def build_model(self):
# Build stem
x = self.img_input
x = layers.Rescaling(1. / 255.)(x)
x = layers.Normalization(axis=self.bn_axis)(x)
x = tf.keras.layers.ZeroPadding2D(padding=imagenet_utils.correct_pad(
x, 3),
name='stem_conv_pad')(x)
x = tf.keras.layers.Conv2D(self.round_filters(32),
3,
strides=2,
padding='valid',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER,
name='stem_conv')(x)
x = build_normalization(**self.normalization, name='stem_bn')(x)
x = build_activation(**self.activation, name='stem_activation')(x)
block_outputs = [x]
# Build blocks
blocks_args = copy.deepcopy(self.blocks_args)
b = 0
blocks = float(sum(args['repeats'] for args in blocks_args))
output_stages = [1, 2, 4, 6]
for (i, args) in enumerate(blocks_args):
assert args['repeats'] > 0
# Update block input and output filters based on depth multiplier.
args['filters_in'] = self.round_filters(args['filters_in'])
args['filters_out'] = self.round_filters(args['filters_out'])
strides = args["strides"]
for j in range(self.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 = self.block(x,
self.activation,
self.drop_connect_rate * b / blocks,
name='block{}{}_'.format(i + 1, chr(j + 97)),
**args)
b += 1
if i in output_stages:
block_outputs.append(x)
# Build top
x = tf.keras.layers.Conv2D(self.round_filters(1280),
1,
padding='same',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER,
name='top_conv')(x)
x = build_normalization(**self.normalization, name='top_bn')(x)
x = build_activation(**self.activation, name='top_activation')(x)
if -1 in self.output_indices:
x = tf.keras.layers.GlobalAveragePooling2D(name='avg_pool')(x)
if self.dropout_rate > 0:
x = tf.keras.layers.Dropout(self.dropout_rate,
name='top_dropout')(x)
x = tf.keras.layers.Dense(
1000,
activation=self.classifier_activation,
kernel_initializer=DENSE_KERNEL_INITIALIZER,
name='predictions')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if self.input_tensor is not None:
inputs = tf.keras.utils.get_source_inputs(self.input_tensor)
else:
inputs = self.img_input
# Create model.
return tf.keras.Model(inputs=self.img_input,
outputs=x,
name=model_name)
return [block_outputs[i - 1] for i in self.output_indices]
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):
"""Instantiates the EfficientNet architecture using given scaling coefficients.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Arguments:
width_coefficient: float, scaling coefficient for network width.
depth_coefficient: float, scaling coefficient for network depth.
default_size: integer, default input image size.
dropout_rate: float, dropout rate before final classifier layer.
drop_connect_rate: float, dropout rate at skip connections.
depth_divisor: integer, a unit of network width.
activation: activation function.
blocks_args: list of dicts, parameters to construct block modules.
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False.
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if blocks_args == 'default':
blocks_args = DEFAULT_BLOCKS_ARGS
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = 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(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)
x = layers.Dense(
classes,
activation='softmax',
kernel_initializer=DENSE_KERNEL_INITIALIZER,
name='probs')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = 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 efficientnetB0(width_coeff=1,
depth_coeff=1,
default_img_size=224,
dropoutrate=0.2,
drop_connect_rate=0.2,
depth_divisor=8,
activations='swish',
block_args='default',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
if block_args == 'default':
block_args = DEFAULT_BLOCKS_ARGS
if not (weights in {'imagenet', None} or file_io.file_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')
# proper input shape check
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=default_img_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_coeff
new_filters = max(divisor,
int(filters + divisor / 2) // divisor * divisor)
#making sure round down does not go down by 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_coeff * repeats))
#building 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))(x)
x = layers.Conv2D(round_filters(32),
kernel_size=3,
strides=2,
padding='valid',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER)(x)
x = layers.BatchNormalization(axis=bn_axis)(x)
x = layers.Activation(activations)(x)
#building blocks
block_args = copy.deepcopy(block_args)
b = 0
blocks = float(sum(round_repeats(args['repeats']) for args in block_args))
for (i, args) in enumerate(block_args):
assert args['repeats'] > 0
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 = mbconvblock(inputs=x,
activations=activations,
droprate=drop_connect_rate * b / blocks,
name=str(i),
**args)
b += 1
#build top
x = layers.Conv2D(round_filters(1280),
kernel_size=1,
padding='same',
use_bias=False,
kernel_initializer=CONV_KERNEL_INITIALIZER)(x)
x = layers.BatchNormalization(axis=bn_axis)(x)
x = layers.Activation(activations)(x)
if include_top:
x = layers.GlobalAveragePooling2D()(x)
if dropoutrate > 0:
x = layers.Dropout(dropoutrate)(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
kernel_initializer=DENSE_KERNEL_INITIALIZER)(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
#creating model
model = training.Model(inputs, x)
return model