Python keras.layers.LeakyReLU() Examples
The following are 30
code examples of keras.layers.LeakyReLU().
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
, or try the search function
.
.
Example #1
| Source File: bigan.py From Keras-BiGAN with MIT License | 6 votes |
|
def d_block(inp, fil, p = True):
skip = Conv2D(fil, 1, padding = 'same', kernel_initializer = 'he_normal')(inp)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(inp)
out = LeakyReLU(0.2)(out)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
out = LeakyReLU(0.2)(out)
out = Conv2D(fil, 1, padding = 'same', kernel_initializer = 'he_normal')(out)
out = add([out, skip])
out = LeakyReLU(0.2)(out)
if p:
out = AveragePooling2D()(out)
return out
Example #2
| Source File: mnist_model.py From keras-tqdm with MIT License | 6 votes |
|
def build_model():
x = Input((28 * 28,), name="x")
hidden_dim = 512
h = x
h = Dense(hidden_dim)(h)
h = BatchNormalization()(h)
h = LeakyReLU(0.2)(h)
h = Dropout(0.5)(h)
h = Dense(hidden_dim / 2)(h)
h = BatchNormalization()(h)
h = LeakyReLU(0.2)(h)
h = Dropout(0.5)(h)
h = Dense(10)(h)
h = Activation('softmax')(h)
m = Model(x, h)
m.compile('adam', 'categorical_crossentropy', metrics=['accuracy'])
return m
Example #3
| Source File: neural_network.py From ReinforcementLearning with Apache License 2.0 | 6 votes |
|
def residual_layer(self, x, filters, kernel_size):
conv_1 = self.conv_layer(x, filters, kernel_size)
conv_2 = Conv2D(
filters = filters,
kernel_size = kernel_size,
strides = (1, 1),
padding = 'same',
data_format = 'channels_first',
use_bias = False,
activation = 'linear',
kernel_regularizer = regularizers.l2(self.reg_const)
)(conv_1)
bn = BatchNormalization(axis=1)(conv_2)
merge_layer = add([x, bn])
lrelu = LeakyReLU()(merge_layer)
return lrelu
Example #4
| Source File: object_detection.py From Traffic-Signal-Violation-Detection-System with GNU General Public License v3.0 | 6 votes |
|
def _conv_block(inp, convs, skip=True):
x = inp
count = 0
for conv in convs:
if count == (len(convs) - 2) and skip:
skip_connection = x
count += 1
if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet prefer left and top
x = Conv2D(conv['filter'],
conv['kernel'],
strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet prefer left and top
name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
return add([skip_connection, x]) if skip else x
Example #5
| Source File: yolo.py From ImageAI with MIT License | 6 votes |
|
def _conv_block(inp, convs, do_skip=True):
x = inp
count = 0
for conv in convs:
if count == (len(convs) - 2) and do_skip:
skip_connection = x
count += 1
if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # unlike tensorflow darknet prefer left and top paddings
x = Conv2D(conv['filter'],
conv['kernel'],
strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else 'same', # unlike tensorflow darknet prefer left and top paddings
name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
return add([skip_connection, x]) if do_skip else x
Example #6
| Source File: yolo.py From keras-yolo3 with MIT License | 6 votes |
|
def _conv_block(inp, convs, do_skip=True):
x = inp
count = 0
for conv in convs:
if count == (len(convs) - 2) and do_skip:
skip_connection = x
count += 1
if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # unlike tensorflow darknet prefer left and top paddings
x = Conv2D(conv['filter'],
conv['kernel'],
strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else 'same', # unlike tensorflow darknet prefer left and top paddings
name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
return add([skip_connection, x]) if do_skip else x
Example #7
| Source File: yolo3_one_file_to_detect_them_all.py From keras-yolo3 with MIT License | 6 votes |
|
def _conv_block(inp, convs, skip=True):
x = inp
count = 0
for conv in convs:
if count == (len(convs) - 2) and skip:
skip_connection = x
count += 1
if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet prefer left and top
x = Conv2D(conv['filter'],
conv['kernel'],
strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet prefer left and top
name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
return add([skip_connection, x]) if skip else x
Example #8
| Source File: neural_network.py From ReinforcementLearning with Apache License 2.0 | 6 votes |
|
def value_head(self, x):
x = self.conv_layer(x, 1, (1, 1))
x = Flatten()(x)
x = Dense(
self.value_head_hidden_layer_size,
use_bias = False,
activation = 'linear',
kernel_regularizer = regularizers.l2(self.reg_const)
)(x)
x = LeakyReLU()(x)
x = Dense(
1,
use_bias = False,
activation = 'tanh',
kernel_regularizer = regularizers.l2(self.reg_const),
name = 'value_head'
)(x)
return x
Example #9
| Source File: yolov3_weights_to_keras.py From ai-platform with MIT License | 6 votes |
|
def _conv_block(inp, convs, skip=True):
x = inp
count = 0
len_convs = len(convs)
for conv in convs:
if count == (len_convs - 2) and skip:
skip_connection = x
count += 1
if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet prefer left and top
x = Conv2D(conv['filter'],
conv['kernel'],
strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet prefer left and top
name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
return add([skip_connection, x]) if skip else x
#SPP block uses three pooling layers of sizes [5, 9, 13] with strides one and all outputs together with the input are concatenated to be fed
#to the FC block
Example #10
| Source File: bigan.py From Keras-BiGAN with MIT License | 6 votes |
|
def encoder(self):
if self.E:
return self.E
inp = Input(shape = [im_size, im_size, 3])
x = d_block(inp, 1 * cha) #64
x = d_block(x, 2 * cha) #32
x = d_block(x, 3 * cha) #16
x = d_block(x, 4 * cha) #8
x = d_block(x, 8 * cha) #4
x = d_block(x, 16 * cha, p = False) #4
x = Flatten()(x)
x = Dense(16 * cha, kernel_initializer = 'he_normal')(x)
x = LeakyReLU(0.2)(x)
x = Dense(latent_size, kernel_initializer = 'he_normal', bias_initializer = 'zeros')(x)
self.E = Model(inputs = inp, outputs = x)
return self.E
Example #11
| Source File: bigan.py From Keras-BiGAN with MIT License | 6 votes |
|
def g_block(inp, fil, u = True):
if u:
out = UpSampling2D(interpolation = 'bilinear')(inp)
else:
out = Activation('linear')(inp)
skip = Conv2D(fil, 1, padding = 'same', kernel_initializer = 'he_normal')(out)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
out = LeakyReLU(0.2)(out)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
out = LeakyReLU(0.2)(out)
out = Conv2D(fil, 1, padding = 'same', kernel_initializer = 'he_normal')(out)
out = add([out, skip])
out = LeakyReLU(0.2)(out)
return out
Example #12
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateConv3DTranspose(filters, strides, kernel_size=(4, 4, 2), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
conv2d = Conv3DTranspose(filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
return LeakyReLU()(conv2d)
return f
Example #13
| Source File: stylegan.py From StyleGAN-Keras with MIT License | 5 votes |
|
def d_block(inp, fil, p = True):
route2 = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(inp)
route2 = LeakyReLU(0.01)(route2)
if p:
route2 = AveragePooling2D()(route2)
route2 = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(route2)
out = LeakyReLU(0.01)(route2)
return out
#This object holds the models
Example #14
| Source File: stylegan.py From StyleGAN-Keras with MIT License | 5 votes |
|
def g_block(inp, style, noise, fil, u = True):
b = Dense(fil)(style)
b = Reshape([1, 1, fil])(b)
g = Dense(fil)(style)
g = Reshape([1, 1, fil])(g)
n = Conv2D(filters = fil, kernel_size = 1, padding = 'same', kernel_initializer = 'he_normal')(noise)
if u:
out = UpSampling2D(interpolation = 'bilinear')(inp)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
else:
out = Activation('linear')(inp)
out = AdaInstanceNormalization()([out, b, g])
out = add([out, n])
out = LeakyReLU(0.01)(out)
b = Dense(fil)(style)
b = Reshape([1, 1, fil])(b)
g = Dense(fil)(style)
g = Reshape([1, 1, fil])(g)
n = Conv2D(filters = fil, kernel_size = 1, padding = 'same', kernel_initializer = 'he_normal')(noise)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
out = AdaInstanceNormalization()([out, b, g])
out = add([out, n])
out = LeakyReLU(0.01)(out)
return out
#Convolution, Activation, Pooling, Convolution, Activation
Example #15
| Source File: nn.py From rl-teacher with MIT License | 5 votes |
|
def __init__(self, obs_shape, act_shape, h_size=64):
input_dim = np.prod(obs_shape) + np.prod(act_shape)
self.model = Sequential()
self.model.add(Dense(h_size, input_dim=input_dim))
self.model.add(LeakyReLU())
self.model.add(Dropout(0.5))
self.model.add(Dense(h_size))
self.model.add(LeakyReLU())
self.model.add(Dropout(0.5))
self.model.add(Dense(1))
Example #16
| Source File: DCGAN.py From DCGAN-Keras with MIT License | 5 votes |
|
def build_discriminator(self):
img_shape = (self.img_size[0], self.img_size[1], self.channels)
model = Sequential()
model.add(Conv2D(32, kernel_size=self.kernel_size, strides=2, input_shape=img_shape, padding="same")) # 192x256 -> 96x128
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(64, kernel_size=self.kernel_size, strides=2, padding="same")) # 96x128 -> 48x64
model.add(ZeroPadding2D(padding=((0, 1), (0, 1))))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(BatchNormalization(momentum=0.8))
model.add(Conv2D(128, kernel_size=self.kernel_size, strides=2, padding="same")) # 48x64 -> 24x32
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(BatchNormalization(momentum=0.8))
model.add(Conv2D(256, kernel_size=self.kernel_size, strides=1, padding="same")) # 24x32 -> 12x16
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(512, kernel_size=self.kernel_size, strides=1, padding="same")) # 12x16 -> 6x8
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.summary()
img = Input(shape=img_shape)
validity = model(img)
return Model(img, validity)
Example #17
| Source File: _vae_keras.py From scgen with GNU General Public License v3.0 | 5 votes |
|
def _decoder(self):
"""
Constructs the decoder sub-network of VAE. This function implements the
decoder part of Variational Auto-encoder. It will transform constructed
latent space to the previous space of data with n_dimensions = n_vars.
Parameters
----------
No parameters are needed.
Returns
-------
h: Tensor
A Tensor for last dense layer with the shape of [n_vars, ] to reconstruct data.
"""
h = Dense(800, kernel_initializer=self.init_w, use_bias=False)(self.z)
h = BatchNormalization(axis=1)(h)
h = LeakyReLU()(h)
h = Dropout(self.dropout_rate)(h)
h = Dense(800, kernel_initializer=self.init_w, use_bias=False)(h)
h = BatchNormalization(axis=1)(h)
h = LeakyReLU()(h)
h = Dropout(self.dropout_rate)(h)
# h = Dense(768, kernel_initializer=self.init_w, use_bias=False)(h)
# h = BatchNormalization()(h)
# h = LeakyReLU()(h)
# h = Dropout(self.dropout_rate)(h)
# h = Dense(1024, kernel_initializer=self.init_w, use_bias=False)(h)
# h = BatchNormalization()(h)
# h = LeakyReLU()(h)
# h = Dropout(self.dropout_rate)(h)
h = Dense(self.x_dim, kernel_initializer=self.init_w, use_bias=True)(h)
self.decoder_model = Model(inputs=self.z, outputs=h, name="decoder")
return h
Example #18
| Source File: videograph.py From videograph with GNU General Public License v3.0 | 5 votes |
|
def node_attention(x, n, n_channels_in, activation_type='softmax'):
activation_types = ['relu', 'softmax', 'sigmoid']
assert activation_type in activation_types, 'Sorry, unknown activation type: %s' % (activation_type)
# expand for multiplication
n = ExpandDimsLayer(axis=0)(n)
# phi path (Q) or (x)
x = BatchNormalization()(x)
phi = x # (None, 64, 1024)
# theta path (K) or (c)
theta = BatchNormalization()(n) # (1, 100, 1024)
theta = Conv1D(n_channels_in, 1, padding='same', name='node_embedding')(theta) # (1, 100, 1024)
# f path (theta and phi) or (Q and K)
f = Lambda(__tensor_product)([phi, theta]) # (None, 7, 7, 100, 64)
f = TransposeLayer((0, 1, 2, 4, 3))(f) # (None, 7, 7, 64, 100)
f = BatchNormalization()(f)
if activation_type == 'relu':
f = LeakyReLU(alpha=0.2, name='node_attention')(f)
f = BatchNormalization()(f)
elif activation_type == 'softmax':
f = Activation('softmax', name='node_attention')(f)
elif activation_type == 'sigmoid':
f = Activation('sigmoid', name='node_attention')(f)
else:
raise Exception('sorry, unknown activation type')
f = TransposeLayer((0, 1, 2, 4, 3))(f) # (None, 7, 7, 100, 64)
# g path (V)
g = BatchNormalization()(n)
y = Lambda(__tensor_multiplication, name='node_attenative')([f, g]) # (N, 100, 64, 7, 7, 1024)
y = BatchNormalization()(y)
y = LeakyReLU(alpha=0.2)(y)
return y
Example #19
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateLeakyReluBNConv2D(filters, kernel_size=(3, 3), strides=(1, 1), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
output = Conv2D(filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
output = BatchNormalization(axis=1)(output)
return LeakyReLU()(output)
return f
Example #20
| Source File: motion_VAEGAN2D.py From CNNArt with Apache License 2.0 | 5 votes |
|
def build_discriminator(patchSize):
def d_block(layer_input, filters, strides=1, bn=True):
"""Discriminator layer"""
d = Conv2D(filters, kernel_size=3, strides=strides, padding='same')(layer_input)
d = LeakyReLU(alpha=0.2)(d)
if bn:
d = BatchNormalization(momentum=0.8, axis=1)(d)
return d
# define number of filters
df = 32
# Input image
d0 = Input(shape=(1, patchSize[0], patchSize[1]))
d1 = d_block(d0, df, bn=False)
d2 = d_block(d1, df, strides=2)
d3 = d_block(d2, df*2)
d4 = d_block(d3, df*2, strides=2)
d5 = d_block(d4, df*4)
d6 = d_block(d5, df*4, strides=2)
flat = Flatten()(d6)
d7 = Dense(df*8)(flat)
d8 = LeakyReLU(alpha=0.2)(d7)
validity = Dense(1, activation='sigmoid')(d8)
return Model(d0, validity)
Example #21
| Source File: deep_residual_learning_blocks.py From CNNArt with Apache License 2.0 | 5 votes |
|
def identity_block_3D(input_tensor, filters, kernel_size=(3, 3, 3), stage=0, block=0, se_enabled=False, se_ratio=16):
numFilters1, numFilters2 = filters
if K.image_data_format() == 'channels_last':
bn_axis = -1
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + '_' + str(block) + '_branch'
bn_name_base = 'bn' + str(stage) + '_' + str(block) + '_branch'
x = Conv3D(filters=numFilters1,
kernel_size=kernel_size,
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal',
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = LeakyReLU(alpha=0.01)(x)
x = Conv3D(filters=numFilters2,
kernel_size=kernel_size,
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal',
name=conv_name_base + '2b')(x)
# squeeze and excitation block
if se_enabled:
x = squeeze_excitation_block_3D(x, ratio=se_ratio)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Add()([x, input_tensor])
x = LeakyReLU(alpha=0.01)(x)
return x
Example #22
| Source File: deep_residual_learning_blocks.py From CNNArt with Apache License 2.0 | 5 votes |
|
def identity_block_3D(input_tensor, filters, kernel_size=(3, 3, 3), stage=0, block=0, se_enabled=False, se_ratio=16):
numFilters1, numFilters2 = filters
if K.image_data_format() == 'channels_last':
bn_axis = -1
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + '_' + str(block) + '_branch'
bn_name_base = 'bn' + str(stage) + '_' + str(block) + '_branch'
x = Conv3D(filters=numFilters1,
kernel_size=kernel_size,
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal',
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = LeakyReLU(alpha=0.01)(x)
x = Conv3D(filters=numFilters2,
kernel_size=kernel_size,
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal',
name=conv_name_base + '2b')(x)
# squeeze and excitation block
if se_enabled:
x = squeeze_excitation_block_3D(x, ratio=se_ratio)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Add()([x, input_tensor])
x = LeakyReLU(alpha=0.01)(x)
return x
Example #23
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateConv2D_ResBlock(filters, kernel_size=(3, 3), strides=(2, 2), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
output = Conv2D(filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
skip = LeakyReLU()(output)
output = Conv2D(filters,
kernel_size=kernel_size,
strides=(1, 1),
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(skip)
output = LeakyReLU()(output)
output = Conv2D(filters,
kernel_size=kernel_size,
strides=(1, 1),
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(output)
output = LeakyReLU()(output)
output = add([skip, output])
return output
return f
Example #24
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateConv2DBNTranspose(filters, strides, kernel_size=(3, 3), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
output = Conv2DTranspose(filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
output = BatchNormalization(axis=1)(output)
return LeakyReLU()(output)
return f
Example #25
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateConv2DTranspose(filters, strides, kernel_size=(3, 3), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
conv2d = Conv2DTranspose(filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
return LeakyReLU()(conv2d)
return f
Example #26
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateConv3DTranspose_ResBlock(filters, kernel_size=(3, 3, 1), strides=(2, 2, 1), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
output = Conv3DTranspose(filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
skip = LeakyReLU()(output)
output = Conv3DTranspose(filters,
kernel_size=kernel_size,
strides=(1, 1, 1),
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(skip)
output = LeakyReLU()(output)
output = Conv3DTranspose(filters,
kernel_size=kernel_size,
strides=(1, 1, 1),
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(output)
output = LeakyReLU()(output)
output = add([skip, output])
return output
return f
Example #27
| Source File: mixed-stylegan.py From StyleGAN-Keras with MIT License | 5 votes |
|
def g_block(inp, style, noise, fil, u = True):
b = Dense(fil, kernel_initializer = 'he_normal', bias_initializer = 'ones')(style)
b = Reshape([1, 1, fil])(b)
g = Dense(fil, kernel_initializer = 'he_normal', bias_initializer = 'zeros')(style)
g = Reshape([1, 1, fil])(g)
n = Conv2D(filters = fil, kernel_size = 1, padding = 'same', kernel_initializer = 'zeros', bias_initializer = 'zeros')(noise)
if u:
out = UpSampling2D(interpolation = 'bilinear')(inp)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal', bias_initializer = 'zeros')(out)
else:
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal', bias_initializer = 'zeros')(inp)
out = add([out, n])
out = AdaInstanceNormalization()([out, b, g])
out = LeakyReLU(0.01)(out)
b = Dense(fil, kernel_initializer = 'he_normal', bias_initializer = 'ones')(style)
b = Reshape([1, 1, fil])(b)
g = Dense(fil, kernel_initializer = 'he_normal', bias_initializer = 'zeros')(style)
g = Reshape([1, 1, fil])(g)
n = Conv2D(filters = fil, kernel_size = 1, padding = 'same', kernel_initializer = 'zeros', bias_initializer = 'zeros')(noise)
out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal', bias_initializer = 'zeros')(out)
out = add([out, n])
out = AdaInstanceNormalization()([out, b, g])
out = LeakyReLU(0.01)(out)
return out
#Convolution, Activation, Pooling, Convolution, Activation
Example #28
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateLeakyReluConv3D(filters, kernel_size=(3, 3, 3), strides=(1, 1, 1), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
conv3d = Conv3D(filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
return LeakyReLU()(conv3d)
return f
Example #29
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateLeakyReluBNConv3D(filters, kernel_size, strides, padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
conv3d = Conv3D(filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
return BatchNormalization(axis=1)(LeakyReLU()(conv3d))
return f
Example #30
| Source File: network.py From CNNArt with Apache License 2.0 | 5 votes |
|
def fCreateConv2DTranspose_ResBlock(filters, kernel_size=(3, 3), strides=(2, 2), padding='same'):
l1_reg = 0
l2_reg = 1e-6
def f(inputs):
output = Conv2DTranspose(filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(inputs)
skip = LeakyReLU()(output)
output = Conv2D(filters,
kernel_size=kernel_size,
strides=(1, 1),
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(skip)
output = LeakyReLU()(output)
output = Conv2D(filters,
kernel_size=kernel_size,
strides=(1, 1),
padding=padding,
kernel_regularizer=l1_l2(l1_reg, l2_reg))(output)
output = LeakyReLU()(output)
output = add([skip, output])
return output
return f
