
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = layers.MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = layers.MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = layers.AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if backend.image_data_format() == 'channels_first' else 3
x = layers.Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='inception_resnet_v2')
# Load weights.
if weights == 'imagenet':
if include_top:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = data_utils.get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
fname = ('inception_resnet_v2_weights_'
'tf_dim_ordering_tf_kernels_notop.h5')
weights_path = data_utils.get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def Xception(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
):
"""Instantiates the Xception architecture.
Reference:
- [Xception: Deep Learning with Depthwise Separable Convolutions](
https://arxiv.org/abs/1610.02357) (CVPR 2017)
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
The default input image size for this model is 299x299.
Note: each Keras Application expects a specific kind of input preprocessing.
For Xception, call `tf.keras.applications.xception.preprocess_input` on your
inputs before passing them to the model.
`xception.preprocess_input` will scale input pixels between -1 and 1.
Args:
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
Returns:
A `keras.Model` instance.
"""
if not (weights in {"imagenet", None} or tf.io.gfile.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 = imagenet_utils.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), 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), 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)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(
classes, activation=classifier_activation, 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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name="xception")
# Load weights.
if weights == "imagenet":
if include_top:
weights_path = data_utils.get_file(
"xception_weights_tf_dim_ordering_tf_kernels.h5",
TF_WEIGHTS_PATH,
cache_subdir="models",
file_hash="0a58e3b7378bc2990ea3b43d5981f1f6",
)
else:
weights_path = data_utils.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)
elif weights is not None:
model.load_weights(weights)
return model
def NASNet(input_shape=None,
penultimate_filters=4032,
num_blocks=6,
stem_block_filters=96,
skip_reduction=True,
filter_multiplier=2,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000,
default_size=None,
classifier_activation='softmax'):
"""Instantiates a NASNet model.
Reference:
- [Learning Transferable Architectures for Scalable Image Recognition](
https://arxiv.org/abs/1707.07012) (CVPR 2018)
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
Note: each Keras Application expects a specific kind of input preprocessing.
For NasNet, call `tf.keras.applications.nasnet.preprocess_input`
on your inputs before passing them to the model.
`nasnet.preprocess_input` will scale input pixels between -1 and 1.
Args:
input_shape: Optional shape tuple, the input shape
is by default `(331, 331, 3)` for NASNetLarge and
`(224, 224, 3)` for NASNetMobile.
It should have exactly 3 input channels,
and width and height should be no smaller than 32.
E.g. `(224, 224, 3)` would be one valid value.
penultimate_filters: Number of filters in the penultimate layer.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
num_blocks: Number of repeated blocks of the NASNet model.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
stem_block_filters: Number of filters in the initial stem block
skip_reduction: Whether to skip the reduction step at the tail
end of the network.
filter_multiplier: Controls the width of the network.
- If `filter_multiplier` < 1.0, proportionally decreases the number
of filters in each layer.
- If `filter_multiplier` > 1.0, proportionally increases the number
of filters in each layer.
- If `filter_multiplier` = 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: `None` (random initialization) or
`imagenet` (ImageNet weights)
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.
default_size: Specifies the default image size of the model
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
Returns:
A `keras.Model` instance.
"""
if not (weights in {'imagenet', None} or tf.io.gfile.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')
if (isinstance(input_shape, tuple) and None in input_shape and
weights == 'imagenet'):
raise ValueError('When specifying the input shape of a NASNet'
' and loading `ImageNet` weights, '
'the input_shape argument must be static '
'(no None entries). Got: `input_shape=' +
str(input_shape) + '`.')
if default_size is None:
default_size = 331
# Determine proper input shape and default size.
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=default_size,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=True,
weights=weights)
if backend.image_data_format() != 'channels_last':
logging.warning('The NASNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
backend.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
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
if penultimate_filters % (24 * (filter_multiplier**2)) != 0:
raise ValueError(
'For NASNet-A models, the `penultimate_filters` must be a multiple '
'of 24 * (`filter_multiplier` ** 2). Current value: %d' %
penultimate_filters)
channel_dim = 1 if backend.image_data_format() == 'channels_first' else -1
filters = penultimate_filters // 24
x = layers.Conv2D(
stem_block_filters, (3, 3),
strides=(2, 2),
padding='valid',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal')(
img_input)
x = layers.BatchNormalization(
axis=channel_dim, momentum=0.9997, epsilon=1e-3, name='stem_bn1')(
x)
p = None
x, p = _reduction_a_cell(
x, p, filters // (filter_multiplier**2), block_id='stem_1')
x, p = _reduction_a_cell(
x, p, filters // filter_multiplier, block_id='stem_2')
for i in range(num_blocks):
x, p = _normal_a_cell(x, p, filters, block_id='%d' % (i))
x, p0 = _reduction_a_cell(
x, p, filters * filter_multiplier, block_id='reduce_%d' % (num_blocks))
p = p0 if not skip_reduction else p
for i in range(num_blocks):
x, p = _normal_a_cell(
x, p, filters * filter_multiplier, block_id='%d' % (num_blocks + i + 1))
x, p0 = _reduction_a_cell(
x,
p,
filters * filter_multiplier**2,
block_id='reduce_%d' % (2 * num_blocks))
p = p0 if not skip_reduction else p
for i in range(num_blocks):
x, p = _normal_a_cell(
x,
p,
filters * filter_multiplier**2,
block_id='%d' % (2 * num_blocks + i + 1))
x = layers.Activation('relu')(x)
if include_top:
x = layers.GlobalAveragePooling2D()(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes, activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
model = training.Model(inputs, x, name='NASNet')
# Load weights.
if weights == 'imagenet':
if default_size == 224: # mobile version
if include_top:
weights_path = data_utils.get_file(
'nasnet_mobile.h5',
NASNET_MOBILE_WEIGHT_PATH,
cache_subdir='models',
file_hash='020fb642bf7360b370c678b08e0adf61')
else:
weights_path = data_utils.get_file(
'nasnet_mobile_no_top.h5',
NASNET_MOBILE_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1ed92395b5b598bdda52abe5c0dbfd63')
model.load_weights(weights_path)
elif default_size == 331: # large version
if include_top:
weights_path = data_utils.get_file(
'nasnet_large.h5',
NASNET_LARGE_WEIGHT_PATH,
cache_subdir='models',
file_hash='11577c9a518f0070763c2b964a382f17')
else:
weights_path = data_utils.get_file(
'nasnet_large_no_top.h5',
NASNET_LARGE_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='d81d89dc07e6e56530c4e77faddd61b5')
model.load_weights(weights_path)
else:
raise ValueError('ImageNet weights can only be loaded with NASNetLarge'
' or NASNetMobile')
elif weights is not None:
model.load_weights(weights)
if old_data_format:
backend.set_image_data_format(old_data_format)
return model
def MobileNet(
input_shape=None,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights="imagenet",
input_tensor=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
**kwargs,
):
"""Instantiates the MobileNet architecture.
Reference:
- [MobileNets: Efficient Convolutional Neural Networks
for Mobile Vision Applications](
https://arxiv.org/abs/1704.04861)
This function returns a Keras image classification model,
optionally loaded with weights pre-trained on ImageNet.
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
Note: each Keras Application expects a specific kind of input preprocessing.
For MobileNet, call `tf.keras.applications.mobilenet.preprocess_input`
on your inputs before passing them to the model.
`mobilenet.preprocess_input` will scale input pixels between -1 and 1.
Args:
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. Default to `None`.
`input_shape` will be ignored if the `input_tensor` is provided.
alpha: Controls the width of the network. This is known as the width
multiplier in the MobileNet 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. Default to 1.0.
depth_multiplier: Depth multiplier for depthwise convolution. This is
called the resolution multiplier in the MobileNet paper. Default to 1.0.
dropout: Dropout rate. Default to 0.001.
include_top: Boolean, whether to include the fully-connected layer at the
top of the network. Default to `True`.
weights: One of `None` (random initialization), 'imagenet' (pre-training
on ImageNet), or the path to the weights file to be loaded. Default to
`imagenet`.
input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to
use as image input for the model. `input_tensor` is useful for sharing
inputs between multiple different networks. Default to None.
pooling: Optional pooling mode for feature extraction when `include_top`
is `False`.
- `None` (default) 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. Defaults to 1000.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
"""
global layers
if "layers" in kwargs:
layers = kwargs.pop("layers")
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError(f"Unknown argument(s): {(kwargs,)}")
if not (weights in {"imagenet", None} or tf.io.gfile.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. "
f"Received weights={weights}"
)
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. "
f"Received classes={classes}"
)
# Determine proper input shape and default size.
if input_shape is None:
default_size = 224
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 [128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
input_shape = imagenet_utils.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 depth_multiplier != 1:
raise ValueError(
"If imagenet weights are being loaded, "
"depth multiplier must be 1. "
f"Received depth_multiplier={depth_multiplier}"
)
if alpha not in [0.25, 0.50, 0.75, 1.0]:
raise ValueError(
"If imagenet weights are being loaded, "
"alpha can be one of"
"`0.25`, `0.50`, `0.75` or `1.0` only. "
f"Received alpha={alpha}"
)
if rows != cols or rows not in [128, 160, 192, 224]:
rows = 224
logging.warning(
"`input_shape` is undefined or non-square, "
"or `rows` is not in [128, 160, 192, 224]. "
"Weights for input shape (224, 224) will be "
"loaded as the default."
)
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
x = _conv_block(img_input, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)
x = _depthwise_conv_block(
x, 128, alpha, depth_multiplier, strides=(2, 2), block_id=2
)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)
x = _depthwise_conv_block(
x, 256, alpha, depth_multiplier, strides=(2, 2), block_id=4
)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(
x, 512, alpha, depth_multiplier, strides=(2, 2), block_id=6
)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)
x = _depthwise_conv_block(
x, 1024, alpha, depth_multiplier, strides=(2, 2), block_id=12
)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)
if include_top:
x = layers.GlobalAveragePooling2D(keepdims=True)(x)
x = layers.Dropout(dropout, name="dropout")(x)
x = layers.Conv2D(classes, (1, 1), padding="same", name="conv_preds")(x)
x = layers.Reshape((classes,), name="reshape_2")(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Activation(
activation=classifier_activation, 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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name="mobilenet_%0.2f_%s" % (alpha, rows))
# Load weights.
if weights == "imagenet":
if alpha == 1.0:
alpha_text = "1_0"
elif alpha == 0.75:
alpha_text = "7_5"
elif alpha == 0.50:
alpha_text = "5_0"
else:
alpha_text = "2_5"
if include_top:
model_name = "mobilenet_%s_%d_tf.h5" % (alpha_text, rows)
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = data_utils.get_file(
model_name, weight_path, cache_subdir="models"
)
else:
model_name = "mobilenet_%s_%d_tf_no_top.h5" % (alpha_text, rows)
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = data_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 xception(stack_fn,
model_name='alignedxception',
include_top=True,
weights=None,
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
**kwargs):
""" Generator for Xception models.
This function generates a family of Xception models. See the Xception*() methods for specific model instantiations,
obtained by selecting different block instantiations that produce Xception of various depths.
Args:
stack_fn: a function that returns output tensor for the stacked blocks.
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) 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, channels)` with `channels_last` data format
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.
classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless
`include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
"""
global layers
if 'layers' in kwargs:
layers = kwargs.pop('layers')
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights is None or file_io.file_exists(weights)):
raise ValueError(
'The `weights` argument should be `None` (random initialization) or the path to the weights '
'file to be loaded. Pre-trained weights are unavailable')
# Determine proper input shape
input_shape = imagenet_utils.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 = conv2d_same(img_input, 32, 3, stride=2, name='entry_flow/conv1_1')
x = layers.BatchNormalization(axis=channel_axis,
name='entry_flow/conv1_1_bn')(x)
x = layers.ReLU(name='entry_flow/conv1_1_relu')(x)
x = conv2d_same(x, 64, 3, stride=1, name='entry_flow/conv1_2')
x = layers.BatchNormalization(axis=channel_axis,
name='entry_flow/conv1_2_bn')(x)
x = layers.ReLU(name='entry_flow/conv1_2_relu')(x)
x = stack_fn(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dropout(0.5)(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name=model_name)
# Load weights.
if weights is not None:
model.load_weights(weights)
return model
def ResNetRS(
depth: int,
input_shape=None,
bn_momentum=0.0,
bn_epsilon=1e-5,
activation: str = "relu",
se_ratio=0.25,
dropout_rate=0.25,
drop_connect_rate=0.2,
include_top=True,
block_args: List[Dict[str, int]] = None,
model_name="resnet-rs",
pooling=None,
weights="imagenet",
input_tensor=None,
classes=1000,
classifier_activation: Union[str, Callable] = "softmax",
include_preprocessing=True,
):
"""Build Resnet-RS model, given provided parameters.
Args:
depth: Depth of ResNet network.
input_shape: optional shape tuple. 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.
bn_momentum: Momentum parameter for Batch Normalization layers.
bn_epsilon: Epsilon parameter for Batch Normalization layers.
activation: activation function.
se_ratio: Squeeze and Excitation layer ratio.
dropout_rate: dropout rate before final classifier layer.
drop_connect_rate: dropout rate at skip connections.
include_top: whether to include the fully-connected layer at the top of
the network.
block_args: list of dicts, parameters to construct block modules.
model_name: name of 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 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.
weights: one of `None` (random initialization), `'imagenet'`
(pre-training on ImageNet), or the path to the weights file to be
loaded. Note- one model can have multiple imagenet variants depending
on input shape it was trained with. For input_shape 224x224 pass
`imagenet-i224` as argument. By default, highest input shape weights
are downloaded.
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.
classifier_activation: A `str` or callable. The activation function to
use on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
include_preprocessing: Boolean, whether to include the preprocessing
layer (`Rescaling`) at the bottom of the network. Defaults to `True`.
Note- Input image is normalized by ImageNet mean and standard
deviation.
Returns:
A `tf.keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`, or invalid input
shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
# Validate parameters
available_weight_variants = DEPTH_TO_WEIGHT_VARIANTS[depth]
if weights == "imagenet":
max_input_shape = max(available_weight_variants)
# `imagenet` argument without explicit weights input size.
# Picking weights trained with biggest available shape
weights = f"{weights}-i{max_input_shape}"
weights_allow_list = [f"imagenet-i{x}" for x in available_weight_variants]
if not (weights in {*weights_allow_list, None}
or tf.io.gfile.exists(weights)):
raise ValueError(
"The `weights` argument should be either "
"`None` (random initialization), `'imagenet'` "
"(pre-training on ImageNet, with highest available input shape),"
" or the path to the weights file to be loaded. "
f"For ResNetRS{depth} the following weight variants are "
f"available {weights_allow_list} (default=highest)."
f" Received weights={weights}")
if weights in weights_allow_list and include_top and classes != 1000:
raise ValueError(
f"If using `weights` as `'imagenet'` or any "
f"of {weights_allow_list} "
f"with `include_top` as true, `classes` should be 1000. "
f"Received classes={classes}")
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights,
)
# Define input tensor
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 = img_input
if include_preprocessing:
num_channels = input_shape[bn_axis - 1]
x = layers.Rescaling(scale=1.0 / 255)(x)
if num_channels == 3:
x = layers.Normalization(
mean=[0.485, 0.456, 0.406],
variance=[0.229**2, 0.224**2, 0.225**2],
axis=bn_axis,
)(x)
# Build stem
x = STEM(bn_momentum=bn_momentum,
bn_epsilon=bn_epsilon,
activation=activation)(x)
# Build blocks
if block_args is None:
block_args = BLOCK_ARGS[depth]
for i, args in enumerate(block_args):
survival_probability = get_survival_probability(
init_rate=drop_connect_rate,
block_num=i + 2,
total_blocks=len(block_args) + 1,
)
x = BlockGroup(
filters=args["input_filters"],
activation=activation,
strides=(1 if i == 0 else 2),
num_repeats=args["num_repeats"],
se_ratio=se_ratio,
bn_momentum=bn_momentum,
bn_epsilon=bn_epsilon,
survival_probability=survival_probability,
name=f"BlockGroup{i + 2}_",
)(x)
# Build head:
if include_top:
x = layers.GlobalAveragePooling2D(name="avg_pool")(x)
if dropout_rate > 0:
x = layers.Dropout(dropout_rate, name="top_dropout")(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name="predictions")(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name=model_name)
# Download weights
if weights in weights_allow_list:
weights_input_shape = weights.split("-")[-1] # e. g. "i160"
weights_name = f"{model_name}-{weights_input_shape}"
if not include_top:
weights_name += "_notop"
filename = f"{weights_name}.h5"
download_url = BASE_WEIGHTS_URL + filename
weights_path = data_utils.get_file(
fname=filename,
origin=download_url,
cache_subdir="models",
file_hash=WEIGHT_HASHES[filename],
)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
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,
classifier_activation='softmax'):
if not (weights in {'imagenet', None} or tf.io.gfile.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(
layer_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 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]
input_shape = (3, cols, rows)
else:
rows = backend.int_shape(input_tensor)[1]
cols = backend.int_shape(input_tensor)[2]
input_shape = (cols, rows, 3)
# 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 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 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 (not minimalistic and alpha not in [0.75, 1.0]
or minimalistic 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:
logging.warning('`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 = 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
if minimalistic:
kernel = 3
activation = relu
se_ratio = None
else:
kernel = 5
activation = hard_swish
se_ratio = 0.25
x = img_input
x = layers.Rescaling(scale=1. / 127.5, offset=-1.)(x)
x = layers.Conv2D(16,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name='Conv')(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='Conv/BatchNorm')(x)
x = activation(x)
x = stack_fn(x, kernel, activation, se_ratio)
last_conv_ch = _depth(backend.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 = layers.Conv2D(last_conv_ch,
kernel_size=1,
padding='same',
use_bias=False,
name='Conv_1')(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='Conv_1/BatchNorm')(x)
x = activation(x)
x = layers.Conv2D(last_point_ch,
kernel_size=1,
padding='same',
use_bias=True,
name='Conv_2')(x)
x = activation(x)
if include_top:
x = layers.GlobalAveragePooling2D()(x)
if channel_axis == 1:
x = layers.Reshape((last_point_ch, 1, 1))(x)
else:
x = layers.Reshape((1, 1, last_point_ch))(x)
if dropout_rate > 0:
x = layers.Dropout(dropout_rate)(x)
x = layers.Conv2D(classes,
kernel_size=1,
padding='same',
name='Logits')(x)
x = layers.Flatten()(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Activation(activation=classifier_activation,
name='Predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.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 = data_utils.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
def EfficientNet(
width_coefficient,
depth_coefficient,
default_size,
dropout_rate=0.2,
drop_connect_rate=0.2,
depth_divisor=8,
activation='swish',
blocks_args='default',
model_name='efficientnet',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the EfficientNet architecture using given scaling coefficients.
Args:
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: 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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if blocks_args == 'default':
blocks_args = DEFAULT_BLOCKS_ARGS
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.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 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
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 = layers.Rescaling(1. / 255.)(x)
x = layers.Normalization(axis=bn_axis)(x)
x = layers.ZeroPadding2D(
padding=imagenet_utils.correct_pad(x, 3),
name='stem_conv_pad')(x)
x = layers.Conv2D(
round_filters(32),
3,
strides=2,
padding='valid',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER,
name='stem_conv')(x)
x = layers.BatchNormalization(axis=bn_axis, name='stem_bn')(x)
x = layers.Activation(activation, name='stem_activation')(x)
# Build blocks
blocks_args = copy.deepcopy(blocks_args)
b = 0
blocks = float(sum(round_repeats(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,
drop_connect_rate * b / blocks,
name='block{}{}_'.format(i + 1, chr(j + 97)),
**args)
b += 1
# Build top
x = layers.Conv2D(
round_filters(1280),
1,
padding='same',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER,
name='top_conv')(x)
x = layers.BatchNormalization(axis=bn_axis, name='top_bn')(x)
x = layers.Activation(activation, name='top_activation')(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
if dropout_rate > 0:
x = layers.Dropout(dropout_rate, name='top_dropout')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(
classes,
activation=classifier_activation,
kernel_initializer=DENSE_KERNEL_INITIALIZER,
name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name=model_name)
# Load weights.
if weights == 'imagenet':
if include_top:
file_suffix = '.h5'
file_hash = WEIGHTS_HASHES[model_name[-2:]][0]
else:
file_suffix = '_notop.h5'
file_hash = WEIGHTS_HASHES[model_name[-2:]][1]
file_name = model_name + file_suffix
weights_path = data_utils.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 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,
classifier_activation="softmax",
include_preprocessing=True,
):
if not (weights in {"imagenet", None} or tf.io.gfile.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. "
f"Received weights={weights}")
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. "
f"Received classes={classes}")
# 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(
layer_utils.get_source_inputs(input_tensor))
except ValueError:
raise ValueError(
"input_tensor: ",
input_tensor,
"is not type input_tensor. "
f"Received type(input_tensor)={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(
"When backend.image_data_format()=channels_first, "
"input_shape[1] must equal "
"backend.int_shape(input_tensor)[1]. Received "
f"input_shape={input_shape}, "
"backend.int_shape(input_tensor)="
f"{backend.int_shape(input_tensor)}")
else:
if backend.int_shape(input_tensor)[2] != input_shape[1]:
raise ValueError(
"input_shape[1] must equal "
"backend.int_shape(input_tensor)[2]. Received "
f"input_shape={input_shape}, "
"backend.int_shape(input_tensor)="
f"{backend.int_shape(input_tensor)}")
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 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]
input_shape = (3, cols, rows)
else:
rows = backend.int_shape(input_tensor)[1]
cols = backend.int_shape(input_tensor)[2]
input_shape = (cols, rows, 3)
# If input_shape is None and input_tensor is None using standard shape
if input_shape is None and input_tensor is None:
input_shape = (None, None, 3)
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 rows and cols and (rows < 32 or cols < 32):
raise ValueError(
"Input size must be at least 32x32; Received `input_shape="
f"{input_shape}`")
if weights == "imagenet":
if (not minimalistic and alpha not in [0.75, 1.0]
or minimalistic 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:
logging.warning("`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 = 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
if minimalistic:
kernel = 3
activation = relu
se_ratio = None
else:
kernel = 5
activation = hard_swish
se_ratio = 0.25
x = img_input
if include_preprocessing:
x = layers.Rescaling(scale=1.0 / 127.5, offset=-1.0)(x)
x = layers.Conv2D(
16,
kernel_size=3,
strides=(2, 2),
padding="same",
use_bias=False,
name="Conv",
)(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name="Conv/BatchNorm")(x)
x = activation(x)
x = stack_fn(x, kernel, activation, se_ratio)
last_conv_ch = _depth(backend.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 = layers.Conv2D(
last_conv_ch,
kernel_size=1,
padding="same",
use_bias=False,
name="Conv_1",
)(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name="Conv_1/BatchNorm")(x)
x = activation(x)
if include_top:
x = layers.GlobalAveragePooling2D(keepdims=True)(x)
x = layers.Conv2D(
last_point_ch,
kernel_size=1,
padding="same",
use_bias=True,
name="Conv_2",
)(x)
x = activation(x)
if dropout_rate > 0:
x = layers.Dropout(dropout_rate)(x)
x = layers.Conv2D(classes,
kernel_size=1,
padding="same",
name="Logits")(x)
x = layers.Flatten()(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Activation(activation=classifier_activation,
name="Predictions")(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.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_v2.h5"
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.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
def InceptionResNetV2(include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
**kwargs):
"""Instantiates the Inception-ResNet v2 architecture.
Reference:
- [Inception-v4, Inception-ResNet and the Impact of
Residual Connections on Learning](https://arxiv.org/abs/1602.07261)
(AAAI 2017)
This function returns a Keras image classification model,
optionally loaded with weights pre-trained on ImageNet.
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
Note: each Keras Application expects a specific kind of input preprocessing.
For InceptionResNetV2, call
`tf.keras.applications.inception_resnet_v2.preprocess_input`
on your inputs before passing them to the model.
`inception_resnet_v2.preprocess_input`
will scale input pixels between -1 and 1.
Args:
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 75.
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
"""
global layers
if "layers" in kwargs:
layers = kwargs.pop("layers")
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError("Unknown argument(s): %s" % (kwargs, ))
if not (weights in {"imagenet", None} or tf.io.gfile.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 = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
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
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding="valid")
x = conv2d_bn(x, 32, 3, padding="valid")
x = conv2d_bn(x, 64, 3)
x = layers.MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding="valid")
x = conv2d_bn(x, 192, 3, padding="valid")
x = layers.MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = layers.AveragePooling2D(3, strides=1, padding="same")(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if backend.image_data_format() == "channels_first" else 3
x = layers.Concatenate(axis=channel_axis, name="mixed_5b")(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type="block35",
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding="valid")
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding="valid")
branch_pool = layers.MaxPooling2D(3, strides=2, padding="valid")(x)
branches = [branch_0, branch_1, branch_pool]
x = layers.Concatenate(axis=channel_axis, name="mixed_6a")(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type="block17",
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding="valid")
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding="valid")
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding="valid")
branch_pool = layers.MaxPooling2D(3, strides=2, padding="valid")(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = layers.Concatenate(axis=channel_axis, name="mixed_7a")(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type="block8",
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.0,
activation=None,
block_type="block8",
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name="conv_7b")
if include_top:
# Classification block
x = layers.GlobalAveragePooling2D(name="avg_pool")(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name="inception_resnet_v2")
# Load weights.
if weights == "imagenet":
if include_top:
fname = "inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5"
weights_path = data_utils.get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir="models",
file_hash="e693bd0210a403b3192acc6073ad2e96",
)
else:
fname = ("inception_resnet_v2_weights_"
"tf_dim_ordering_tf_kernels_notop.h5")
weights_path = data_utils.get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir="models",
file_hash="d19885ff4a710c122648d3b5c3b684e4",
)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def MobileNet(input_shape=None,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
**kwargs):
"""Instantiates the MobileNet architecture.
Reference:
- [MobileNets: Efficient Convolutional Neural Networks
for Mobile Vision Applications](
https://arxiv.org/abs/1704.04861)
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in the `tf.keras.backend.image_data_format()`.
Note: each Keras Application expects a specific kind of input preprocessing.
For MobileNet, call `tf.keras.applications.mobilenet.preprocess_input`
on your inputs before passing them to the model.
Args:
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. Default to `None`.
`input_shape` will be ignored if the `input_tensor` is provided.
alpha: Controls the width of the network. This is known as the width
multiplier in the MobileNet 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. Default to 1.0.
depth_multiplier: Depth multiplier for depthwise convolution. This is
called the resolution multiplier in the MobileNet paper. Default to 1.0.
dropout: Dropout rate. Default to 0.001.
include_top: Boolean, whether to include the fully-connected layer at the
top of the network. Default to `True`.
weights: One of `None` (random initialization), 'imagenet' (pre-training
on ImageNet), or the path to the weights file to be loaded. Default to
`imagenet`.
input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to
use as image input for the model. `input_tensor` is useful for sharing
inputs between multiple different networks. Default to None.
pooling: Optional pooling mode for feature extraction when `include_top`
is `False`.
- `None` (default) 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. Defaults to 1000.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
global layers
if 'layers' in kwargs:
layers = kwargs.pop('layers')
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or tf.io.gfile.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 input_shape is None:
default_size = 224
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 [128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
input_shape = imagenet_utils.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 depth_multiplier != 1:
raise ValueError('If imagenet weights are being loaded, '
'depth multiplier must be 1')
if alpha not in [0.25, 0.50, 0.75, 1.0]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of'
'`0.25`, `0.50`, `0.75` or `1.0` only.')
if rows != cols or rows not in [128, 160, 192, 224]:
rows = 224
logging.warning('`input_shape` is undefined or non-square, '
'or `rows` is not in [128, 160, 192, 224]. '
'Weights for input shape (224, 224) will be'
' loaded as the default.')
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
x = _conv_block(img_input, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)
x = _depthwise_conv_block(x,
128,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=2)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)
x = _depthwise_conv_block(x,
256,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=4)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(x,
512,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=6)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)
x = _depthwise_conv_block(x,
1024,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=12)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)
if include_top:
if backend.image_data_format() == 'channels_first':
shape = (int(1024 * alpha), 1, 1)
else:
shape = (1, 1, int(1024 * alpha))
x = layers.GlobalAveragePooling2D()(x)
x = layers.Reshape(shape, name='reshape_1')(x)
x = layers.Dropout(dropout, name='dropout')(x)
x = layers.Conv2D(classes, (1, 1), padding='same',
name='conv_preds')(x)
x = layers.Reshape((classes, ), name='reshape_2')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Activation(activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs,
x,
name='mobilenet_%0.2f_%s' % (alpha, rows))
# Load weights.
if weights == 'imagenet':
if alpha == 1.0:
alpha_text = '1_0'
elif alpha == 0.75:
alpha_text = '7_5'
elif alpha == 0.50:
alpha_text = '5_0'
else:
alpha_text = '2_5'
if include_top:
model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = data_utils.get_file(model_name,
weight_path,
cache_subdir='models')
else:
model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = data_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 BiT(model_name,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
**kwargs):
"""Instantiates the BiT-ResNet architecture.
Reference:
- [Big Transfer (BiT): General Visual Representation Learning](
https://arxiv.org/abs/1912.11370)
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:
model_name: string, model name.
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.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
global layers
if 'layers' in kwargs:
layers = kwargs.pop('layers')
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or file_io.file_exists_v2(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.')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=False,
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
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = [img_input]
# Create base model.
outputs = ResnetV2(img_input,
num_units=NUM_UNITS[model_name],
num_outputs=21843 if '-M-' in model_name else 1000,
filters_factor=int(model_name[-1]) * 4)
full_model = training.Model(inputs=inputs,
outputs=outputs,
name=model_name)
# Load weights.
if 'imagenet' == weights and model_name in WEIGHTS_HASHES:
file_name = model_name + '.h5'
file_hash = WEIGHTS_HASHES[model_name]
weights_path = data_utils.get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
full_model.load_weights(weights_path)
elif weights is not None:
full_model.load_weights(weights)
# Create model.
if include_top:
return full_model
outputs = full_model.get_layer(name='head_relu').output
model = training.Model(inputs=inputs, outputs=outputs, name=model_name)
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,
classifier_activation="softmax",
**kwargs
):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Args:
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
"""
global layers
if "layers" in kwargs:
layers = kwargs.pop("layers")
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError("Unknown argument(s): %s" % (kwargs,))
if not (weights in {"imagenet", None} or tf.io.gfile.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 = imagenet_utils.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")(x)
if not preact:
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:
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)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(
classes, activation=classifier_activation, name="predictions"
)(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.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 = data_utils.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 VGG16(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the VGG16 model.
Reference:
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](
https://arxiv.org/abs/1409.1556) (ICLR 2015)
By default, it loads weights pre-trained on ImageNet. Check 'weights' for
other options.
This model can be built both with 'channels_first' data format
(channels, height, width) or 'channels_last' data format
(height, width, channels).
The default input size for this model is 224x224.
Note: each Keras Application expects a specific kind of input preprocessing.
For VGG16, call `tf.keras.applications.vgg16.preprocess_input` on your
inputs before passing them to the model.
Args:
include_top: whether to include the 3 fully-connected
layers 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 input 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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.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
# Block 1
x = layers.Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = layers.Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = layers.Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = layers.Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = layers.Dense(4096, activation='relu', name='fc1')(x)
x = layers.Dense(4096, activation='relu', name='fc2')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='vgg16')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='64373286793e3c8b2b4e3219cbf3544b')
else:
weights_path = data_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='6d6bbae143d832006294945121d1f1fc')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the DenseNet architecture.
Reference:
- [Densely Connected Convolutional Networks](
https://arxiv.org/abs/1608.06993) (CVPR 2017)
This function returns a Keras image classification model,
optionally loaded with weights pre-trained on ImageNet.
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
Note: each Keras Application expects a specific kind of input preprocessing.
For DenseNet, call `tf.keras.applications.densenet.preprocess_input` on your
inputs before passing them to the model.
`densenet.preprocess_input` will scale pixels between 0 and 1 and then
will normalize each channel with respect to the ImageNet dataset statistics.
Args:
blocks: numbers of building blocks for the four dense layers.
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
Returns:
A `keras.Model` instance.
"""
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.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)))(img_input)
x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
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)))(x)
x = layers.MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
x = layers.Activation('relu', name='relu')(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = training.Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = training.Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = training.Model(inputs, x, name='densenet201')
else:
model = training.Model(inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = data_utils.get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='9d60b8095a5708f2dcce2bca79d332c7')
elif blocks == [6, 12, 32, 32]:
weights_path = data_utils.get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='d699b8f76981ab1b30698df4c175e90b')
elif blocks == [6, 12, 48, 32]:
weights_path = data_utils.get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='1ceb130c1ea1b78c3bf6114dbdfd8807')
else:
if blocks == [6, 12, 24, 16]:
weights_path = data_utils.get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='30ee3e1110167f948a6b9946edeeb738')
elif blocks == [6, 12, 32, 32]:
weights_path = data_utils.get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='b8c4d4c20dd625c148057b9ff1c1176b')
elif blocks == [6, 12, 48, 32]:
weights_path = data_utils.get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='c13680b51ded0fb44dff2d8f86ac8bb1')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def Deeplabv3(weights='pascal_voc', input_tensor=None, input_shape=(512, 512, 3), classes=21, backbone='mobilenetv2',
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('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('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(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 = K.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('relu')(b4)
# upsample. have to use compat because of the option align_corners
size_before = K.int_shape(x)
b4 = Lambda(lambda x: tf.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('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)
x = BatchNormalization(name='concat_projection_BN', epsilon=1e-5)(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
# DeepLab v.3+ decoder
if backbone == 'xception':
# Feature projection
# x4 (x2) block
size_before2 = K.int_shape(x)
x = Lambda(lambda xx: tf.image.resize(xx,
skip1.shape[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('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)
# you can use it with arbitary number of classes
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'
x = Conv2D(classes, (1, 1), padding='same', name=last_layer_name)(x)
size_before3 = K.int_shape(img_input)
x = Lambda(lambda xx: tf.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 = 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',
WEIGHTS_PATH_MOBILE_CS,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model
def Xception(
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the Xception architecture.
Reference:
- [Xception: Deep Learning with Depthwise Separable Convolutions](
https://arxiv.org/abs/1610.02357) (CVPR 2017)
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.
Note: each Keras Application expects a specific kind of input preprocessing.
For Xception, call `tf.keras.applications.xception.preprocess_input` on your
inputs before passing them to the model.
Args:
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.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),
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), 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)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes, activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='xception')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models',
file_hash='0a58e3b7378bc2990ea3b43d5981f1f6')
else:
weights_path = data_utils.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)
elif weights is not None:
model.load_weights(weights)
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,
classifier_activation='softmax',
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Reference:
- [Deep Residual Learning for Image Recognition](
https://arxiv.org/abs/1512.03385) (CVPR 2015)
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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
global layers
if 'layers' in kwargs:
layers = kwargs.pop('layers')
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.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')(x)
if not preact:
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:
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)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.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 = data_utils.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 EfficientNetV2(
width_coefficient,
depth_coefficient,
default_size,
dropout_rate=0.2,
drop_connect_rate=0.2,
depth_divisor=8,
min_depth=8,
bn_momentum=0.9,
activation="swish",
blocks_args="default",
model_name="efficientnetv2",
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
):
"""Instantiates the EfficientNetV2 architecture using given scaling coefficients.
Args:
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.
min_depth: integer, minimum number of filters.
bn_momentum: float. Momentum parameter for Batch Normalization layers.
activation: 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()`) or
numpy array 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.
classifier_activation: A string or callable. The activation function to use
on the `"top"` layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the `"top"` layer.
include_preprocessing: Boolean, whether to include the preprocessing layer
(`Rescaling`) at the bottom of the network. Defaults to `True`.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `"softmax"` or `None` when
using a pretrained top layer.
"""
if blocks_args == "default":
blocks_args = DEFAULT_BLOCKS_ARGS[model_name]
if not (weights in {"imagenet", None} or tf.io.gfile.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."
f"Received: weights={weights}")
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"
f"Received: classes={classes}")
# Determine proper input shape
input_shape = imagenet_utils.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 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 = img_input
if include_preprocessing:
# Apply original V1 preprocessing for Bx variants
# if number of channels allows it
num_channels = input_shape[bn_axis - 1]
if model_name.split("-")[-1].startswith("b") and num_channels == 3:
x = layers.Rescaling(scale=1. / 255)(x)
x = layers.Normalization(
mean=[0.485, 0.456, 0.406],
variance=[0.229**2, 0.224**2, 0.225**2],
axis=bn_axis,
)(x)
else:
x = layers.Rescaling(scale=1. / 128.0, offset=-1)(x)
# Build stem
stem_filters = round_filters(
filters=blocks_args[0]["input_filters"],
width_coefficient=width_coefficient,
min_depth=min_depth,
depth_divisor=depth_divisor,
)
x = layers.Conv2D(
filters=stem_filters,
kernel_size=3,
strides=2,
kernel_initializer=CONV_KERNEL_INITIALIZER,
padding="same",
use_bias=False,
name="stem_conv",
)(x)
x = layers.BatchNormalization(
axis=bn_axis,
momentum=bn_momentum,
name="stem_bn",
)(x)
x = layers.Activation(activation, name="stem_activation")(x)
# Build blocks
blocks_args = copy.deepcopy(blocks_args)
b = 0
blocks = float(sum(args["num_repeat"] for args in blocks_args))
for (i, args) in enumerate(blocks_args):
assert args["num_repeat"] > 0
# Update block input and output filters based on depth multiplier.
args["input_filters"] = round_filters(
filters=args["input_filters"],
width_coefficient=width_coefficient,
min_depth=min_depth,
depth_divisor=depth_divisor)
args["output_filters"] = round_filters(
filters=args["output_filters"],
width_coefficient=width_coefficient,
min_depth=min_depth,
depth_divisor=depth_divisor)
# Determine which conv type to use:
block = {0: MBConvBlock, 1: FusedMBConvBlock}[args.pop("conv_type")]
repeats = round_repeats(repeats=args.pop("num_repeat"),
depth_coefficient=depth_coefficient)
for j in range(repeats):
# The first block needs to take care of stride and filter size increase.
if j > 0:
args["strides"] = 1
args["input_filters"] = args["output_filters"]
x = block(
activation=activation,
bn_momentum=bn_momentum,
survival_probability=drop_connect_rate * b / blocks,
name="block{}{}_".format(i + 1, chr(j + 97)),
**args,
)(x)
b += 1
# Build top
top_filters = round_filters(filters=1280,
width_coefficient=width_coefficient,
min_depth=min_depth,
depth_divisor=depth_divisor)
x = layers.Conv2D(
filters=top_filters,
kernel_size=1,
strides=1,
kernel_initializer=CONV_KERNEL_INITIALIZER,
padding="same",
data_format="channels_last",
use_bias=False,
name="top_conv",
)(x)
x = layers.BatchNormalization(
axis=bn_axis,
momentum=bn_momentum,
name="top_bn",
)(x)
x = layers.Activation(activation=activation, name="top_activation")(x)
if include_top:
x = layers.GlobalAveragePooling2D(name="avg_pool")(x)
if dropout_rate > 0:
x = layers.Dropout(dropout_rate, name="top_dropout")(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
kernel_initializer=DENSE_KERNEL_INITIALIZER,
bias_initializer=tf.constant_initializer(0),
name="predictions")(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name=model_name)
# Load weights.
if weights == "imagenet":
if include_top:
file_suffix = ".h5"
file_hash = WEIGHTS_HASHES[model_name[-2:]][0]
else:
file_suffix = "_notop.h5"
file_hash = WEIGHTS_HASHES[model_name[-2:]][1]
file_name = model_name + file_suffix
weights_path = data_utils.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 InceptionV3(
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the Inception v3 architecture.
Reference:
- [Rethinking the Inception Architecture for Computer Vision](
http://arxiv.org/abs/1512.00567) (CVPR 2016)
This function returns a Keras image classification model,
optionally loaded with weights pre-trained on ImageNet.
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
Note: each Keras Application expects a specific kind of input preprocessing.
For `InceptionV3`, call `tf.keras.applications.inception_v3.preprocess_input`
on your inputs before passing them to the model.
`inception_v3.preprocess_input` will scale input pixels between -1 and 1.
Args:
include_top: Boolean, whether to include the fully-connected
layer at the top, as the last layer of the network. Default to `True`.
weights: One of `None` (random initialization),
`imagenet` (pre-training on ImageNet),
or the path to the weights file to be loaded. Default to `imagenet`.
input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model. `input_tensor` is useful for sharing
inputs between multiple different networks. Default to None.
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 75.
E.g. `(150, 150, 3)` would be one valid value.
`input_shape` will be ignored if the `input_tensor` is provided.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` (default) 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. Default to 1000.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
Returns:
A `keras.Model` instance.
"""
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
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
if backend.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0: 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 = layers.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 288
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 = layers.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 288
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 = layers.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='valid')
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='valid')
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(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 = layers.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 = layers.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 = layers.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='valid')
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='valid')
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(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 = layers.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 = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes, activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='inception_v3')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = data_utils.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 add(self, layer):
"""Adds a layer instance on top of the layer stack.
Args:
layer: layer instance.
Raises:
TypeError: If `layer` is not a layer instance.
ValueError: In case the `layer` argument does not
know its input shape.
ValueError: In case the `layer` argument has
multiple output tensors, or is already connected
somewhere else (forbidden in `Sequential` models).
"""
# If we are passed a Keras tensor created by keras.Input(), we can extract
# the input layer from its keras history and use that without any loss of
# generality.
if hasattr(layer, '_keras_history'):
origin_layer = layer._keras_history[0]
if isinstance(origin_layer, input_layer.InputLayer):
layer = origin_layer
logging.warning(
'Please add `keras.layers.InputLayer` instead of `keras.Input` to '
'Sequential model. `keras.Input` is intended to be used by '
'Functional model.')
if isinstance(layer, tf.Module):
if not isinstance(layer, base_layer.Layer):
layer = functional.ModuleWrapper(layer)
else:
raise TypeError('The added layer must be '
'an instance of class Layer. '
'Found: ' + str(layer))
tf_utils.assert_no_legacy_layers([layer])
if not self._is_layer_name_unique(layer):
raise ValueError('All layers added to a Sequential model '
'should have unique names. Name "%s" is already the name'
' of a layer in this model. Update the `name` argument '
'to pass a unique name.' % (layer.name,))
self.built = False
set_inputs = False
self._maybe_create_attribute('_self_tracked_trackables', [])
if not self._self_tracked_trackables:
if isinstance(layer, input_layer.InputLayer):
# Case where the user passes an Input or InputLayer layer via `add`.
set_inputs = True
else:
batch_shape, dtype = training_utils.get_input_shape_and_dtype(layer)
if batch_shape:
# Instantiate an input layer.
x = input_layer.Input(
batch_shape=batch_shape, dtype=dtype, name=layer.name + '_input')
# This will build the current layer
# and create the node connecting the current layer
# to the input layer we just created.
layer(x)
set_inputs = True
if set_inputs:
outputs = tf.nest.flatten(layer._inbound_nodes[-1].outputs)
if len(outputs) != 1:
raise ValueError(SINGLE_LAYER_OUTPUT_ERROR_MSG)
self.outputs = outputs
self.inputs = layer_utils.get_source_inputs(self.outputs[0])
self.built = True
self._has_explicit_input_shape = True
elif self.outputs:
# If the model is being built continuously on top of an input layer:
# refresh its output.
output_tensor = layer(self.outputs[0])
if len(tf.nest.flatten(output_tensor)) != 1:
raise ValueError(SINGLE_LAYER_OUTPUT_ERROR_MSG)
self.outputs = [output_tensor]
self.built = True
if set_inputs or self._graph_initialized:
self._init_graph_network(self.inputs, self.outputs)
self._graph_initialized = True
else:
self._self_tracked_trackables.append(layer)
self._handle_deferred_layer_dependencies([layer])
self._layer_call_argspecs[layer] = tf_inspect.getfullargspec(layer.call)
def MobileNetV2(input_shape=None,
alpha=1.0,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
**kwargs):
"""Instantiates the MobileNetV2 architecture.
Reference:
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](
https://arxiv.org/abs/1801.04381) (CVPR 2018)
Optionally loads weights pre-trained on ImageNet.
Note: each Keras Application expects a specific kind of input preprocessing.
For MobileNetV2, call `tf.keras.applications.mobilenet_v2.preprocess_input`
on your inputs before passing them to the model.
Args:
input_shape: Optional shape tuple, to be specified if you would
like to use a model with an input image 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: Float between 0 and 1. 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 `applications.MobileNetV1`
model 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: Boolean, whether to include the fully-connected
layer at the top of the network. Defaults to `True`.
weights: String, 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: String, 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: Integer, optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
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'
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
global layers
if 'layers' in kwargs:
layers = kwargs.pop('layers')
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or tf.io.gfile.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(
layer_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 = imagenet_utils.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
logging.warning('`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.Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name='Conv1')(img_input)
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)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.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 = data_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 = data_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 VGG19(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the VGG19 architecture.
Reference:
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](
https://arxiv.org/abs/1409.1556) (ICLR 2015)
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
The default input size for this model is 224x224.
Note: each Keras Application expects a specific kind of input preprocessing.
For VGG19, call `tf.keras.applications.vgg19.preprocess_input` on your
inputs before passing them to the model.
`vgg19.preprocess_input` will convert the input images from RGB to BGR,
then will zero-center each color channel with respect to the ImageNet dataset,
without scaling.
Args:
include_top: whether to include the 3 fully-connected
layers 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.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
Returns:
A `keras.Model` instance.
"""
if not (weights in {'imagenet', None} or tf.io.gfile.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 = imagenet_utils.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
# Block 1
x = layers.Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = layers.Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = layers.Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = layers.Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = layers.Dense(4096, activation='relu', name='fc1')(x)
x = layers.Dense(4096, activation='relu', name='fc2')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='vgg19')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='cbe5617147190e668d6c5d5026f83318')
else:
weights_path = data_utils.get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='253f8cb515780f3b799900260a226db6')
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,
classifier_activation="softmax",
**kwargs,
):
"""Instantiates the MobileNetV2 architecture.
MobileNetV2 is very similar to the original MobileNet,
except that it uses inverted residual blocks with
bottlenecking features. It has a drastically lower
parameter count than the original MobileNet.
MobileNets support any input size greater
than 32 x 32, with larger image sizes
offering better performance.
Reference:
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](
https://arxiv.org/abs/1801.04381) (CVPR 2018)
This function returns a Keras image classification model,
optionally loaded with weights pre-trained on ImageNet.
For image classification use cases, see
[this page for detailed examples](
https://keras.io/api/applications/#usage-examples-for-image-classification-models).
For transfer learning use cases, make sure to read the
[guide to transfer learning & fine-tuning](
https://keras.io/guides/transfer_learning/).
Note: each Keras Application expects a specific kind of input preprocessing.
For MobileNetV2, call `tf.keras.applications.mobilenet_v2.preprocess_input`
on your inputs before passing them to the model.
`mobilenet_v2.preprocess_input` will scale input pixels between -1 and 1.
Args:
input_shape: Optional shape tuple, to be specified if you would
like to use a model with an input image 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: Float, larger than zero, 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 `applications.MobileNetV1` model 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` = 1.0, default number of filters from the paper
are used at each layer.
include_top: Boolean, whether to include the fully-connected layer at the
top of the network. Defaults to `True`.
weights: String, 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: String, 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 integer number of classes to classify images into, only
to be specified if `include_top` is True, and if no `weights` argument
is specified.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
When loading pretrained weights, `classifier_activation` can only
be `None` or `"softmax"`.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
"""
global layers
if "layers" in kwargs:
layers = kwargs.pop("layers")
else:
layers = VersionAwareLayers()
if kwargs:
raise ValueError(f"Unknown argument(s): {kwargs}")
if not (weights in {"imagenet", None} or tf.io.gfile.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. "
f"Received `weights={weights}`")
if weights == "imagenet" and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top` '
f"as true, `classes` should be 1000. Received `classes={classes}`")
# 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(
layer_utils.get_source_inputs(input_tensor))
except ValueError:
raise ValueError(
f"input_tensor: {input_tensor}"
"is not type input_tensor. "
f"Received `type(input_tensor)={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[1] must equal shape(input_tensor)[1] "
"when `image_data_format` is `channels_first`; "
"Received `input_tensor.shape="
f"{input_tensor.shape}`"
f", `input_shape={input_shape}`")
else:
if backend.int_shape(input_tensor)[2] != input_shape[1]:
raise ValueError(
"input_tensor.shape[2] must equal input_shape[1]; "
"Received `input_tensor.shape="
f"{input_tensor.shape}`, "
f"`input_shape={input_shape}`")
else:
raise ValueError("input_tensor is not a Keras tensor; "
f"Received `input_tensor={input_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 must be a valid Keras tensor type; "
f"Received {input_tensor} of type {type(input_tensor)}")
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 = imagenet_utils.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 must be one of `0.35`, `0.50`, `0.75`, "
"`1.0`, `1.3` or `1.4` only;"
f" Received `alpha={alpha}`")
if rows != cols or rows not in [96, 128, 160, 192, 224]:
rows = 224
logging.warning("`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.Conv2D(
first_block_filters,
kernel_size=3,
strides=(2, 2),
padding="same",
use_bias=False,
name="Conv1",
)(img_input)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name="bn_Conv1")(x)
x = layers.ReLU(6.0, 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(6.0, name="out_relu")(x)
if include_top:
x = layers.GlobalAveragePooling2D()(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.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(float(alpha)) + "_" + str(rows) + ".h5")
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = data_utils.get_file(model_name,
weight_path,
cache_subdir="models")
else:
model_name = ("mobilenet_v2_weights_tf_dim_ordering_tf_kernels_" +
str(float(alpha)) + "_" + str(rows) + "_no_top" +
".h5")
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = data_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
