Python tensorflow.keras.layers.ReLU() Examples
The following are 30
code examples of tensorflow.keras.layers.ReLU().
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
tensorflow.keras.layers
, or try the search function
.
.
Example #1
| Source File: model.py From DexiNed with MIT License | 7 votes |
|
def __init__(self, out_features,**kwargs):
super(_DenseLayer, self).__init__(**kwargs)
k_reg = None if w_decay is None else l2(w_decay)
self.layers = []
self.layers.append(tf.keras.Sequential(
[
layers.ReLU(),
layers.Conv2D(
filters=out_features, kernel_size=(3,3), strides=(1,1), padding='same',
use_bias=True, kernel_initializer=weight_init,
kernel_regularizer=k_reg),
layers.BatchNormalization(),
layers.ReLU(),
layers.Conv2D(
filters=out_features, kernel_size=(3,3), strides=(1,1), padding='same',
use_bias=True, kernel_initializer=weight_init,
kernel_regularizer=k_reg),
layers.BatchNormalization(),
])) # first relu can be not needed
Example #2
| Source File: layers.py From CartoonGan-tensorflow with Apache License 2.0 | 6 votes |
|
def __init__(self,
filters,
kernel_size,
norm_type="instance",
pad_type="constant",
**kwargs):
super(ResBlock, self).__init__(name="ResBlock")
padding = (kernel_size - 1) // 2
padding = (padding, padding)
self.model = tf.keras.models.Sequential()
self.model.add(get_padding(pad_type, padding))
self.model.add(Conv2D(filters, kernel_size))
self.model.add(get_norm(norm_type))
self.model.add(ReLU())
self.model.add(get_padding(pad_type, padding))
self.model.add(Conv2D(filters, kernel_size))
self.model.add(get_norm(norm_type))
self.add = Add()
Example #3
| Source File: squeezenet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
padding,
data_format="channels_last",
**kwargs):
super(FireConv, self).__init__(**kwargs)
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
padding=padding,
data_format=data_format,
name="conv")
self.activ = nn.ReLU()
Example #4
| Source File: polynet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
num_blocks,
data_format="channels_last",
**kwargs):
super(PolyConv, self).__init__(**kwargs)
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
use_bias=False,
data_format=data_format,
name="conv")
self.bns = []
for i in range(num_blocks):
self.bns.append(BatchNorm(
data_format=data_format,
name="bn{}".format(i + 1)))
self.activ = nn.ReLU()
Example #5
| Source File: polynet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
scale,
res_block,
num_blocks,
pre_block,
data_format="channels_last",
**kwargs):
super(PolyResidual, self).__init__(**kwargs)
assert (num_blocks >= 1)
self.scale = scale
self.pre_block = pre_block(
num_blocks=num_blocks,
data_format=data_format,
name="pre_block")
self.res_blocks = [res_block(
data_format=data_format,
name="res_block{}".format(i + 1)) for i in range(num_blocks)]
self.activ = nn.ReLU()
Example #6
| Source File: model.py From DexiNed with MIT License | 6 votes |
|
def __init__(self, mid_features, out_features=None, stride=(1,1),
use_bn=True,use_act=True,**kwargs):
super(DoubleConvBlock, self).__init__(**kwargs)
self.use_bn =use_bn
self.use_act =use_act
out_features = mid_features if out_features is None else out_features
k_reg = None if w_decay is None else l2(w_decay)
self.conv1 = layers.Conv2D(
filters=mid_features, kernel_size=(3, 3), strides=stride, padding='same',
use_bias=True, kernel_initializer=weight_init,
kernel_regularizer=k_reg)
self.bn1 = layers.BatchNormalization()
self.conv2 = layers.Conv2D(
filters=out_features, kernel_size=(3, 3), padding='same',strides=(1,1),
use_bias=True, kernel_initializer=weight_init,
kernel_regularizer=k_reg)
self.bn2 = layers.BatchNormalization()
self.relu = layers.ReLU()
Example #7
| Source File: sknet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
strides,
data_format="channels_last",
**kwargs):
super(SKNetUnit, self).__init__(**kwargs)
self.resize_identity = (in_channels != out_channels) or (strides != 1)
self.body = SKNetBottleneck(
in_channels=in_channels,
out_channels=out_channels,
strides=strides,
data_format=data_format,
name="body")
if self.resize_identity:
self.identity_conv = conv1x1_block(
in_channels=in_channels,
out_channels=out_channels,
strides=strides,
activation=None,
data_format=data_format,
name="identity_conv")
self.activ = nn.ReLU()
Example #8
| Source File: dla.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
residual,
data_format="channels_last",
**kwargs):
super(DLARoot, self).__init__(**kwargs)
self.residual = residual
self.data_format = data_format
self.conv = conv1x1_block(
in_channels=in_channels,
out_channels=out_channels,
activation=None,
data_format=data_format,
name="conv")
self.activ = nn.ReLU()
Example #9
| Source File: xception.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
data_format="channels_last",
**kwargs):
super(XceptionFinalBlock, self).__init__(**kwargs)
self.conv1 = dws_conv3x3_block(
in_channels=1024,
out_channels=1536,
activate=False,
data_format=data_format,
name="conv1")
self.conv2 = dws_conv3x3_block(
in_channels=1536,
out_channels=2048,
activate=True,
data_format=data_format,
name="conv2")
self.activ = nn.ReLU()
self.pool = AvgPool2d(
pool_size=10,
strides=1,
data_format=data_format,
name="pool")
Example #10
| Source File: layers.py From CartoonGan-tensorflow with Apache License 2.0 | 6 votes |
|
def __init__(self,
filters,
kernel_size,
stride=1,
norm_type="instance",
pad_type="constant",
**kwargs):
super(ConvBlock, self).__init__(name="ConvBlock")
padding = (kernel_size - 1) // 2
padding = (padding, padding)
self.model = tf.keras.models.Sequential()
self.model.add(get_padding(pad_type, padding))
self.model.add(Conv2D(filters, kernel_size, stride))
self.model.add(get_padding(pad_type, padding))
self.model.add(Conv2D(filters, kernel_size))
self.model.add(get_norm(norm_type))
self.model.add(ReLU())
Example #11
| Source File: layers.py From CartoonGan-tensorflow with Apache License 2.0 | 6 votes |
|
def __init__(self,
filters, # NOTE: will be filters // 2
norm_type="instance",
pad_type="constant",
**kwargs):
super(DownShuffleUnitV2, self).__init__(name="DownShuffleUnitV2")
filters //= 2
self.r_model = tf.keras.models.Sequential([
Conv2D(filters, 1, use_bias=False),
get_norm(norm_type),
ReLU(),
DepthwiseConv2D(3, 2, 'same', use_bias=False),
get_norm(norm_type),
Conv2D(filters, 1, use_bias=False),
])
self.l_model = tf.keras.models.Sequential([
DepthwiseConv2D(3, 2, 'same', use_bias=False),
get_norm(norm_type),
Conv2D(filters, 1, use_bias=False),
])
self.bn_act = tf.keras.models.Sequential([
get_norm(norm_type),
ReLU(),
])
Example #12
| Source File: inceptionv4.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
data_format="channels_last",
**kwargs):
super(InceptConv, self).__init__(**kwargs)
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
use_bias=False,
data_format=data_format,
name="conv")
self.bn = BatchNorm(
momentum=0.1,
epsilon=1e-3,
data_format=data_format,
name="bn")
self.activ = nn.ReLU()
Example #13
| Source File: dpn.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
groups,
data_format="channels_last",
**kwargs):
super(DPNConv, self).__init__(**kwargs)
self.bn = dpn_batch_norm(
channels=in_channels,
data_format=data_format,
name="bn")
self.activ = nn.ReLU()
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
groups=groups,
use_bias=False,
data_format=data_format,
name="conv")
Example #14
| Source File: wrn.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
activate,
data_format="channels_last",
**kwargs):
super(WRNConv, self).__init__(**kwargs)
self.activate = activate
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
use_bias=True,
data_format=data_format,
name="conv")
if self.activate:
self.activ = nn.ReLU()
Example #15
| Source File: preresnet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
data_format="channels_last",
**kwargs):
super(PreResInitBlock, self).__init__(**kwargs)
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=7,
strides=2,
padding=3,
use_bias=False,
data_format=data_format,
name="conv")
self.bn = BatchNorm(
data_format=data_format,
name="bn")
self.activ = nn.ReLU()
self.pool = MaxPool2d(
pool_size=3,
strides=2,
padding=1,
name="pool")
Example #16
| Source File: nasnet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
data_format="channels_last",
**kwargs):
super(NasPathBlock, self).__init__(**kwargs)
self.data_format = data_format
mid_channels = out_channels // 2
self.activ = nn.ReLU()
self.path1 = NasPathBranch(
in_channels=in_channels,
out_channels=mid_channels,
data_format=data_format,
name="path1")
self.path2 = NasPathBranch(
in_channels=in_channels,
out_channels=mid_channels,
extra_padding=True,
data_format=data_format,
name="path2")
self.bn = nasnet_batch_norm(
channels=out_channels,
data_format=data_format,
name="bn")
Example #17
| Source File: layers.py From CartoonGan-tensorflow with Apache License 2.0 | 6 votes |
|
def __init__(self,
filters, # NOTE: will be filters // 2
norm_type="instance",
pad_type="constant",
**kwargs):
super(BasicShuffleUnitV2, self).__init__(name="BasicShuffleUnitV2")
filters //= 2
self.model = tf.keras.models.Sequential([
Conv2D(filters, 1, use_bias=False),
get_norm(norm_type),
ReLU(),
DepthwiseConv2D(3, padding='same', use_bias=False),
get_norm(norm_type),
Conv2D(filters, 1, use_bias=False),
get_norm(norm_type),
ReLU(),
])
Example #18
| Source File: nasnet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
groups,
data_format="channels_last",
**kwargs):
super(NasConv, self).__init__(**kwargs)
self.activ = nn.ReLU()
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
groups=groups,
use_bias=False,
data_format=data_format,
name="conv")
self.bn = nasnet_batch_norm(
channels=out_channels,
data_format=data_format,
name="bn")
Example #19
| Source File: pyramidnet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
data_format="channels_last",
**kwargs):
super(PyrInitBlock, self).__init__(**kwargs)
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=7,
strides=2,
padding=3,
use_bias=False,
data_format=data_format,
name="conv")
self.bn = BatchNorm(
data_format=data_format,
name="bn")
self.activ = nn.ReLU()
self.pool = MaxPool2d(
pool_size=3,
strides=2,
padding=1,
data_format=data_format,
name="pool")
Example #20
| Source File: diracnetv2.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
data_format="channels_last",
**kwargs):
super(DiracConv, self).__init__(**kwargs)
self.activ = nn.ReLU()
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
use_bias=True,
data_format=data_format,
name="conv")
Example #21
| Source File: shufflenet.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
data_format="channels_last",
**kwargs):
super(ShuffleInitBlock, self).__init__(**kwargs)
self.conv = conv3x3(
in_channels=in_channels,
out_channels=out_channels,
strides=2,
data_format=data_format,
name="conv")
self.bn = BatchNorm(
# in_channels=out_channels,
data_format=data_format,
name="bn")
self.activ = nn.ReLU()
self.pool = MaxPool2d(
pool_size=3,
strides=2,
padding=1,
data_format=data_format,
name="pool")
Example #22
| Source File: xception.py From imgclsmob with MIT License | 6 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
activate,
data_format="channels_last",
**kwargs):
super(DwsConvBlock, self).__init__(**kwargs)
self.activate = activate
if self.activate:
self.activ = nn.ReLU()
self.conv = DwsConv(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
name="conv")
self.bn = BatchNorm(
data_format=data_format,
name="bn")
Example #23
| Source File: module.py From Centernet-Tensorflow2.0 with Apache License 2.0 | 5 votes |
|
def convblock(inputs, outchannels, kernel_size):
x = layers.Conv2D(outchannels, kernel_size, padding='same', use_bias=False)(inputs)
x = layers.ReLU(max_value=6)(x)
out = layers.BatchNormalization()(x)
return out
Example #24
| Source File: basic.py From autokeras with MIT License | 5 votes |
|
def build(self, hp, inputs=None):
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
output_node = reduction.Flatten().build(hp, output_node)
num_layers = self.num_layers or hp.Choice('num_layers', [1, 2, 3], default=2)
use_batchnorm = self.use_batchnorm
if use_batchnorm is None:
use_batchnorm = hp.Boolean('use_batchnorm', default=False)
if self.dropout_rate is not None:
dropout_rate = self.dropout_rate
else:
dropout_rate = hp.Choice('dropout_rate', [0.0, 0.25, 0.5], default=0)
for i in range(num_layers):
units = hp.Choice(
'units_{i}'.format(i=i),
[16, 32, 64, 128, 256, 512, 1024],
default=32)
output_node = layers.Dense(units)(output_node)
if use_batchnorm:
output_node = layers.BatchNormalization()(output_node)
output_node = layers.ReLU()(output_node)
if dropout_rate > 0:
output_node = layers.Dropout(dropout_rate)(output_node)
return output_node
Example #25
| Source File: ibnbresnet.py From imgclsmob with MIT License | 5 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
dilation=1,
groups=1,
use_bias=False,
activate=True,
data_format="channels_last",
**kwargs):
super(IBNbConvBlock, self).__init__(**kwargs)
self.activate = activate
self.conv = Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
dilation=dilation,
groups=groups,
use_bias=use_bias,
data_format=data_format,
name="conv")
self.inst_norm = InstanceNorm(
scale=True,
data_format=data_format,
name="inst_norm")
if self.activate:
self.activ = nn.ReLU()
Example #26
| Source File: ibnbresnet.py From imgclsmob with MIT License | 5 votes |
|
def __init__(self,
in_channels,
out_channels,
strides,
use_inst_norm,
data_format="channels_last",
**kwargs):
super(IBNbResUnit, self).__init__(**kwargs)
self.use_inst_norm = use_inst_norm
self.resize_identity = (in_channels != out_channels) or (strides != 1)
self.body = ResBottleneck(
in_channels=in_channels,
out_channels=out_channels,
strides=strides,
conv1_stride=False,
data_format=data_format,
name="body")
if self.resize_identity:
self.identity_conv = conv1x1_block(
in_channels=in_channels,
out_channels=out_channels,
strides=strides,
activation=None,
data_format=data_format,
name="identity_conv")
if self.use_inst_norm:
self.inst_norm = InstanceNorm(
scale=True,
data_format=data_format,
name="inst_norm")
self.activ = nn.ReLU()
Example #27
| Source File: get_activations_test.py From keract with MIT License | 5 votes |
|
def __init__(self, *args, **kwargs):
super(NestedLayer, self).__init__(*args, **kwargs)
self.fc = Dense(10, name='fc1')
self.relu = ReLU(name='relu')
Example #28
| Source File: get_activations_test.py From keract with MIT License | 5 votes |
|
def __init__(self, *args, **kwargs):
super(NestedModel, self).__init__(*args, **kwargs)
self.fc = Dense(10, name='fc1')
self.relu = ReLU(name='relu')
Example #29
| Source File: nasnet.py From imgclsmob with MIT License | 5 votes |
|
def __init__(self,
in_channels,
out_channels,
kernel_size,
strides,
padding,
extra_padding=False,
data_format="channels_last",
**kwargs):
super(NasDwsConv, self).__init__(**kwargs)
self.extra_padding = extra_padding
self.data_format = data_format
self.activ = nn.ReLU()
self.conv = DwsConv(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
strides=strides,
padding=padding,
use_bias=False,
data_format=data_format,
name="conv")
self.bn = nasnet_batch_norm(
channels=out_channels,
data_format=data_format,
name="bn")
if self.extra_padding:
self.pad = nn.ZeroPadding2D(
padding=((1, 0), (1, 0)),
data_format=data_format)
Example #30
| Source File: model.py From EfficientDet with Apache License 2.0 | 5 votes |
|
def ConvBlock(num_channels, kernel_size, strides, name, freeze_bn=False):
f1 = layers.Conv2D(num_channels, kernel_size=kernel_size, strides=strides, padding='same',
use_bias=True, name='{}_conv'.format(name))
f2 = layers.BatchNormalization(momentum=MOMENTUM, epsilon=EPSILON, name='{}_bn'.format(name))
# f2 = BatchNormalization(freeze=freeze_bn, name='{}_bn'.format(name))
f3 = layers.ReLU(name='{}_relu'.format(name))
return reduce(lambda f, g: lambda *args, **kwargs: g(f(*args, **kwargs)), (f1, f2, f3))
