Python chainer.functions.clipped_relu() Examples
The following are 10
code examples of chainer.functions.clipped_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
chainer.functions
, or try the search function
.
.
Example #1
| Source File: basic_cnn_tail.py From SeRanet with MIT License | 6 votes |
|
def __call__(self, x, t=None):
self.clear()
#x = Variable(x_data) # x_data.astype(np.float32)
h = F.leaky_relu(self.conv1(x), slope=0.1)
h = F.leaky_relu(self.conv2(h), slope=0.1)
h = F.leaky_relu(self.conv3(h), slope=0.1)
h = F.leaky_relu(self.conv4(h), slope=0.1)
h = F.leaky_relu(self.conv5(h), slope=0.1)
h = F.leaky_relu(self.conv6(h), slope=0.1)
h = F.clipped_relu(self.conv7(h), z=1.0)
if self.train:
self.loss = F.mean_squared_error(h, t)
return self.loss
else:
return h
Example #2
| Source File: test_clipped_relu.py From chainer with MIT License | 5 votes |
|
def forward(self, inputs, device):
x, = inputs
y = functions.clipped_relu(x, self.z)
return y,
Example #3
| Source File: test_clipped_relu.py From chainer with MIT License | 5 votes |
|
def forward(self):
x = chainer.Variable(self.x)
return functions.clipped_relu(x, self.z)
Example #4
| Source File: basic_cnn_small.py From SeRanet with MIT License | 5 votes |
|
def __call__(self, x, t=None):
self.clear()
h = F.leaky_relu(self.conv1(x), slope=0.1)
h = F.leaky_relu(self.conv2(h), slope=0.1)
#h = F.leaky_relu(self.conv3(h), slope=0.1)
#h = F.leaky_relu(self.conv4(h), slope=0.1)
h = F.clipped_relu(self.conv3(h), z=1.0)
if self.train:
self.loss = F.mean_squared_error(h, t)
return self.loss
else:
return h
Example #5
| Source File: seranet_v1.py From SeRanet with MIT License | 5 votes |
|
def __call__(self, x, t=None):
self.clear()
h1 = F.leaky_relu(self.conv1(x), slope=0.1)
h1 = F.leaky_relu(self.conv2(h1), slope=0.1)
h1 = F.leaky_relu(self.conv3(h1), slope=0.1)
h2 = self.seranet_v1_crbm(x)
# Fusion
h12 = F.concat((h1, h2), axis=1)
lu = F.leaky_relu(self.convlu6(h12), slope=0.1)
lu = F.leaky_relu(self.convlu7(lu), slope=0.1)
lu = F.leaky_relu(self.convlu8(lu), slope=0.1)
ru = F.leaky_relu(self.convru6(h12), slope=0.1)
ru = F.leaky_relu(self.convru7(ru), slope=0.1)
ru = F.leaky_relu(self.convru8(ru), slope=0.1)
ld = F.leaky_relu(self.convld6(h12), slope=0.1)
ld = F.leaky_relu(self.convld7(ld), slope=0.1)
ld = F.leaky_relu(self.convld8(ld), slope=0.1)
rd = F.leaky_relu(self.convrd6(h12), slope=0.1)
rd = F.leaky_relu(self.convrd7(rd), slope=0.1)
rd = F.leaky_relu(self.convrd8(rd), slope=0.1)
# Splice
h = CF.splice(lu, ru, ld, rd)
h = F.leaky_relu(self.conv9(h), slope=0.1)
h = F.leaky_relu(self.conv10(h), slope=0.1)
h = F.leaky_relu(self.conv11(h), slope=0.1)
h = F.clipped_relu(self.conv12(h), z=1.0)
if self.train:
self.loss = F.mean_squared_error(h, t)
return self.loss
else:
return h
Example #6
| Source File: basic_cnn_head.py From SeRanet with MIT License | 5 votes |
|
def __call__(self, x, t=None):
self.clear()
h = F.leaky_relu(self.conv1(x), slope=0.1)
h = F.leaky_relu(self.conv2(h), slope=0.1)
h = F.leaky_relu(self.conv3(h), slope=0.1)
h = F.leaky_relu(self.conv4(h), slope=0.1)
h = F.leaky_relu(self.conv5(h), slope=0.1)
h = F.leaky_relu(self.conv6(h), slope=0.1)
h = F.clipped_relu(self.conv7(h), z=1.0)
if self.train:
self.loss = F.mean_squared_error(h, t)
return self.loss
else:
return h
Example #7
| Source File: basic_cnn_middle.py From SeRanet with MIT License | 5 votes |
|
def __call__(self, x, t=None):
self.clear()
h = F.leaky_relu(self.conv1(x), slope=0.1)
h = F.leaky_relu(self.conv2(h), slope=0.1)
h = F.leaky_relu(self.conv3(h), slope=0.1)
h = F.leaky_relu(self.conv4(h), slope=0.1)
h = F.leaky_relu(self.conv5(h), slope=0.1)
h = F.leaky_relu(self.conv6(h), slope=0.1)
h = F.clipped_relu(self.conv7(h), z=1.0)
if self.train:
self.loss = F.mean_squared_error(h, t)
return self.loss
else:
return h
Example #8
| Source File: net.py From PredNet with Apache License 2.0 | 5 votes |
|
def __call__(self, x):
for nth in range(self.layers):
if getattr(self, 'P' + str(nth)) is None:
setattr(self, 'P' + str(nth), variable.Variable(
self.xp.zeros(self.sizes[nth], dtype=x.data.dtype),
volatile='auto'))
E = [None] * self.layers
for nth in range(self.layers):
if nth == 0:
E[nth] = F.concat((F.relu(x - getattr(self, 'P' + str(nth))),
F.relu(getattr(self, 'P' + str(nth)) - x)))
else:
A = F.max_pooling_2d(F.relu(getattr(self, 'ConvA' + str(nth))(E[nth - 1])), 2, stride = 2)
E[nth] = F.concat((F.relu(A - getattr(self, 'P' + str(nth))),
F.relu(getattr(self, 'P' + str(nth)) - A)))
R = [None] * self.layers
for nth in reversed(range(self.layers)):
if nth == self.layers - 1:
R[nth] = getattr(self, 'ConvLSTM' + str(nth))((E[nth],))
else:
upR = F.unpooling_2d(R[nth + 1], 2, stride = 2, cover_all=False)
R[nth] = getattr(self, 'ConvLSTM' + str(nth))((E[nth], upR))
if nth == 0:
setattr(self, 'P' + str(nth), F.clipped_relu(getattr(self, 'ConvP' + str(nth))(R[nth]), 1.0))
else:
setattr(self, 'P' + str(nth), F.relu(getattr(self, 'ConvP' + str(nth))(R[nth])))
return self.P0
Example #9
| Source File: expanded_conv_2d.py From chainercv with MIT License | 4 votes |
|
def __init__(self,
in_channels,
out_channels,
expansion_size=expand_input_by_factor(6),
expand_pad='SAME',
depthwise_stride=1,
depthwise_ksize=3,
depthwise_pad='SAME',
project_pad='SAME',
initialW=None,
bn_kwargs={}):
super(ExpandedConv2D, self).__init__()
with self.init_scope():
if callable(expansion_size):
self.inner_size = expansion_size(num_inputs=in_channels)
else:
self.inner_size = expansion_size
def relu6(x):
return clipped_relu(x, 6.)
if self.inner_size > in_channels:
self.expand = TFConv2DBNActiv(
in_channels,
self.inner_size,
ksize=1,
pad=expand_pad,
nobias=True,
initialW=initialW,
bn_kwargs=bn_kwargs,
activ=relu6)
depthwise_in_channels = self.inner_size
else:
depthwise_in_channels = in_channels
self.depthwise = TFConv2DBNActiv(
depthwise_in_channels,
self.inner_size,
ksize=depthwise_ksize,
stride=depthwise_stride,
pad=depthwise_pad,
nobias=True,
initialW=initialW,
groups=depthwise_in_channels,
bn_kwargs=bn_kwargs,
activ=relu6)
self.project = TFConv2DBNActiv(
self.inner_size,
out_channels,
ksize=1,
pad=project_pad,
nobias=True,
initialW=initialW,
bn_kwargs=bn_kwargs,
activ=None)
Example #10
| Source File: model.py From brain_segmentation with MIT License | 4 votes |
|
def __call__(self, x, train=False):
"""
calculate output of VoxResNet given input x
Parameters
----------
x : (batch_size, in_channels, xlen, ylen, zlen) ndarray
image to perform semantic segmentation
Returns
-------
proba: (batch_size, n_classes, xlen, ylen, zlen) ndarray
probability of each voxel belonging each class
elif train=True, returns list of logits
"""
with chainer.using_config("train", train):
h = self.conv1a(x)
h = F.relu(self.bnorm1a(h))
h = self.conv1b(h)
c1 = F.clipped_relu(self.c1deconv(h))
c1 = self.c1conv(c1)
h = F.relu(self.bnorm1b(h))
h = self.conv1c(h)
h = self.voxres2(h)
h = self.voxres3(h)
c2 = F.clipped_relu(self.c2deconv(h))
c2 = self.c2conv(c2)
h = F.relu(self.bnorm3(h))
h = self.conv4(h)
h = self.voxres5(h)
h = self.voxres6(h)
c3 = F.clipped_relu(self.c3deconv(h))
c3 = self.c3conv(c3)
h = F.relu(self.bnorm6(h))
h = self.conv7(h)
h = self.voxres8(h)
h = self.voxres9(h)
c4 = F.clipped_relu(self.c4deconv(h))
c4 = self.c4conv(c4)
c = c1 + c2 + c3 + c4
if train:
return [c1, c2, c3, c4, c]
else:
return F.softmax(c)
