Python keras.layers.convolutional.UpSampling2D() Examples
The following are 30
code examples of keras.layers.convolutional.UpSampling2D().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
keras.layers.convolutional
, or try the search function
.
.
Example #1
| Source File: sgan.py From Keras-GAN with MIT License | 8 votes |
|
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(BatchNormalization(momentum=0.8))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=3, padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=3, padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Conv2D(1, kernel_size=3, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
Example #2
| Source File: base.py From keras-rtst with MIT License | 6 votes |
|
def create_res_texture_net(input_rows, input_cols, num_res_filters=128,
res_out_activation='linear', activation='relu', num_res_blocks=5):
net = Graph()
net.add_input('x', input_shape=(3, input_rows, input_cols))
add_conv_block(net, 'in0', 'x', num_res_filters // 4, 9, activation=activation)
add_conv_block(net, 'in1', 'in0', num_res_filters // 2, 3, subsample=(2, 2), activation=activation)
add_conv_block(net, 'in2', 'in1', num_res_filters, 3, subsample=(2, 2), activation=activation)
last_block_name = 'in2'
for res_i in range(num_res_blocks):
block_name = 'res_{}'.format(res_i)
add_conv_block(net, block_name + '_in0', last_block_name, num_res_filters, 3, activation=activation)
add_conv_block(net, block_name + '_in1', block_name + '_in0', num_res_filters, 3, activation='linear')
net.add_node(Activation(res_out_activation), block_name, merge_mode='sum', inputs=[block_name + '_in1', last_block_name])
last_block_name = block_name
# theano doesn't seem to support fractionally-strided convolutions at the moment
net.add_node(UpSampling2D(), 'out_up0', last_block_name)
add_conv_block(net, 'out_0', 'out_up0', num_res_filters // 2, 3, activation=activation)
net.add_node(UpSampling2D(), 'out_up1', 'out_0')
add_conv_block(net, 'out_1', 'out_up1', num_res_filters // 4, 3, activation=activation)
add_conv_block(net, 'out_2', 'out_1', 3, 9, activation='linear')
net.add_node(Activation('linear'), 'texture_rgb', 'out_2', create_output=True)
return net
Example #3
| Source File: dcgan.py From Keras-DCGAN-killmebaby with MIT License | 6 votes |
|
def build_generator(self):
noise_shape = (self.z_dim,)
model = Sequential()
model.add(Dense(128 * 32 * 32, activation="relu", input_shape=noise_shape))
model.add(Reshape((32, 32, 128)))
model.add(BatchNormalization(momentum=0.8))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=3, padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=3, padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Conv2D(3, kernel_size=3, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=noise_shape)
img = model(noise)
return Model(noise, img)
Example #4
| Source File: wgan_gp.py From Keras-GAN with MIT License | 6 votes |
|
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=4, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
Example #5
| Source File: wgan.py From Keras-GAN with MIT License | 6 votes |
|
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=4, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
Example #6
| Source File: Chapter_3_wgan.py From Hands-On-Deep-Learning-for-Games with MIT License | 6 votes |
|
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=4, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
Example #7
| Source File: Chapter_3_2.py From Hands-On-Deep-Learning-for-Games with MIT License | 6 votes |
|
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=3, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
Example #8
| Source File: Chapter_3_3.py From Hands-On-Deep-Learning-for-Games with MIT License | 6 votes |
|
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 8 * 8, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((8, 8, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=4, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=4, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
Example #9
| Source File: densenet.py From SSR-Net with Apache License 2.0 | 6 votes |
|
def __transition_up_block(ip, nb_filters, type='deconv', weight_decay=1E-4):
''' SubpixelConvolutional Upscaling (factor = 2)
Args:
ip: keras tensor
nb_filters: number of layers
type: can be 'upsampling', 'subpixel', 'deconv'. Determines type of upsampling performed
weight_decay: weight decay factor
Returns: keras tensor, after applying upsampling operation.
'''
if type == 'upsampling':
x = UpSampling2D()(ip)
elif type == 'subpixel':
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(ip)
x = SubPixelUpscaling(scale_factor=2)(x)
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(x)
else:
x = Conv2DTranspose(nb_filters, (3, 3), activation='relu', padding='same', strides=(2, 2),
kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(ip)
return x
Example #10
| Source File: cifar_10_gan.py From Deep-Learning-Quick-Reference with MIT License | 6 votes |
|
def build_generator(noise_shape=(100,)):
input = Input(noise_shape)
x = Dense(128 * 8 * 8, activation="relu")(input)
x = Reshape((8, 8, 128))(x)
x = BatchNormalization(momentum=0.8)(x)
x = UpSampling2D()(x)
x = Conv2D(128, kernel_size=3, padding="same")(x)
x = Activation("relu")(x)
x = BatchNormalization(momentum=0.8)(x)
x = UpSampling2D()(x)
x = Conv2D(64, kernel_size=3, padding="same")(x)
x = Activation("relu")(x)
x = BatchNormalization(momentum=0.8)(x)
x = Conv2D(3, kernel_size=3, padding="same")(x)
out = Activation("tanh")(x)
model = Model(input, out)
print("-- Generator -- ")
model.summary()
return model
Example #11
| Source File: densenet.py From Model-Playgrounds with MIT License | 6 votes |
|
def __transition_up_block(ip, nb_filters, type='deconv', weight_decay=1E-4):
''' SubpixelConvolutional Upscaling (factor = 2)
Args:
ip: keras tensor
nb_filters: number of layers
type: can be 'upsampling', 'subpixel', 'deconv'. Determines type of upsampling performed
weight_decay: weight decay factor
Returns: keras tensor, after applying upsampling operation.
'''
if type == 'upsampling':
x = UpSampling2D()(ip)
elif type == 'subpixel':
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(ip)
x = SubPixelUpscaling(scale_factor=2)(x)
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(x)
else:
x = Conv2DTranspose(nb_filters, (3, 3), activation='relu', padding='same', strides=(2, 2),
kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(ip)
return x
Example #12
| Source File: fcDensenet.py From PyTorch-Luna16 with Apache License 2.0 | 6 votes |
|
def __transition_up_block(ip, nb_filters, type='deconv', weight_decay=1E-4):
''' SubpixelConvolutional Upscaling (factor = 2)
Args:
ip: keras tensor
nb_filters: number of layers
type: can be 'upsampling', 'subpixel', 'deconv'. Determines type of upsampling performed
weight_decay: weight decay factor
Returns: keras tensor, after applying upsampling operation.
'''
if type == 'upsampling':
x = UpSampling2D()(ip)
elif type == 'subpixel':
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(ip)
x = SubPixelUpscaling(scale_factor=2)(x)
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(x)
else:
x = Conv2DTranspose(nb_filters, (3, 3), activation='relu', padding='same', strides=(2, 2),
kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(ip)
return x
Example #13
| Source File: example_gan_convolutional.py From keras-adversarial with MIT License | 6 votes |
|
def model_generator():
nch = 256
g_input = Input(shape=[100])
H = Dense(nch * 14 * 14)(g_input)
H = BatchNormalization(mode=2)(H)
H = Activation('relu')(H)
H = dim_ordering_reshape(nch, 14)(H)
H = UpSampling2D(size=(2, 2))(H)
H = Convolution2D(int(nch / 2), 3, 3, border_mode='same')(H)
H = BatchNormalization(mode=2, axis=1)(H)
H = Activation('relu')(H)
H = Convolution2D(int(nch / 4), 3, 3, border_mode='same')(H)
H = BatchNormalization(mode=2, axis=1)(H)
H = Activation('relu')(H)
H = Convolution2D(1, 1, 1, border_mode='same')(H)
g_V = Activation('sigmoid')(H)
return Model(g_input, g_V)
Example #14
| Source File: dcgan_mnist.py From keras-examples with MIT License | 6 votes |
|
def generator_model():
model = Sequential()
model.add(Dense(input_dim=100, output_dim=1024))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dense(7 * 7 * 128))
model.add(BatchNormalization())
model.add(Activation('relu'))
# tfモードの場合はチャネルは後！
model.add(Reshape((7, 7, 128), input_shape=(7 * 7 * 128,)))
model.add(UpSampling2D((2, 2))) # 画像のサイズが2倍になる 14x14
model.add(Convolution2D(64, 5, 5, border_mode='same'))
model.add(Activation('tanh'))
model.add(UpSampling2D(size=(2, 2))) # 28x28
model.add(Convolution2D(1, 5, 5, border_mode='same')) # 28x28x1が出力
model.add(Activation('tanh'))
return model
Example #15
| Source File: example_aae_cifar10.py From keras-adversarial with MIT License | 6 votes |
|
def model_generator(latent_dim, units=512, dropout=0.5, reg=lambda: l1l2(l1=1e-7, l2=1e-7)):
model = Sequential(name="decoder")
h = 5
model.add(Dense(units * 4 * 4, input_dim=latent_dim, W_regularizer=reg()))
model.add(Reshape(dim_ordering_shape((units, 4, 4))))
# model.add(SpatialDropout2D(dropout))
model.add(LeakyReLU(0.2))
model.add(Convolution2D(units / 2, h, h, border_mode='same', W_regularizer=reg()))
# model.add(SpatialDropout2D(dropout))
model.add(LeakyReLU(0.2))
model.add(UpSampling2D(size=(2, 2)))
model.add(Convolution2D(units / 2, h, h, border_mode='same', W_regularizer=reg()))
# model.add(SpatialDropout2D(dropout))
model.add(LeakyReLU(0.2))
model.add(UpSampling2D(size=(2, 2)))
model.add(Convolution2D(units / 4, h, h, border_mode='same', W_regularizer=reg()))
# model.add(SpatialDropout2D(dropout))
model.add(LeakyReLU(0.2))
model.add(UpSampling2D(size=(2, 2)))
model.add(Convolution2D(3, h, h, border_mode='same', W_regularizer=reg()))
model.add(Activation('sigmoid'))
return model
Example #16
| Source File: example_gan_cifar10.py From keras-adversarial with MIT License | 6 votes |
|
def model_generator():
model = Sequential()
nch = 256
reg = lambda: l1l2(l1=1e-7, l2=1e-7)
h = 5
model.add(Dense(nch * 4 * 4, input_dim=100, W_regularizer=reg()))
model.add(BatchNormalization(mode=0))
model.add(Reshape(dim_ordering_shape((nch, 4, 4))))
model.add(Convolution2D(int(nch / 2), h, h, border_mode='same', W_regularizer=reg()))
model.add(BatchNormalization(mode=0, axis=1))
model.add(LeakyReLU(0.2))
model.add(UpSampling2D(size=(2, 2)))
model.add(Convolution2D(int(nch / 2), h, h, border_mode='same', W_regularizer=reg()))
model.add(BatchNormalization(mode=0, axis=1))
model.add(LeakyReLU(0.2))
model.add(UpSampling2D(size=(2, 2)))
model.add(Convolution2D(int(nch / 4), h, h, border_mode='same', W_regularizer=reg()))
model.add(BatchNormalization(mode=0, axis=1))
model.add(LeakyReLU(0.2))
model.add(UpSampling2D(size=(2, 2)))
model.add(Convolution2D(3, h, h, border_mode='same', W_regularizer=reg()))
model.add(Activation('sigmoid'))
return model
Example #17
| Source File: run.py From Generative-Adversarial-Networks-Projects with MIT License | 6 votes |
|
def build_generator():
gen_model = Sequential()
gen_model.add(Dense(input_dim=100, output_dim=2048))
gen_model.add(ReLU())
gen_model.add(Dense(256 * 8 * 8))
gen_model.add(BatchNormalization())
gen_model.add(ReLU())
gen_model.add(Reshape((8, 8, 256), input_shape=(256 * 8 * 8,)))
gen_model.add(UpSampling2D(size=(2, 2)))
gen_model.add(Conv2D(128, (5, 5), padding='same'))
gen_model.add(ReLU())
gen_model.add(UpSampling2D(size=(2, 2)))
gen_model.add(Conv2D(64, (5, 5), padding='same'))
gen_model.add(ReLU())
gen_model.add(UpSampling2D(size=(2, 2)))
gen_model.add(Conv2D(3, (5, 5), padding='same'))
gen_model.add(Activation('tanh'))
return gen_model
Example #18
| Source File: base.py From keras-rtst with MIT License | 6 votes |
|
def create_sequential_texture_net(input_rows, input_cols, num_res_filters=128,
res_out_activation='linear', activation='relu', num_inner_blocks=5):
net = Sequential()
add_seq_conv_block(net, num_res_filters // 4, 9, input_shape=(3, input_rows, input_cols), activation=activation)
add_seq_conv_block(net, num_res_filters // 2, 3, subsample=(2, 2), activation=activation)
add_seq_conv_block(net, num_res_filters, 3, subsample=(2, 2), activation=activation)
for i in range(num_inner_blocks):
add_seq_conv_block(net, num_res_filters, 3, activation=activation)
add_seq_conv_block(net, num_res_filters, 3, activation=activation)
# theano doesn't seem to support fractionally-strided convolutions at the moment
net.add(UpSampling2D())
add_seq_conv_block(net, num_res_filters // 2, 3, activation=activation)
net.add(UpSampling2D())
add_seq_conv_block(net, num_res_filters // 4, 3, activation=activation)
add_seq_conv_block(net, 3, 9, activation='linear')
return net
Example #19
| Source File: densenet_1.py From keras-onnx with MIT License | 6 votes |
|
def __transition_up_block(ip, nb_filters, type='deconv', weight_decay=1E-4):
''' SubpixelConvolutional Upscaling (factor = 2)
Args:
ip: keras tensor
nb_filters: number of layers
type: can be 'upsampling', 'subpixel', 'deconv'. Determines type of upsampling performed
weight_decay: weight decay factor
Returns: keras tensor, after applying upsampling operation.
'''
if type == 'upsampling':
x = UpSampling2D()(ip)
elif type == 'subpixel':
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(ip)
x = SubPixelUpscaling(scale_factor=2)(x)
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(x)
else:
x = Conv2DTranspose(nb_filters, (3, 3), activation='relu', padding='same', strides=(2, 2),
kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(ip)
return x
Example #20
| Source File: densenet.py From semantic-embeddings with MIT License | 6 votes |
|
def __transition_up_block(ip, nb_filters, type='deconv', weight_decay=1E-4):
''' SubpixelConvolutional Upscaling (factor = 2)
Args:
ip: keras tensor
nb_filters: number of layers
type: can be 'upsampling', 'subpixel', 'deconv'. Determines type of upsampling performed
weight_decay: weight decay factor
Returns: keras tensor, after applying upsampling operation.
'''
if type == 'upsampling':
x = UpSampling2D()(ip)
elif type == 'subpixel':
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(ip)
x = SubPixelUpscaling(scale_factor=2)(x)
x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay),
use_bias=False, kernel_initializer='he_normal')(x)
else:
x = Conv2DTranspose(nb_filters, (3, 3), activation='relu', padding='same', strides=(2, 2),
kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(ip)
return x
Example #21
| Source File: mnist_gan.py From Deep-Learning-Quick-Reference with MIT License | 6 votes |
|
def build_generator(noise_shape=(100,)):
input = Input(noise_shape)
x = Dense(128 * 7 * 7, activation="relu")(input)
x = Reshape((7, 7, 128))(x)
x = BatchNormalization(momentum=0.8)(x)
x = UpSampling2D()(x)
x = Conv2D(128, kernel_size=3, padding="same")(x)
x = Activation("relu")(x)
x = BatchNormalization(momentum=0.8)(x)
x = UpSampling2D()(x)
x = Conv2D(64, kernel_size=3, padding="same")(x)
x = Activation("relu")(x)
x = BatchNormalization(momentum=0.8)(x)
x = Conv2D(1, kernel_size=3, padding="same")(x)
out = Activation("tanh")(x)
model = Model(input, out)
print("-- Generator -- ")
model.summary()
return model
Example #22
| Source File: models.py From DeepLearningImplementations with MIT License | 5 votes |
|
def up_conv_block_unet(x, x2, f, name, bn_mode, bn_axis, bn=True, dropout=False):
x = Activation("relu")(x)
x = UpSampling2D(size=(2, 2))(x)
x = Conv2D(f, (3, 3), name=name, padding="same")(x)
if bn:
x = BatchNormalization(axis=bn_axis)(x)
if dropout:
x = Dropout(0.5)(x)
x = Concatenate(axis=bn_axis)([x, x2])
return x
Example #23
| Source File: models.py From DeepLearningImplementations with MIT License | 5 votes |
|
def lambda_output(input_shape):
return input_shape[:2]
# def conv_block_unet(x, f, name, bn_mode, bn_axis, bn=True, dropout=False, strides=(2,2)):
# x = Conv2D(f, (3, 3), strides=strides, name=name, padding="same")(x)
# if bn:
# x = BatchNormalization(axis=bn_axis)(x)
# x = LeakyReLU(0.2)(x)
# if dropout:
# x = Dropout(0.5)(x)
# return x
# def up_conv_block_unet(x1, x2, f, name, bn_mode, bn_axis, bn=True, dropout=False):
# x1 = UpSampling2D(size=(2, 2))(x1)
# x = merge([x1, x2], mode="concat", concat_axis=bn_axis)
# x = Conv2D(f, (3, 3), name=name, padding="same")(x)
# if bn:
# x = BatchNormalization(axis=bn_axis)(x)
# x = Activation("relu")(x)
# if dropout:
# x = Dropout(0.5)(x)
# return x
Example #24
| Source File: model_fcn.py From Keras-FCN with MIT License | 5 votes |
|
def testnet_fcn(n_classes): stride = 32 input_tensor = Input(shape=(None, None, 3)) x = Convolution2D(4,5,5,name='conv', activation = 'relu', border_mode='same', subsample= (stride,stride))(input_tensor) x = Softmax4D(axis=-1)(x) x = UpSampling2D(size=(stride,stride))(x) x = Convolution2D(n_classes,3,3,name = 'pred_up',border_mode = 'same')(x) model = Model(input=input_tensor,output=x) return model, stride
Example #25
| Source File: models.py From Hands-On-Generative-Adversarial-Networks-with-Keras with MIT License | 5 votes |
|
def decoding_block(x, skip_input, n_filters, kernel_size=4):
x = UpSampling2D(size=2)(x)
x = Conv2D(n_filters, kernel_size=kernel_size, strides=1, padding='same')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
x = Concatenate()([x, skip_input])
return x
Example #26
| Source File: girthy.py From keras-rtst with MIT License | 5 votes |
|
def create_res_texture_net(input_rows, input_cols, num_res_filters=128,
res_out_activation='linear', activation='relu', num_res_blocks=5, depth=3):
'''Adds a series of residual blocks at each resolution scale, rather than just
the minimium one.
'''
net = Graph()
net.add_input('x', input_shape=(3, input_rows, input_cols))
add_conv_block(net, 'in0', 'x', num_res_filters // 4, 9, activation=activation)
last_name = 'in0'
# scale down input to max depth with a series of strided convolutions
for scale_i in range(depth):
num_scale_filters = num_res_filters - scale_i * 8 # // (2 ** scale_i) # (depth - scale_i - 1))
scale_name = 'down_{}'.format(scale_i)
add_conv_block(net, scale_name, last_name, num_scale_filters, 3, subsample=(2, 2), activation=activation)
last_name = scale_name
# add a series of residual blocks at each scale, from smallest to largest
for scale_i in reversed(range(depth)):
num_scale_filters = num_res_filters - scale_i * 8 # // (2 ** scale_i) # (depth - scale_i - 1))
last_scale_name = last_name
for res_i in range(num_res_blocks):
block_name = 'res_{}_{}'.format(scale_i, res_i)
add_conv_block(net, block_name + '_b0', last_name, num_res_filters, 3, activation=activation)
add_conv_block(net, block_name + '_b1', block_name + '_b0', num_res_filters, 1, activation='linear')
if last_name == last_scale_name:
# tranform residual connection to same number of filters
add_conv_block(net, block_name + '_res', last_name, num_res_filters, 1, activation='linear')
else:
# no transform needed when the last node was part of the current residual block
net.add_node(Layer(), block_name + '_res', last_name)
net.add_node(Activation(res_out_activation), block_name, merge_mode='sum', inputs=[block_name + '_b1', block_name + '_res'])
last_name = block_name
# theano doesn't seem to support fractionally-strided convolutions at the moment
up_name = 'up_{}'.format(scale_i)
net.add_node(UpSampling2D(), up_name, last_name)
last_name = up_name
last_scale_name = up_name
# final output
add_conv_block(net, 'out', last_name, 3, 9, activation='linear')
net.add_node(Activation('linear'), 'texture_rgb', 'out', create_output=True)
return net
Example #27
| Source File: SeGAN.py From DeepLearning-SeGAN-Segmentation with MIT License | 5 votes |
|
def upsampl_block(x, nb_filters, kernel, stride, size):
x = UpSampling2D(size=size)(x)
x = conv_l1(x, nb_filters, kernel, stride)
x = bnorm(x)
return relu(x)
Example #28
| Source File: SeGAN.py From DeepLearning-SeGAN-Segmentation with MIT License | 5 votes |
|
def upsampl_conv(x, nb_filters, kernel, stride, size):
x = UpSampling2D(size=size)(x)
return conv_l1(x, nb_filters, kernel, stride)
Example #29
| Source File: models.py From kaggle-carvana-2017 with MIT License | 5 votes |
|
def get_unet_resnet(input_shape):
resnet_base = ResNet50(input_shape=input_shape, include_top=False)
if args.show_summary:
resnet_base.summary()
for l in resnet_base.layers:
l.trainable = True
conv1 = resnet_base.get_layer("activation_1").output
conv2 = resnet_base.get_layer("activation_10").output
conv3 = resnet_base.get_layer("activation_22").output
conv4 = resnet_base.get_layer("activation_40").output
conv5 = resnet_base.get_layer("activation_49").output
up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
conv6 = conv_block_simple(up6, 256, "conv6_1")
conv6 = conv_block_simple(conv6, 256, "conv6_2")
up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
conv7 = conv_block_simple(up7, 192, "conv7_1")
conv7 = conv_block_simple(conv7, 192, "conv7_2")
up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
conv8 = conv_block_simple(up8, 128, "conv8_1")
conv8 = conv_block_simple(conv8, 128, "conv8_2")
up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
conv9 = conv_block_simple(up9, 64, "conv9_1")
conv9 = conv_block_simple(conv9, 64, "conv9_2")
vgg = VGG16(input_shape=input_shape, input_tensor=resnet_base.input, include_top=False)
for l in vgg.layers:
l.trainable = False
vgg_first_conv = vgg.get_layer("block1_conv2").output
up10 = concatenate([UpSampling2D()(conv9), resnet_base.input, vgg_first_conv], axis=-1)
conv10 = conv_block_simple(up10, 32, "conv10_1")
conv10 = conv_block_simple(conv10, 32, "conv10_2")
conv10 = SpatialDropout2D(0.2)(conv10)
x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
model = Model(resnet_base.input, x)
return model
Example #30
| Source File: models.py From Hands-On-Generative-Adversarial-Networks-with-Keras with MIT License | 5 votes |
|
def build_generator(input_shape=(256, 256, 3), ngf=64, kernel_size=4,
strides=2):
"""U-Net Generator"""
image_input = Input(shape=input_shape)
n_channels = input_shape[-1]
# encoding blocks
e1 = Conv2D(ngf, kernel_size=kernel_size, strides=2, padding='same')(
image_input)
e1 = LeakyReLU(alpha=0.2)(e1)
e2 = encoding_block(e1, ngf*2)
e3 = encoding_block(e2, ngf*4)
e4 = encoding_block(e3, ngf*8)
e5 = encoding_block(e4, ngf*8)
e6 = encoding_block(e5, ngf*8)
x = encoding_block(e6, ngf*8)
# decoding blocks
x = decoding_block(x, e6, ngf*8)
x = decoding_block(x, e5, ngf*8)
x = decoding_block(x, e4, ngf*8)
x = decoding_block(x, e3, ngf*4)
x = decoding_block(x, e2, ngf*2)
x = decoding_block(x, e1, ngf)
x = UpSampling2D(size=2)(x)
x = Conv2D(n_channels, kernel_size=4, strides=1, padding='same')(x)
x = Activation('tanh')(x)
# create model graph
model = Model(inputs=image_input, outputs=x, name='Generator')
print("\nGenerator")
model.summary()
return model
