def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Conv2D(inter_channel, (1, 1), name=conv_name_base+'_x1', use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Conv2D(nb_filter, (3, 3), name=conv_name_base+'_x2', use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def transition_block3d(x,
stage,
nb_filter,
compression=1.0,
dropout_rate=None,
weight_decay=1E-4):
''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
# Arguments
x: input tensor
stage: index for dense block
nb_filter: number of filters
compression: calculated as 1 - reduction. Reduces the number of feature maps in the transition block.
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = '3dconv' + str(stage) + '_blk'
relu_name_base = '3drelu' + str(stage) + '_blk'
pool_name_base = '3dpool' + str(stage)
x = BatchNormalization(epsilon=eps, axis=4, name=conv_name_base + '_bn')(x)
x = Scale(axis=4, name=conv_name_base + '_scale')(x)
x = Activation('relu', name=relu_name_base)(x)
x = Conv3D(int(nb_filter * compression), (1, 1, 1),
name=conv_name_base,
use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
x = AveragePooling3D((2, 2, 1), strides=(2, 2, 1), name=pool_name_base)(x)
return x
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None):
""" Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
# Arguments
x: input tensor
stage: index for dense block
nb_filter: number of filters
compression: calculated as 1 - reduction. Reduces the number of feature maps in the transition block.
dropout_rate: dropout rate
weight_decay: weight decay factor
"""
eps = 1.1e-5
conv_name_base = 'convolution_' + str(stage) + '_blk'
relu_name_base = 'ReLU_' + str(stage) + '_blk'
pool_name_base = 'pooling_' + str(stage)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
momentum=1,
name=conv_name_base + '_batch_normalization',
trainable=False)(x, training=False)
x = Scale(axis=concat_axis, name=conv_name_base + '_scale')(x)
x = Activation('relu', name=relu_name_base)(x)
x = Conv2D(int(nb_filter * compression), (1, 1),
name=conv_name_base,
use_bias=False,
trainable=True)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)
return x
def conv_block3d(x, stage, branch, nb_filter, dropout_rate=None):
"""Apply BatchNorm, Relu, bottleneck 1x1 Conv3D, 3x3 Conv3D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
"""
eps = 1.1e-5
conv_name_base = '3D_convolution_' + str(stage) + '_' + str(branch)
relu_name_base = '3D_ReLU_' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps,
axis=4,
name=conv_name_base + '_x1_batch_normalization',
momentum=1.0,
trainable=False)(x, training=False)
x = Scale(axis=4, name=conv_name_base + '_x1_scale')(x)
x = Activation('relu', name=relu_name_base + '_x1')(x)
x = Conv3D(inter_channel, (1, 1, 1),
name=conv_name_base + '_x1',
use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
x = BatchNormalization(epsilon=eps,
axis=4,
name=conv_name_base + '_x2_batch_normalization',
momentum=1.0,
trainable=False)(x, training=False)
x = Scale(axis=4, name=conv_name_base + '_x2_scale')(x)
x = Activation('relu', name=relu_name_base + '_x2')(x)
x = ZeroPadding3D((1, 1, 1), name=conv_name_base + '_x2_zero_padding')(x)
x = Conv3D(nb_filter, (3, 3, 3),
name=conv_name_base + '_x2',
use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def DenseUNet(img_input,
nb_dense_block=4,
growth_rate=48,
nb_filter=96,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
classes=1000,
weights_path=None):
'''Instantiate the DenseNet 161 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
'''
eps = 1.1e-5
# compute compression factor
compression = 1.0 - reduction
# Handle Dimension Ordering for different backends
global concat_axis
concat_axis = 3
# From architecture for ImageNet (Table 1 in the paper)
nb_filter = 96
nb_layers = [6, 12, 36, 24] # For DenseNet-161
box = []
# Initial convolution
x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input)
x = Conv2D(nb_filter, (7, 7),
strides=(2, 2),
name='conv1',
use_bias=False,
trainable=False)(x)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
momentum=1,
name='conv1_bn',
trainable=False)(x, training=False)
x = Scale(axis=concat_axis, name='conv1_scale', trainable=False)(x)
x = Activation('relu', name='relu1')(x)
box.append(x)
x = ZeroPadding2D((1, 1), name='pool1_zeropadding')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(x)
# Add dense blocks
for block_idx in range(nb_dense_block - 1):
stage = block_idx + 2
x, nb_filter = dense_block(x,
stage,
nb_layers[block_idx],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
box.append(x)
# Add transition_block
x = transition_block(x,
stage,
nb_filter,
compression=compression,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
final_stage = stage + 1
x, nb_filter = dense_block(x,
final_stage,
nb_layers[-1],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
momentum=1,
name='conv' + str(final_stage) + '_blk_bn',
trainable=False)(x, training=False)
x = Scale(axis=concat_axis,
name='conv' + str(final_stage) + '_blk_scale',
trainable=False)(x)
x = Activation('relu', name='relu' + str(final_stage) + '_blk')(x)
box.append(x)
up0 = UpSampling2D(size=(2, 2))(x)
conv_up0 = Conv2D(768, (3, 3),
padding="same",
name="conv_up0",
trainable=False)(up0)
bn_up0 = BatchNormalization(name="bn_up0", momentum=1,
trainable=False)(conv_up0, training=False)
ac_up0 = Activation('relu', name='ac_up0')(bn_up0)
up1 = UpSampling2D(size=(2, 2))(ac_up0)
conv_up1 = Conv2D(384, (3, 3),
padding="same",
name="conv_up1",
trainable=False)(up1)
bn_up1 = BatchNormalization(name="bn_up1", momentum=1,
trainable=False)(conv_up1, training=False)
ac_up1 = Activation('relu', name='ac_up1')(bn_up1)
up2 = UpSampling2D(size=(2, 2))(ac_up1)
conv_up2 = Conv2D(96, (3, 3),
padding="same",
name="conv_up2",
trainable=False)(up2)
bn_up2 = BatchNormalization(name="bn_up2", momentum=1,
trainable=False)(conv_up2, training=False)
ac_up2 = Activation('relu', name='ac_up2')(bn_up2)
up3 = UpSampling2D(size=(2, 2))(ac_up2)
conv_up3 = Conv2D(96, (3, 3),
padding="same",
name="conv_up3",
trainable=False)(up3)
bn_up3 = BatchNormalization(name="bn_up3", momentum=1,
trainable=False)(conv_up3, training=False)
ac_up3 = Activation('relu', name='ac_up3')(bn_up3)
up4 = UpSampling2D(size=(2, 2))(ac_up3)
conv_up4 = Conv2D(64, (3, 3),
padding="same",
name="conv_up4",
trainable=False)(up4)
bn_up4 = BatchNormalization(name="bn_up4", momentum=1,
trainable=False)(conv_up4, training=False)
ac_up4 = Activation('relu', name='ac_up4')(bn_up4)
x = Conv2D(3, (1, 1),
padding="same",
name='dense167classifer',
trainable=False)(ac_up4)
return ac_up4, x
def DenseNet3D(img_input,
nb_dense_block=4,
growth_rate=32,
nb_filter=96,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
classes=1000,
weights_path=None):
'''Instantiate the DenseNet 161 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
'''
eps = 1.1e-5
# compute compression factor
compression = 1.0 - reduction
# From architecture for ImageNet (Table 1 in the paper)
nb_filter = 96
nb_layers = [3, 4, 12, 8] # For DenseNet-161
box = []
# Initial convolution
x = ZeroPadding3D((3, 3, 3), name='3dconv1_zeropadding')(img_input)
x = Conv3D(nb_filter, (7, 7, 7),
strides=(2, 2, 2),
name='3dconv1',
use_bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=4, name='3dconv1_bn')(x)
x = Scale(axis=4, name='3dconv1_scale')(x)
x = Activation('relu', name='3drelu1')(x)
box.append(x)
x = ZeroPadding3D((1, 1, 1), name='3dpool1_zeropadding')(x)
x = MaxPooling3D((3, 3, 3), strides=(2, 2, 2), name='3dpool1')(x)
# Add dense blocks
for block_idx in range(nb_dense_block - 1):
stage = block_idx + 2
x, nb_filter = dense_block3d(x,
stage,
nb_layers[block_idx],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
box.append(x)
# Add transition_block
x = transition_block3d(x,
stage,
nb_filter,
compression=compression,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
final_stage = stage + 1
x, nb_filter = dense_block3d(x,
final_stage,
nb_layers[-1],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
x = BatchNormalization(epsilon=eps,
axis=4,
name='3dconv' + str(final_stage) + '_blk_bn')(x)
x = Scale(axis=4, name='3dconv' + str(final_stage) + '_blk_scale')(x)
x = Activation('relu', name='3drelu' + str(final_stage) + '_blk')(x)
box.append(x)
# print (box)
up0 = UpSampling3D(size=(2, 2, 1))(x)
# line0 = Conv3D(504, (1, 1, 1), padding="same", name="3dline0")(box[3])
# up0_sum = add([line0, up0])
conv_up0 = Conv3D(504, (3, 3, 3), padding="same", name="3dconv_up0")(up0)
bn_up0 = BatchNormalization(name="3dbn_up0")(conv_up0)
ac_up0 = Activation('relu', name='3dac_up0')(bn_up0)
up1 = UpSampling3D(size=(2, 2, 1))(ac_up0)
# up1_sum = add([box[2], up1])
conv_up1 = Conv3D(224, (3, 3, 3), padding="same", name="3dconv_up1")(up1)
bn_up1 = BatchNormalization(name="3dbn_up1")(conv_up1)
ac_up1 = Activation('relu', name='3dac_up1')(bn_up1)
up2 = UpSampling3D(size=(2, 2, 1))(ac_up1)
# up2_sum = add([box[1], up2])
conv_up2 = Conv3D(192, (3, 3, 3), padding="same", name="3dconv_up2")(up2)
bn_up2 = BatchNormalization(name="3dbn_up2")(conv_up2)
ac_up2 = Activation('relu', name='3dac_up2')(bn_up2)
up3 = UpSampling3D(size=(2, 2, 2))(ac_up2)
# up3_sum = add([box[0], up3])
conv_up3 = Conv3D(96, (3, 3, 3), padding="same", name="3dconv_up3")(up3)
bn_up3 = BatchNormalization(name="3dbn_up3")(conv_up3)
ac_up3 = Activation('relu', name='3dac_up3')(bn_up3)
up4 = UpSampling3D(size=(2, 2, 2))(ac_up3)
conv_up4 = Conv3D(64, (3, 3, 3), padding="same", name="3dconv_up4")(up4)
bn_up4 = BatchNormalization(name="3dbn_up4")(conv_up4)
ac_up4 = Activation('relu', name='3dac_up4')(bn_up4)
x = Conv3D(3, (1, 1, 1), padding="same", name='3dclassifer')(ac_up4)
return ac_up4, x
def DenseUNet(nb_dense_block=4,
growth_rate=48,
nb_filter=96,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
weights_path=None,
args=None):
'''Instantiate the DenseNet 161 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
'''
eps = 1.1e-5
# compute compression factor
compression = 1.0 - reduction
# Handle Dimension Ordering for different backends
global concat_axis
if K.image_dim_ordering() == 'tf':
concat_axis = 3
img_input = Input(batch_shape=(args.b, args.input_size,
args.input_size, 3),
name='data')
else:
concat_axis = 1
img_input = Input(shape=(3, 224, 224), name='data')
# From architecture for ImageNet (Table 1 in the paper)
nb_filter = 96
nb_layers = [6, 12, 36, 24] # For DenseNet-161
box = []
# Initial convolution
x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input)
x = Conv2D(nb_filter, (7, 7), strides=(2, 2), name='conv1',
use_bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=concat_axis, name='conv1_bn')(x)
x = Scale(axis=concat_axis, name='conv1_scale')(x)
x = Activation('relu', name='relu1')(x)
box.append(x)
x = ZeroPadding2D((1, 1), name='pool1_zeropadding')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(x)
# Add dense blocks
for block_idx in range(nb_dense_block - 1):
stage = block_idx + 2
x, nb_filter = dense_block(x,
stage,
nb_layers[block_idx],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
box.append(x)
# Add transition_block
x = transition_block(x,
stage,
nb_filter,
compression=compression,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
final_stage = stage + 1
x, nb_filter = dense_block(x,
final_stage,
nb_layers[-1],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
name='conv' + str(final_stage) + '_blk_bn')(x)
x = Scale(axis=concat_axis,
name='conv' + str(final_stage) + '_blk_scale')(x)
x = Activation('relu', name='relu' + str(final_stage) + '_blk')(x)
box.append(x)
up0 = UpSampling2D(size=(2, 2))(x)
line0 = Conv2D(2208, (1, 1),
padding="same",
kernel_initializer="normal",
name="line0")(box[3])
up0_sum = add([line0, up0])
conv_up0 = Conv2D(768, (3, 3),
padding="same",
kernel_initializer="normal",
name="conv_up0")(up0_sum)
bn_up0 = BatchNormalization(name="bn_up0")(conv_up0)
ac_up0 = Activation('relu', name='ac_up0')(bn_up0)
up1 = UpSampling2D(size=(2, 2))(ac_up0)
up1_sum = add([box[2], up1])
conv_up1 = Conv2D(384, (3, 3),
padding="same",
kernel_initializer="normal",
name="conv_up1")(up1_sum)
bn_up1 = BatchNormalization(name="bn_up1")(conv_up1)
ac_up1 = Activation('relu', name='ac_up1')(bn_up1)
up2 = UpSampling2D(size=(2, 2))(ac_up1)
up2_sum = add([box[1], up2])
conv_up2 = Conv2D(96, (3, 3),
padding="same",
kernel_initializer="normal",
name="conv_up2")(up2_sum)
bn_up2 = BatchNormalization(name="bn_up2")(conv_up2)
ac_up2 = Activation('relu', name='ac_up2')(bn_up2)
up3 = UpSampling2D(size=(2, 2))(ac_up2)
up3_sum = add([box[0], up3])
conv_up3 = Conv2D(96, (3, 3),
padding="same",
kernel_initializer="normal",
name="conv_up3")(up3_sum)
bn_up3 = BatchNormalization(name="bn_up3")(conv_up3)
ac_up3 = Activation('relu', name='ac_up3')(bn_up3)
up4 = UpSampling2D(size=(2, 2))(ac_up3)
conv_up4 = Conv2D(64, (3, 3),
padding="same",
kernel_initializer="normal",
name="conv_up4")(up4)
conv_up4 = Dropout(rate=0.3)(conv_up4)
bn_up4 = BatchNormalization(name="bn_up4")(conv_up4)
ac_up4 = Activation('relu', name='ac_up4')(bn_up4)
x = Conv2D(3, (1, 1),
padding="same",
kernel_initializer="normal",
name="dense167classifer")(ac_up4)
model = Model(img_input, x, name='denseu161')
return model
def DenseNet3D(img_input, nb_dense_block=4, growth_rate=32, nb_filter=96, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, classes=1000, weights_path=None):
'''Instantiate the DenseNet 161 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
'''
eps = 1.1e-5
# compute compression factor
compression = 1.0 - reduction
# From architecture for ImageNet (Table 1 in the paper)
nb_filter = 96
nb_layers = [3, 4, 12, 8] # For DenseNet-161
box = []
# Initial convolution
print("Input: " + str(img_input.shape))
x = ZeroPadding3D((3, 3, 3), name='3dconv1_zeropadding')(img_input)
x = Conv3D(nb_filter, (7, 7, 7), strides=(2, 2, 2), name='3dconv1', use_bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=4, name='3dconv1_bn')(x)
x = Scale(axis=4, name='3dconv1_scale')(x)
x = Activation('relu', name='3drelu1')(x)
box.append(x)
print("Conv1: " + str(x.shape))
x = ZeroPadding3D((1, 1, 1), name='3dpool1_zeropadding')(x)
x = MaxPooling3D((3, 3, 3), strides=(2, 2, 2), name='3dpool1')(x)
print("Pooling: " + str(x.shape))
# Add dense blocks
for block_idx in range(nb_dense_block - 1):
stage = block_idx + 2
x, nb_filter = dense_block3d(x, stage, nb_layers[block_idx], nb_filter, growth_rate, dropout_rate=dropout_rate,
weight_decay=weight_decay)
print("Dense Block " + str(block_idx + 1) + ": " + str(x.shape))
box.append(x)
# Add transition_block
x = transition_block3d(x, stage, nb_filter, compression=compression, dropout_rate=dropout_rate,
weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
print("Transition " + str(block_idx + 1) + ": " + str(x.shape))
final_stage = stage + 1
# The `latent space block`, i.e., the final dense block before upsampling
latent_space, nb_filter = dense_block3d(x, final_stage, nb_layers[-1], nb_filter, growth_rate, dropout_rate=dropout_rate,
weight_decay=weight_decay)
print("Dense Block 4: " + str(latent_space.shape))
x = BatchNormalization(epsilon=eps, axis=4, name='3dconv' + str(final_stage) + '_blk_bn')(latent_space)
x = Scale(axis=4, name='3dconv' + str(final_stage) + '_blk_scale')(x)
x = Activation('relu', name='3drelu' + str(final_stage) + '_blk')(x)
# First upsampling layer
up0 = UpSampling3D(size=(2, 2, 1))(x)
conv_up0 = Conv3D(504, (3, 3, 3), padding="same", name="3dconv_up0")(up0)
bn_up0 = BatchNormalization(name="3dbn_up0")(conv_up0)
ac_up0 = Activation('relu', name='3dac_up0')(bn_up0)
print("Upsampling 1: " + str(ac_up0.shape))
up1 = UpSampling3D(size=(2, 2, 1))(ac_up0)
conv_up1 = Conv3D(224, (3, 3, 3), padding="same", name="3dconv_up1")(up1)
bn_up1 = BatchNormalization(name="3dbn_up1")(conv_up1)
ac_up1 = Activation('relu', name='3dac_up1')(bn_up1)
print("Upsampling 2: " + str(ac_up1.shape))
up2 = UpSampling3D(size=(2, 2, 1))(ac_up1)
conv_up2 = Conv3D(192, (3, 3, 3), padding="same", name="3dconv_up2")(up2)
bn_up2 = BatchNormalization(name="3dbn_up2")(conv_up2)
ac_up2 = Activation('relu', name='3dac_up2')(bn_up2)
print("Upsampling 3: " + str(ac_up2.shape))
up3 = UpSampling3D(size=(2, 2, 2))(ac_up2)
conv_up3 = Conv3D(96, (3, 3, 3), padding="same", name="3dconv_up3")(up3)
bn_up3 = BatchNormalization(name="3dbn_up3")(conv_up3)
ac_up3 = Activation('relu', name='3dac_up3')(bn_up3)
print("Upsampling 4: " + str(ac_up3.shape))
up4 = UpSampling3D(size=(2, 2, 2))(ac_up3)
conv_up4 = Conv3D(64, (3, 3, 3), padding="same", name="3dconv_up4")(up4)
bn_up4 = BatchNormalization(name="3dbn_up4")(conv_up4)
ac_up4 = Activation('relu', name='3dac_up4')(bn_up4)
print("Upsampling 5: " + str(ac_up4.shape))
x = Conv3D(3, (1, 1, 1), padding="same", name='3dclassifer')(ac_up4)
print("Conv2: " + str(x.shape))
return ac_up4, x, latent_space
def DenseNet3D(img_input,
nb_dense_block=4,
growth_rate=32,
nb_filter=96,
reduction=0.0,
dropout_rate=0.0):
"""Instantiate the DenseNet 161 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
"""
eps = 1.1e-5
compression = 1.0 - reduction
# From architecture for ImageNet (Table 1 in the paper)
nb_layers = [3, 4, 12, 8]
box = []
stage = 0
x = ZeroPadding3D((3, 3, 3),
name='3D_convolution_1_zero_padding')(img_input)
x = Conv3D(nb_filter, (7, 7, 7),
strides=(2, 2, 2),
name='3D_convolution_1',
use_bias=False)(x)
x = BatchNormalization(epsilon=eps,
axis=4,
name='3D_convolution_1_batch_normalization')(x)
x = Scale(axis=4, name='3D_convolution_1_scale')(x)
x = Activation('relu', name='3D_convolution_1_ReLU')(x)
box.append(x)
x = ZeroPadding3D((1, 1, 1), name='3D_pooling_1_zero_padding')(x)
x = MaxPooling3D((3, 3, 3), strides=(2, 2, 2), name='3D_pooling_1')(x)
for block_id in range(nb_dense_block - 1):
stage = block_id + 2
x, nb_filter = dense_block3d(x,
stage,
nb_layers[block_id],
nb_filter,
growth_rate,
dropout_rate=dropout_rate)
box.append(x)
# Add transition_block
x = transition_block3d(x,
stage,
nb_filter,
compression=compression,
dropout_rate=dropout_rate)
nb_filter = int(nb_filter * compression)
final_stage = stage + 1
x, nb_filter = dense_block3d(x,
final_stage,
nb_layers[-1],
nb_filter,
growth_rate,
dropout_rate=dropout_rate)
x = BatchNormalization(epsilon=eps,
axis=4,
name='3D_convolution_' + str(final_stage) +
'_blk_batch_normalization')(x)
x = Scale(axis=4,
name='3D_convolution_' + str(final_stage) + '_blk_scale')(x)
x = Activation('relu',
name='3D_convolution_ReLU' + str(final_stage) + '_blk')(x)
box.append(x)
up0 = UpSampling3D(size=(2, 2, 1))(x)
conv_up0 = Conv3D(504, (3, 3, 3), padding="same",
name="3D_upsampling_0")(up0)
bn_up0 = BatchNormalization(
name="3D_upsampling_0_batch_normalization")(conv_up0)
ac_up0 = Activation('relu', name='3D_upsampling_0_ReLU')(bn_up0)
up1 = UpSampling3D(size=(2, 2, 1))(ac_up0)
conv_up1 = Conv3D(224, (3, 3, 3), padding="same",
name="3D_upsampling_1")(up1)
bn_up1 = BatchNormalization(
name="3D_upsampling_1_batch_normalization")(conv_up1)
ac_up1 = Activation('relu', name='3D_upsampling_1_ReLU')(bn_up1)
up2 = UpSampling3D(size=(2, 2, 1))(ac_up1)
conv_up2 = Conv3D(192, (3, 3, 3), padding="same",
name="3D_upsampling_2")(up2)
bn_up2 = BatchNormalization(
name="3D_upsampling_2_batch_normalization")(conv_up2)
ac_up2 = Activation('relu', name='3D_upsampling_2_ReLU')(bn_up2)
up3 = UpSampling3D(size=(2, 2, 2))(ac_up2)
conv_up3 = Conv3D(96, (3, 3, 3), padding="same",
name="3D_upsampling_3")(up3)
bn_up3 = BatchNormalization(
name="3D_upsampling_3_batch_normalization")(conv_up3)
ac_up3 = Activation('relu', name='3D_upsampling_3_ReLU')(bn_up3)
up4 = UpSampling3D(size=(2, 2, 2))(ac_up3)
conv_up4 = Conv3D(64, (3, 3, 3), padding="same",
name="3D_upsampling_4")(up4)
bn_up4 = BatchNormalization(
name="3D_upsampling_4_batch_normalization")(conv_up4)
ac_up4 = Activation('relu', name='3D_upsampling_4_ReLU')(bn_up4)
x = Conv3D(3, (1, 1, 1), padding="same", name='3D_classifier')(ac_up4)
return ac_up4, x
def DenseUNet(img_input,
nb_dense_block=4,
growth_rate=48,
nb_filter=96,
reduction=0.0,
dropout_rate=0.0):
"""Instantiate the DenseNet 161 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
"""
eps = 1.1e-5
compression = 1.0 - reduction
# From architecture for ImageNet (Table 1 in the paper)
nb_layers = [6, 12, 36, 24]
box = []
stage = 0
x = ZeroPadding2D((3, 3), name='convolution_1_zero_padding')(img_input)
x = Conv2D(nb_filter, (7, 7),
strides=(2, 2),
name='convolution_1',
use_bias=False,
trainable=True)(x)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
momentum=1,
name='convolution_1_batch_normalization',
trainable=False)(x, training=False)
x = Scale(axis=concat_axis, name='convolution_1_scale')(x)
x = Activation('relu', name='convolution_1_ReLU')(x)
box.append(x)
x = ZeroPadding2D((1, 1), name='pooling_1_zero_padding')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='pooling_1')(x)
for block_id in range(nb_dense_block - 1):
stage = block_id + 2
x, nb_filter = dense_block(x,
stage,
nb_layers[block_id],
nb_filter,
growth_rate,
dropout_rate=dropout_rate)
box.append(x)
x = transition_block(x,
stage,
nb_filter,
compression=compression,
dropout_rate=dropout_rate)
nb_filter = int(nb_filter * compression)
final_stage = stage + 1
x, nb_filter = dense_block(x,
final_stage,
nb_layers[-1],
nb_filter,
growth_rate,
dropout_rate=dropout_rate)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
momentum=1,
name='convolution_' + str(final_stage) +
'_blk_batch_normalization',
trainable=False)(x, training=False)
x = Scale(axis=concat_axis,
name='convolution_' + str(final_stage) + '_blk_scale')(x)
x = Activation('relu', name='ReLU_' + str(final_stage) + '_blk')(x)
box.append(x)
up0 = UpSampling2D(size=(2, 2))(x)
conv_up0 = Conv2D(768, (3, 3),
padding="same",
name="upsampling_0",
trainable=True)(up0)
bn_up0 = BatchNormalization(name="batch_normalization_upsampling_0",
momentum=1,
trainable=False)(conv_up0, training=False)
ac_up0 = Activation('relu', name='ReLU_upsampling_0')(bn_up0)
up1 = UpSampling2D(size=(2, 2))(ac_up0)
conv_up1 = Conv2D(384, (3, 3),
padding="same",
name="upsampling_1",
trainable=True)(up1)
bn_up1 = BatchNormalization(name="batch_normalization_upsampling_1",
momentum=1,
trainable=False)(conv_up1, training=False)
ac_up1 = Activation('relu', name='ReLU_upsampling_1')(bn_up1)
up2 = UpSampling2D(size=(2, 2))(ac_up1)
conv_up2 = Conv2D(96, (3, 3),
padding="same",
name="upsampling_2",
trainable=True)(up2)
bn_up2 = BatchNormalization(name="batch_normalization_upsampling_2",
momentum=1,
trainable=False)(conv_up2, training=False)
ac_up2 = Activation('relu', name='ReLU_upsampling_2')(bn_up2)
up3 = UpSampling2D(size=(2, 2))(ac_up2)
conv_up3 = Conv2D(96, (3, 3),
padding="same",
name="upsampling_3",
trainable=True)(up3)
bn_up3 = BatchNormalization(name="batch_normalization_upsampling_3",
momentum=1,
trainable=False)(conv_up3, training=False)
ac_up3 = Activation('relu', name='ReLU_upsampling_3')(bn_up3)
up4 = UpSampling2D(size=(2, 2))(ac_up3)
conv_up4 = Conv2D(64, (3, 3),
padding="same",
name="upsampling_4",
trainable=True)(up4)
bn_up4 = BatchNormalization(name="batch_normalization_upsampling_4",
momentum=1,
trainable=False)(conv_up4, training=False)
ac_up4 = Activation('relu', name='ReLU_upsampling_4')(bn_up4)
x = Conv2D(3, (1, 1),
padding="same",
name='2D-DenseUNet-167_classifier',
trainable=True)(ac_up4)
return ac_up4, x