2024年3月22日发(作者：巨朝雨)
def transition_block(x, reduction, name):
"""A transition block.
# Arguments
x: input tensor.
reduction: float, compression rate at transition layers.
name: string, block label.
# Returns
output tensor for the block.
"""
bn_axis = 3 if _data_format() == 'channels_last' else 1
x = ormalization(axis=bn_axis, epsilon=1.001e-5,
name=name + '_bn')(x)
x = tion('relu', name=name + '_relu')(x)
x = 2D(int(_shape(x)[bn_axis] * reduction), 1,
use_bias=False,
name=name + '_conv')(x)
x = ePooling2D(2, strides=2, name=name + '_pool')(x)
return x
def conv_block(x, growth_rate, name):
"""A building block for a dense block.
# Arguments
x: input tensor.
growth_rate: float, growth rate at dense layers.
name: string, block label.
# Returns
Output tensor for the block.
"""
bn_axis = 3 if _data_format() == 'channels_last' else 1
x1 = ormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_0_bn')(x)
x1 = tion('relu', name=name + '_0_relu')(x1)
x1 = 2D(4 * growth_rate, 1,
use_bias=False,
name=name + '_1_conv')(x1)
x1 = ormalization(axis=bn_axis, epsilon=1.001e-5,
name=name + '_1_bn')(x1)
x1 = tion('relu', name=name + '_1_relu')(x1)
x1 = 2D(growth_rate, 3,
padding='same',
use_bias=False,
name=name + '_2_conv')(x1)
x = enate(axis=bn_axis, name=name + '_concat')([x, x1])
return x
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/`.
# Arguments
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 `()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or (weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=221,
data_format=_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = (shape=input_shape)
else:
if not _keras_tensor(input_tensor):
img_input = (tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if _data_format() == 'channels_last' else 1
x = dding2D(padding=((3, 3), (3, 3)))(img_input)
x = 2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = ormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = tion('relu', name='conv1/relu')(x)
x = dding2D(padding=((1, 1), (1, 1)))(x)
x = ling2D(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 = ormalization(
axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
if include_top:
x = AveragePooling2D(name='avg_pool')(x)
x = (classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = AveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = MaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = _source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = (inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = (inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = (inputs, x, name='densenet201')
else:
model = (inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = keras__file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = keras__file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = keras__file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = keras__file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = keras__file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='5e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = keras__file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
_weights(weights_path)
elif weights is not None:
_weights(weights)
return model
def DenseNet121(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 24, 16],
include_top, weights,
input_tensor, input_shape,
pooling, classes)
def DenseNet169(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 32, 32],
include_top, weights,
input_tensor, input_shape,
pooling, classes)
def DenseNet201(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
2024年3月22日发(作者：巨朝雨)
def transition_block(x, reduction, name):
"""A transition block.
# Arguments
x: input tensor.
reduction: float, compression rate at transition layers.
name: string, block label.
# Returns
output tensor for the block.
"""
bn_axis = 3 if _data_format() == 'channels_last' else 1
x = ormalization(axis=bn_axis, epsilon=1.001e-5,
name=name + '_bn')(x)
x = tion('relu', name=name + '_relu')(x)
x = 2D(int(_shape(x)[bn_axis] * reduction), 1,
use_bias=False,
name=name + '_conv')(x)
x = ePooling2D(2, strides=2, name=name + '_pool')(x)
return x
def conv_block(x, growth_rate, name):
"""A building block for a dense block.
# Arguments
x: input tensor.
growth_rate: float, growth rate at dense layers.
name: string, block label.
# Returns
Output tensor for the block.
"""
bn_axis = 3 if _data_format() == 'channels_last' else 1
x1 = ormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_0_bn')(x)
x1 = tion('relu', name=name + '_0_relu')(x1)
x1 = 2D(4 * growth_rate, 1,
use_bias=False,
name=name + '_1_conv')(x1)
x1 = ormalization(axis=bn_axis, epsilon=1.001e-5,
name=name + '_1_bn')(x1)
x1 = tion('relu', name=name + '_1_relu')(x1)
x1 = 2D(growth_rate, 3,
padding='same',
use_bias=False,
name=name + '_2_conv')(x1)
x = enate(axis=bn_axis, name=name + '_concat')([x, x1])
return x
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/`.
# Arguments
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 `()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or (weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=221,
data_format=_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = (shape=input_shape)
else:
if not _keras_tensor(input_tensor):
img_input = (tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if _data_format() == 'channels_last' else 1
x = dding2D(padding=((3, 3), (3, 3)))(img_input)
x = 2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = ormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = tion('relu', name='conv1/relu')(x)
x = dding2D(padding=((1, 1), (1, 1)))(x)
x = ling2D(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 = ormalization(
axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
if include_top:
x = AveragePooling2D(name='avg_pool')(x)
x = (classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = AveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = MaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = _source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = (inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = (inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = (inputs, x, name='densenet201')
else:
model = (inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = keras__file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = keras__file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = keras__file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = keras__file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = keras__file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='5e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = keras__file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
_weights(weights_path)
elif weights is not None:
_weights(weights)
return model
def DenseNet121(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 24, 16],
include_top, weights,
input_tensor, input_shape,
pooling, classes)
def DenseNet169(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 32, 32],
include_top, weights,
input_tensor, input_shape,
pooling, classes)
def DenseNet201(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,