def instantiate_lenet_fix_weights():
from tensorflow.python import keras
from tensorflow.python.keras import layers
model = keras.Sequential()
model.add(
layers.Conv2D(filters=6,
kernel_size=(3, 3),
activation='relu',
input_shape=(32, 32, 1),
kernel_initializer=MyInitializer(10.0)))
model.add(layers.AveragePooling2D())
model.add(
layers.Conv2D(filters=16,
kernel_size=(3, 3),
activation='relu',
kernel_initializer=MyInitializer(20.0)))
model.add(layers.AveragePooling2D())
model.add(layers.Flatten())
model.add(
layers.Dense(units=120,
activation='relu',
kernel_initializer=MyInitializer(30.0)))
model.add(
layers.Dense(units=84,
activation='relu',
kernel_initializer=MyInitializer(0.4)))
model.add(
layers.Dense(units=10,
activation='softmax',
kernel_initializer=MyInitializer(5.5)))
inp = keras.Input(shape=(32, 32, 1), dtype=np.float32)
out = model(inp)
return out, inp, model
def LeNet5(input_shape, num_classes, pretrained_weights=None):
input_image = layers.Input(shape=input_shape, name='input_1')
x = layers.Conv2D(filters=6,
kernel_size=(3, 3),
activation=activations.relu)(input_image)
x = layers.AveragePooling2D(pool_size=(2, 2))(x)
x = layers.Conv2D(filters=16,
kernel_size=(3, 3),
activation=activations.relu)(x)
x = layers.AveragePooling2D(pool_size=(2, 2))(x)
x = layers.Conv2D(filters=16,
kernel_size=(3, 3),
activation=activations.relu)(x)
x = layers.AveragePooling2D(pool_size=(2, 2))(x)
x = layers.Flatten()(x)
x = layers.Dense(units=120, activation=activations.relu)(x)
x = layers.Dropout(0.5)(x)
x = layers.Dense(units=84, activation=activations.relu)(x)
x = layers.Dense(units=num_classes,
activation=activations.softmax,
name='predictions')(x)
model = models.Model(input_image, x, name='lenet5')
if pretrained_weights:
model.load_weights(pretrained_weights)
return model
def create_models():
input = layers.Input((32, 32, 3))
x = input
for i in range(3):
x = conv_bn_relu(x, 64)
x = layers.AveragePooling2D(2)(x)
for i in range(3):
x = conv_bn_relu(x, 128)
x = layers.AveragePooling2D(2)(x)
for i in range(3):
x = conv_bn_relu(x, 256)
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(10, activation="softmax")(x)
return Model(input, x)
def transition_block(self,
x,
reduction,
name,
weight_decay=1e-4,
kernel_initializer='he_normal'):
"""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 K.image_data_format() == 'channels_last' else 1
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_bn')(x)
x = layers.Activation('relu', name=name + '_relu')(x)
x = layers.Conv2D(int(K.int_shape(x)[bn_axis] * reduction),
1,
use_bias=False,
kernel_initializer=kernel_initializer,
kernel_regularizer=l2(weight_decay),
name=name + '_conv')(x)
x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
return x
def ResNet50(input_tensor=None,
pooling=None,
**kwargs):
"""Instantiates the ResNet50 architecture.
# Arguments
# Returns
A Keras model instance.
"""
# Input arguments
include_top = get_varargin(kwargs, 'include_top', True)
nb_classes = get_varargin(kwargs, 'nb_classes', 1000)
default_input_shape = _obtain_input_shape(None,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top)
input_shape = get_varargin(kwargs, 'input_shape', default_input_shape)
if input_tensor is None:
img_input = KL.Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = KL.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
x = KL.ZeroPadding2D((3, 3))(img_input)
x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = KL.BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = KL.Activation('relu')(x)
x = KL.MaxPooling2D((3, 3), strides=(2, 2))(x)
for stage, nb_block in zip([2,3,4,5], [3,4,6,3]):
for blk in range(nb_block):
conv_block = True if blk == 0 else False
strides = (2,2) if stage>2 and blk==0 else (1,1)
x = identity_block(x, stage = stage, block_id = blk + 1,
conv_block = conv_block, strides = strides)
x = KL.AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = KL.Flatten()(x)
x = KL.Dense(nb_classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = KL.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = KL.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
return model
def small_densenet(self,
img_input_shape=(64, 64, 3),
blocks=[6, 12, 24, 16],
weight_decay=1e-4,
kernel_initializer='he_normal',
init_filters=None,
reduction=None,
growth_rate=None,
init_stride=None):
img_input = layers.Input(shape=(img_input_shape))
x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = layers.Conv2D(init_filters,
3,
strides=init_stride,
use_bias=False,
kernel_initializer=kernel_initializer,
kernel_regularizer=l2(weight_decay),
name='conv1/conv')(x)
x = layers.BatchNormalization(axis=3,
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.AveragePooling2D(3, strides=2, name='pool1')(x)
for i, block in enumerate(blocks):
scope_num_str = str(i + 2)
x = self.dense_block(x,
block,
name='conv' + scope_num_str,
growth_rate=growth_rate,
weight_decay=weight_decay,
kernel_initializer=kernel_initializer)
if i != len(blocks) - 1:
x = self.transition_block(
x,
reduction,
name='pool' + scope_num_str,
weight_decay=weight_decay,
kernel_initializer=kernel_initializer)
x = layers.BatchNormalization(axis=3, epsilon=1.001e-5, name='bn')(x)
x = layers.Activation('relu', name='relu')(x)
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(self.cat_max,
activation='softmax',
kernel_initializer=kernel_initializer,
name='fc')(x)
model = Model(img_input, x)
model.compile(optimizer=Adam(lr=self.lr),
loss='categorical_crossentropy',
metrics=['categorical_accuracy'])
return model
def transition_block(x, name, dropout_rate, reduction=0.5):
x = layers.BatchNormalization(name=name + '_bn')(x)
x = layers.Activation('relu', name=name + '_relu')(x)
x = layers.Conv2D(int(x.get_shape().as_list()[-1] * reduction),
1,
padding='same',
name=name + '_conv')(x)
x = layers.Dropout(rate=dropout_rate)(x)
x = layers.AveragePooling2D(strides=2, name=name + '_pool')(x)
return x
def transition_block(x, reduction, name):
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_bn')(x)
x = layers.Activation('relu', name=name + '_relu')(x)
x = layers.Conv2D(int(backend.int_shape(x)[bn_axis] * reduction),
1,
use_bias=False,
name=name + '_conv')(x)
x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
return x
def average_pool1d(x, kernel_size=2, stride=2, padding='same'):
"""
Args:
x: input_tensor (N, L)
kernel_size: int
stride: int
padding: same
Returns: tensor (N, L//ks)
"""
_x = tf.expand_dims(x, axis=2)
_x = kl.AveragePooling2D((kernel_size, 1), (stride, 1), padding)(_x)
_x = tf.squeeze(_x, axis=2)
return _x
def _forward(self, level, inp, var_scope, is_train):
# Upper branch
up1 = inp
up1 = self._modules['b1_' + str(level)](
up1,
256,
256,
var_scope=var_scope + "_ConvBlock_b1_level_%d" % level,
is_train=is_train)
# Lower branch
low1 = layers.AveragePooling2D(pool_size=(2, 2),
strides=2,
name=var_scope +
'_AvgPool2D_level_%d' % level)(inp)
low1 = self._modules['b2_' + str(level)](
low1,
256,
256,
var_scope=var_scope + "_ConvBlock_b2_level_%d" % level,
is_train=is_train)
if level > 1:
low2 = self._forward(level - 1,
low1,
var_scope=var_scope +
'_forward_level_%d' % level,
is_train=is_train)
else:
low2 = low1
low2 = self._modules['b2_plus_' + str(level)](
low2,
256,
256,
var_scope=var_scope + "_ConvBlock_b2_plus_level_%d" % level,
is_train=is_train)
low3 = low2
low3 = self._modules['b3_' + str(level)](
low3,
256,
256,
var_scope=var_scope + "_ConvBlock_b3_level_%d" % level,
is_train=is_train)
up2 = layers.UpSampling2D(size=(2, 2),
name=var_scope + '_UpSample2D')(low3)
return up1 + up2
def learn_inv_cov(self, var_scope='inv'):
'''
Unary precision matrix (inverse of the covariance matrix)
'''
self.learned_inv_covs = []
self.learned_log_det_inv_covs = []
for i in range(self.num_modules):
h = tf.concat([self.logits[i], self.last_feature[i]], axis=-1)
h = self.conv1_inv(h)
h_32 = layers.AveragePooling2D(pool_size=(2, 2),
strides=2,
name=var_scope + '_AvgPool2D')(h)
h_32 = self.conv2_inv(h_32)
h_8 = layers.MaxPool2D(pool_size=(4, 4),
strides=4,
name=var_scope + '_MaxPool2D')(h_32)
h_8 = tf.transpose(h_8, [0, 3, 1, 2])
h_8 = tf.reshape(h_8,
shape=[tf.shape(h_8)[0], self.FLAGS.num_lmks, 64])
h_8 = self.dense1(h_8)
h_8 = self.dense2(h_8)
h_8 = self.dense3(h_8)
# N C 2 2 chol
h_low = tf.contrib.distributions.fill_triangular(h_8) # lower
h_diag = tf.abs(tf.linalg.diag_part(h_low)) + 0.01
log_h_diag = tf.math.log(h_diag) # diagonal element >0
self.h = tf.linalg.set_diag(h_low, h_diag)
# N C 2 2
learned_inv_cov = tf.matmul(self.h, self.h,
transpose_b=True) # lower*upper
learned_log_det_inv_cov = 2 * tf.reduce_sum(log_h_diag, -1)
self.learned_inv_covs.append(learned_inv_cov)
self.learned_log_det_inv_covs.append(learned_log_det_inv_cov)
return self.learned_inv_covs, self.learned_log_det_inv_covs
def new_transition_layer(self, input_tensor, name):
'''This method build the transition layer to help the forward process with three operations:
BN,
Conv2D,
AveragePooling2D.
'''
filters = input_tensor.shape.as_list()[-1]
x = layers.BatchNormalization(
beta_regularizer=tf.keras.regularizers.l2(1e-4),
gamma_regularizer=tf.keras.regularizers.l2(1e-4),
name=name + '-bn')(input_tensor)
x = layers.ReLU(name=name + '-relu')(x)
x = layers.Conv2D(
filters=int(0.5 * filters),
kernel_size=1,
padding='SAME',
kernel_initializer=tf.keras.initializers.he_uniform(),
kernel_regularizer=tf.keras.regularizers.l2(1e-4),
name=name + '-conv')(x)
x = layers.AveragePooling2D(pool_size=(2, 2),
name=name + '-avg_pool')(x)
return x
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 backend.image_data_format() == 'channels_last' else 1
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_bn')(x)
x = layers.Activation('relu', name=name + '_relu')(x)
x = layers.Conv2D(int(backend.int_shape(x)[bn_axis] * reduction),
1,
use_bias=False,
name=name + '_conv')(x)
x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
return x
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
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_bn')(x)
x = layers.Activation('relu', name=name + '_relu')(x)
x = layers.Conv2D(int(backend.int_shape(x)[bn_axis] * reduction),
1,
use_bias=False,
kernel_regularizer=regularizers.l2(l2_reg),
name=name + '_conv')(x)
conv_before_pool = x
x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
return conv_before_pool, x
def _reduction_a_cell(ip, p, filters, block_id=None):
"""Adds a Reduction cell for NASNet-A (Fig. 4 in the paper).
Arguments:
ip: Input tensor `x`
p: Input tensor `p`
filters: Number of output filters
block_id: String block_id
Returns:
A Keras tensor
"""
channel_dim = 1 if backend.image_data_format() == 'channels_first' else -1
with backend.name_scope('reduction_A_block_%s' % block_id):
p = _adjust_block(p, ip, filters, block_id)
h = layers.Activation('relu')(ip)
h = layers.Conv2D(filters, (1, 1),
strides=(1, 1),
padding='same',
name='reduction_conv_1_%s' % block_id,
use_bias=False,
kernel_initializer='he_normal')(h)
h = layers.BatchNormalization(axis=channel_dim,
momentum=0.9997,
epsilon=1e-3,
name='reduction_bn_1_%s' % block_id)(h)
h3 = layers.ZeroPadding2D(padding=imagenet_utils.correct_pad(h, 3),
name='reduction_pad_1_%s' % block_id)(h)
with backend.name_scope('block_1'):
x1_1 = _separable_conv_block(h,
filters, (5, 5),
strides=(2, 2),
block_id='reduction_left1_%s' %
block_id)
x1_2 = _separable_conv_block(p,
filters, (7, 7),
strides=(2, 2),
block_id='reduction_right1_%s' %
block_id)
x1 = layers.add([x1_1, x1_2], name='reduction_add_1_%s' % block_id)
with backend.name_scope('block_2'):
x2_1 = layers.MaxPooling2D(
(3, 3),
strides=(2, 2),
padding='valid',
name='reduction_left2_%s' % block_id)(h3)
x2_2 = _separable_conv_block(p,
filters, (7, 7),
strides=(2, 2),
block_id='reduction_right2_%s' %
block_id)
x2 = layers.add([x2_1, x2_2], name='reduction_add_2_%s' % block_id)
with backend.name_scope('block_3'):
x3_1 = layers.AveragePooling2D(
(3, 3),
strides=(2, 2),
padding='valid',
name='reduction_left3_%s' % block_id)(h3)
x3_2 = _separable_conv_block(p,
filters, (5, 5),
strides=(2, 2),
block_id='reduction_right3_%s' %
block_id)
x3 = layers.add([x3_1, x3_2], name='reduction_add3_%s' % block_id)
with backend.name_scope('block_4'):
x4 = layers.AveragePooling2D(
(3, 3),
strides=(1, 1),
padding='same',
name='reduction_left4_%s' % block_id)(x1)
x4 = layers.add([x2, x4])
with backend.name_scope('block_5'):
x5_1 = _separable_conv_block(x1,
filters, (3, 3),
block_id='reduction_left4_%s' %
block_id)
x5_2 = layers.MaxPooling2D(
(3, 3),
strides=(2, 2),
padding='valid',
name='reduction_right5_%s' % block_id)(h3)
x5 = layers.add([x5_1, x5_2], name='reduction_add4_%s' % block_id)
x = layers.concatenate([x2, x3, x4, x5],
axis=channel_dim,
name='reduction_concat_%s' % block_id)
return x, ip
def _normal_a_cell(ip, p, filters, block_id=None):
"""Adds a Normal cell for NASNet-A (Fig. 4 in the paper).
Arguments:
ip: Input tensor `x`
p: Input tensor `p`
filters: Number of output filters
block_id: String block_id
Returns:
A Keras tensor
"""
channel_dim = 1 if backend.image_data_format() == 'channels_first' else -1
with backend.name_scope('normal_A_block_%s' % block_id):
p = _adjust_block(p, ip, filters, block_id)
h = layers.Activation('relu')(ip)
h = layers.Conv2D(filters, (1, 1),
strides=(1, 1),
padding='same',
name='normal_conv_1_%s' % block_id,
use_bias=False,
kernel_initializer='he_normal')(h)
h = layers.BatchNormalization(axis=channel_dim,
momentum=0.9997,
epsilon=1e-3,
name='normal_bn_1_%s' % block_id)(h)
with backend.name_scope('block_1'):
x1_1 = _separable_conv_block(h,
filters,
kernel_size=(5, 5),
block_id='normal_left1_%s' % block_id)
x1_2 = _separable_conv_block(p,
filters,
block_id='normal_right1_%s' %
block_id)
x1 = layers.add([x1_1, x1_2], name='normal_add_1_%s' % block_id)
with backend.name_scope('block_2'):
x2_1 = _separable_conv_block(p,
filters, (5, 5),
block_id='normal_left2_%s' % block_id)
x2_2 = _separable_conv_block(p,
filters, (3, 3),
block_id='normal_right2_%s' %
block_id)
x2 = layers.add([x2_1, x2_2], name='normal_add_2_%s' % block_id)
with backend.name_scope('block_3'):
x3 = layers.AveragePooling2D(
(3, 3),
strides=(1, 1),
padding='same',
name='normal_left3_%s' % (block_id))(h)
x3 = layers.add([x3, p], name='normal_add_3_%s' % block_id)
with backend.name_scope('block_4'):
x4_1 = layers.AveragePooling2D(
(3, 3),
strides=(1, 1),
padding='same',
name='normal_left4_%s' % (block_id))(p)
x4_2 = layers.AveragePooling2D(
(3, 3),
strides=(1, 1),
padding='same',
name='normal_right4_%s' % (block_id))(p)
x4 = layers.add([x4_1, x4_2], name='normal_add_4_%s' % block_id)
with backend.name_scope('block_5'):
x5 = _separable_conv_block(h,
filters,
block_id='normal_left5_%s' % block_id)
x5 = layers.add([x5, h], name='normal_add_5_%s' % block_id)
x = layers.concatenate([p, x1, x2, x3, x4, x5],
axis=channel_dim,
name='normal_concat_%s' % block_id)
return x, ip
def _adjust_block(p, ip, filters, block_id=None):
"""Adjusts the input `previous path` to match the shape of the `input`.
Used in situations where the output number of filters needs to be changed.
Arguments:
p: Input tensor which needs to be modified
ip: Input tensor whose shape needs to be matched
filters: Number of output filters to be matched
block_id: String block_id
Returns:
Adjusted Keras tensor
"""
channel_dim = 1 if backend.image_data_format() == 'channels_first' else -1
img_dim = 2 if backend.image_data_format() == 'channels_first' else -2
ip_shape = backend.int_shape(ip)
if p is not None:
p_shape = backend.int_shape(p)
with backend.name_scope('adjust_block'):
if p is None:
p = ip
elif p_shape[img_dim] != ip_shape[img_dim]:
with backend.name_scope('adjust_reduction_block_%s' % block_id):
p = layers.Activation('relu',
name='adjust_relu_1_%s' % block_id)(p)
p1 = layers.AveragePooling2D(
(1, 1),
strides=(2, 2),
padding='valid',
name='adjust_avg_pool_1_%s' % block_id)(p)
p1 = layers.Conv2D(filters // 2, (1, 1),
padding='same',
use_bias=False,
name='adjust_conv_1_%s' % block_id,
kernel_initializer='he_normal')(p1)
p2 = layers.ZeroPadding2D(padding=((0, 1), (0, 1)))(p)
p2 = layers.Cropping2D(cropping=((1, 0), (1, 0)))(p2)
p2 = layers.AveragePooling2D(
(1, 1),
strides=(2, 2),
padding='valid',
name='adjust_avg_pool_2_%s' % block_id)(p2)
p2 = layers.Conv2D(filters // 2, (1, 1),
padding='same',
use_bias=False,
name='adjust_conv_2_%s' % block_id,
kernel_initializer='he_normal')(p2)
p = layers.concatenate([p1, p2], axis=channel_dim)
p = layers.BatchNormalization(axis=channel_dim,
momentum=0.9997,
epsilon=1e-3,
name='adjust_bn_%s' %
block_id)(p)
elif p_shape[channel_dim] != filters:
with backend.name_scope('adjust_projection_block_%s' % block_id):
p = layers.Activation('relu')(p)
p = layers.Conv2D(filters, (1, 1),
strides=(1, 1),
padding='same',
name='adjust_conv_projection_%s' % block_id,
use_bias=False,
kernel_initializer='he_normal')(p)
p = layers.BatchNormalization(axis=channel_dim,
momentum=0.9997,
epsilon=1e-3,
name='adjust_bn_%s' %
block_id)(p)
return p
def block2(x,
filters,
kernel_size=3,
stride=1,
groups=1,
base_width=64,
radix=1,
is_first=True,
conv_shortcut=True,
name=None):
"""A residual block.
Arguments:
x: input tensor.
filters: integer, filters of the bottleneck layer.
kernel_size: default 3, kernel size of the bottleneck layer.
stride: default 1, stride of the first layer.
groups: default 1, group size for grouped convolution.
base_width: default 64, filters of the intermediate layer.
radix: default 1, splits for split attention layer.
is_first: default True, when to use pooling layer.
conv_shortcut: default True, use convolution shortcut if True,
otherwise identity shortcut.
name: string, block label.
Returns:
Output tensor for the residual block.
"""
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
width = int(filters * (base_width / 64.)) * groups
expansion = 4
old_stride = stride
if stride > 1 or is_first:
stride = 1
if conv_shortcut:
shortcut = layers.AveragePooling2D(
pool_size=stride, strides=old_stride, name=name + '_0_pool')(x)
shortcut = layers.Conv2D(
filters * expansion,
1,
strides=1,
use_bias=False,
name=name + '_0_conv')(shortcut)
shortcut = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name=name + '_0_bn')(shortcut)
else:
shortcut = x
x = layers.Conv2D(width, 1, use_bias=False, name=name + '_1_conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name=name + '_1_bn')(x)
x = layers.Activation('relu', name=name + '_1_relu')(x)
x = SplitAttentionConv2D(
x,
width,
kernel_size=kernel_size,
stride=stride,
padding=(1, 1),
groups=groups,
radix=radix,
use_bias=False,
name=name + '_2_conv')
if stride > 1 or is_first:
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name=name + '_0_pad')(x)
x = layers.AveragePooling2D(
pool_size=kernel_size, strides=old_stride, name=name + '_1_pool')(x)
x = layers.Conv2D(
filters * expansion, 1, use_bias=False, name=name + '_3_conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name=name + '_3_bn')(x)
x = layers.Add(name=name + '_add')([shortcut, x])
x = layers.Activation('relu', name=name + '_out')(x)
return x
return (x_train, y_train), (x_test, y_test)
# Define model architecture
lenet5 = Sequential()
lenet5.add(
layers.Conv2D(6,
kernel_size=(5, 5),
strides=(1, 1),
activation="tanh",
input_shape=(28, 28, 1),
padding="same"))
lenet5.add(
layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding="valid"))
lenet5.add(
layers.Conv2D(16,
kernel_size=(5, 5),
strides=(1, 1),
activation="tanh",
padding="valid"))
lenet5.add(
layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding="valid"))
lenet5.add(layers.Flatten())
lenet5.add(layers.Dense(units=120, activation="tanh"))
lenet5.add(layers.Dense(84, activation="tanh"))
lenet5.add(layers.Dense(10, activation="softmax"))
# Compile model
def create_network(
Zt,
Ct,
channels=1,
upscaling_filters=[512, 256, 256, 128, 64],
upscaling_ks=[5, 5, 5, 5, 5],
upscaling_strides=[2, 2, 2, 2, 2, 1],
encoder_filters=[64, 128, 256],
encoder_ks=[3, 3, 3],
resblock_filters=[256, 256, 256, 256, 256],
resblock_ks=[3, 3, 3, 3, 3, 3],
decoder_filters=[256, 256, 128, 64],
decoder_ks=[5, 5, 5, 5, 5],
):
with tf.name_scope("Gen"):
Z = kl.Input((
None,
None,
channels,
), tensor=Zt, name="Z")
C = kl.Input((
None,
None,
channels,
), tensor=Ct, name="C")
layer = Z
# Upscaling
for l in range(len(upscaling_filters)):
layer = kl.Conv2DTranspose(filters=upscaling_filters[l],
kernel_size=upscaling_ks[l],
padding="same",
strides=upscaling_strides[l],
kernel_regularizer=kr.l2(),
activation="relu")(layer)
layer = kl.BatchNormalization()(layer)
layer = kl.Conv2DTranspose(filters=channels,
kernel_size=upscaling_ks[-1],
padding="same",
strides=1,
activation="relu",
kernel_regularizer=kr.l2())(layer)
layer = kl.concatenate([layer, C])
# Encoder
skips = [C]
for l in range(len(encoder_filters)):
layer = kl.Conv2D(
filters=encoder_filters[l],
kernel_size=encoder_ks[l],
padding="same",
activation="relu",
# strides=2,
kernel_regularizer=kr.l2())(layer)
layer = kl.AveragePooling2D()(layer)
layer = kl.BatchNormalization()(layer)
skips.append(layer)
# Residual blocks
for l in range(len(resblock_filters)):
layer = ResidualBlock(resblock_filters[l],
nb_layers=3,
kernel_size=resblock_ks[l])(layer)
# Decoder
layer = kl.Conv2DTranspose(filters=decoder_filters[0],
kernel_size=decoder_ks[0],
padding="same",
strides=2,
kernel_regularizer=kr.l2(),
activation="relu")(layer)
layer = kl.BatchNormalization()(layer)
skips = skips[::-1]
for l in range(1, len(decoder_filters)):
layer = kl.concatenate([layer, skips[l]])
layer = kl.Conv2DTranspose(filters=decoder_filters[l],
kernel_size=decoder_ks[l],
padding="same",
strides=2,
kernel_regularizer=kr.l2(),
activation="relu")(layer)
layer = kl.BatchNormalization()(layer)
G_out = kl.Conv2D(filters=channels,
kernel_size=5,
activation="tanh",
padding="same",
kernel_regularizer=kr.l2())(layer)
model = k.Model(inputs=[Z, C], outputs=G_out, name="G")
return model
image = x[i]
label = y[i].argmax()
print(classnames[label])
plt.imshow(image)
plt.show()
"""# Create the first model"""
from tensorflow.python.keras import layers
from tensorflow.python.keras import Sequential
model = Sequential()
#convolutional base
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=train_generator.image_shape))
model.add(layers.AveragePooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.AveragePooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
#dense layers
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(train_generator.num_classes, activation='softmax'))
model.summary()
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
"""# Train the model"""
def InceptionResNetV2(input_shape=None):
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
data_format=backend.image_data_format(),
require_flatten=True)
img_input = layers.Input(shape=input_shape)
# 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')
# Classification block
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation('softmax', None)
x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x)
# Create model.
model = training.Model(img_input, x, name='inception_resnet_v2')
return model
def forward(self, x, is_train=True):
'''
Forward pass through FAN network
'''
x = activations.relu(
self.bn1(self.conv1(x),
training=is_train,
name='FAN_begin_bn1',
trainable=True))
with tf.compat.v1.variable_scope("FAN_start"):
x = layers.AveragePooling2D(pool_size=(2, 2),
strides=2,
name='AvgPool2D_layer1')(ConvBlock(
x,
64,
128,
var_scope="ConvBlock_layer1",
is_train=is_train))
x = ConvBlock(x,
128,
128,
var_scope="ConvBlock_layer2",
is_train=is_train)
x = ConvBlock(x,
128,
256,
var_scope="ConvBlock_layer3",
is_train=is_train)
previous = x
outputs = []
self.last_feature = []
for i in range(self.num_modules):
hg = self._modules['m' + str(i)].forward(previous,
var_scope='HG_%d' % i,
is_train=is_train)
ll = hg
ll = self._modules['top_m_' + str(i)](
ll,
256,
256,
var_scope="ConvBlock_top_m_HG_%d" % i,
is_train=is_train)
ll = activations.relu(self._modules['bn_end' + str(i)](
self._modules['conv_last' + str(i)](ll),
training=is_train,
name='bn_end_HG_%d' % i,
trainable=True))
# Predict heatmaps
# tmp_out, output of each stage
tmp_out = self._modules['l' + str(i)](ll)
outputs.append(tmp_out)
self.last_feature.append(ll)
if i < self.num_modules - 1:
# form previous, input to the next HG stage
ll = self._modules['bl' + str(i)](ll)
tmp_out_ = self._modules['al' + str(i)](tmp_out)
previous = previous + ll + tmp_out_
self.logits = outputs
return outputs
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.
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`.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.inception_resnet_v2.preprocess_input` for an example.
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.
"""
if 'layers' in kwargs:
global layers
layers = kwargs.pop('layers')
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs,))
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = 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 assemble_layers(self):
from tensorflow.python.keras import backend, layers
from tensorflow.python.keras.applications import imagenet_utils
include_top = True
weights = None
pooling = None
classes = 1
if nnstate.FLAGS.PRED_SIZE != 2:
err('bad')
classifier_activation = 'sigmoid'
x = conv2d_bn(self.inputs, 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)
return x
def InceptionV3(input_shape=None):
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
data_format=backend.image_data_format(),
require_flatten=True)
img_input = layers.Input(shape=input_shape)
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))
# Classification block
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation('softmax', None)
x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x)
# Create model.
model = training.Model(img_input, x, name='inception_v3')
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 paper:
- [Rethinking the Inception Architecture for Computer Vision](
http://arxiv.org/abs/1512.00567) (CVPR 2016)
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()`.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.inception_v3.preprocess_input` for an example.
Arguments:
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.
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 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=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 DashNet(input_tensor=None,
input_shape=None,
pooling='avg',
classes=2,
classifier_activation='softmax'):
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
# customize model structure
x = conv2d_bn(img_input, 32, 15, 3, strides=(3, 1), padding='valid')
x = conv2d_bn(x, 32, 15, 3, padding='same')
x = conv2d_bn(x, 64, 15, 3, padding='same')
x = layers.MaxPooling2D(pool_size=(15, 3), strides=(5, 1))(x)
x = conv2d_bn(x, 80, 1, 1, padding='same')
x = conv2d_bn(x, 192, 15, 3, padding='same')
x = layers.MaxPooling2D(pool_size=(15, 3), strides=(5, 2))(x)
# mixed 0:
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_avg_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_avg_pool = conv2d_bn(branch_avg_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_avg_pool],
axis=channel_axis,
name='mixed0')
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(x)
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='dashnet')
return model
from tensorflow.python.keras import layers, Sequential
from tensorflow.python.keras.utils import plot_model
model = Sequential()
model.add(
layers.Conv2D(filters=6,
kernel_size=(5, 5),
activation='relu',
input_shape=(32, 32, 1),
strides=(1, 1)))
model.add(layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(
layers.Conv2D(filters=16,
kernel_size=(5, 5),
activation='relu',
strides=(1, 1)))
model.add(layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(units=120, activation='relu'))
model.add(layers.Dense(units=84, activation='relu'))
model.add(layers.Dense(units=10, activation='softmax'))
plot_model(model,
to_file=f'{__file__.split(".py")[0]}.png',
show_layer_names=True,
show_shapes=True)
def average_pool2d(x,
kernel_size=(2, 2),
strides=(2, 2),
padding='same'):
return kl.AveragePooling2D(kernel_size, strides, padding)(x)