Python lasagne.layers.ElemwiseSumLayer() Examples
The following are 30
code examples of lasagne.layers.ElemwiseSumLayer().
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
lasagne.layers
, or try the search function
.
.
Example #1
| Source File: layers.py From Neural-Photo-Editor with MIT License | 5 votes |
|
def get_output_for(self,input, **kwargs):
if input.ndim > 2:
input = input.flatten(2)
activation = T.dot(input, self.W*self.weights_mask)
if self.b is not None:
activation = activation + self.b.dimshuffle('x', 0)
return self.nonlinearity(activation)
# Stripped-Down Direct Input masked layer: Combine this with ESL and a masked layer to get a true DIML.
# Consider making this a simultaneous subclass of MaskedLayer and elemwise sum layer for cleanliness
# adopted from M.Germain
Example #2
| Source File: layers.py From gogh-figure with GNU Affero General Public License v3.0 | 5 votes |
|
def residual_block(resnet_in, num_styles=None, num_filters=None, filter_size=3, stride=1): if num_filters == None: num_filters = resnet_in.output_shape[1] conv1 = style_conv_block(resnet_in, num_styles, num_filters, filter_size, stride) conv2 = style_conv_block(conv1, num_styles, num_filters, filter_size, stride, linear) res_block = ElemwiseSumLayer([conv2, resnet_in]) return res_block
Example #3
| Source File: enhance.py From neural-enhance with GNU Affero General Public License v3.0 | 5 votes |
|
def make_block(self, name, input, units):
self.make_layer(name+'-A', input, units, alpha=0.1)
# self.make_layer(name+'-B', self.last_layer(), units, alpha=1.0)
return ElemwiseSumLayer([input, self.last_layer()]) if args.generator_residual else self.last_layer()
Example #4
| Source File: VRN.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDropNoPre(incoming, IB, p):
return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #5
| Source File: VRN.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDrop(incoming, IB, p):
return ESL([IfElseDropLayer(IB,survival_p=p),incoming])
# Non-preactivation stochastically-dropped Resnet Wrapper
Example #6
| Source File: VRN.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResLayer(incoming, IB):
return NL(ESL([IB,incoming]),elu)
# If-else Drop Layer, adopted from Christopher Beckham's recipe:
# https://github.com/Lasagne/Recipes/pull/67
Example #7
| Source File: ensemble_model4.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDrop(incoming, IB, p):
return ESL([IfElseDropLayer(IB,survival_p=p),incoming])
Example #8
| Source File: ensemble_model4.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def get_output_for(self, input, deterministic=False, **kwargs):
if deterministic:
return self.p*input
else:
return theano.ifelse.ifelse(
T.lt(self._srng.uniform( (1,), 0, 1)[0], self.p),
input,
T.zeros(input.shape)
)
# def ResDrop(incoming, IB, p):
# return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #9
| Source File: ensemble_model4.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResLayer(incoming, IB):
return NL(ESL([IB,incoming]),elu)
Example #10
| Source File: ensemble_model5.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDropNoPre(incoming, IB, p):
return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #11
| Source File: ensemble_model5.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDrop(incoming, IB, p):
return ESL([IfElseDropLayer(IB,survival_p=p),incoming])
Example #12
| Source File: ensemble_model5.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResLayer(incoming, IB):
return NL(ESL([IB,incoming]),elu)
Example #13
| Source File: ensemble_model1.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDrop(incoming, IB, p):
return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #14
| Source File: ensemble_model1.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResLayer(incoming, IB):
return NL(ESL([IB,incoming]),elu)
Example #15
| Source File: ensemble_model6.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDrop(incoming, IB, p):
return ESL([IfElseDropLayer(IB,survival_p=p),incoming])
Example #16
| Source File: layers.py From Neural-Photo-Editor with MIT License | 5 votes |
|
def ResLayer(incoming, IB,nonlinearity):
return NL(ESL([IB,incoming]),nonlinearity)
# Inverse autoregressive flow layer
Example #17
| Source File: layers.py From Neural-Photo-Editor with MIT License | 5 votes |
|
def GL(mu,ls):
return([GSL(z_mu,z_ls) for z_mu,z_ls in zip(mu,ls)])
# Convenience function to return a residual layer. It's not really that much more convenient than ESL'ing,
# but I like being able to see when I'm using Residual connections as opposed to Elemwise-sums
Example #18
| Source File: res_net_blocks.py From dcase_task2 with MIT License | 5 votes |
|
def residual_block(l, increase_dim=False, projection=True, first=False):
"""
Create a residual learning building block with two stacked 3x3 convlayers as in paper
'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)
"""
input_num_filters = l.output_shape[1]
if increase_dim:
first_stride = (2, 2)
out_num_filters = input_num_filters * 2
else:
first_stride = (1, 1)
out_num_filters = input_num_filters
if first:
# hacky solution to keep layers correct
bn_pre_relu = l
else:
# contains the BN -> ReLU portion, steps 1 to 2
bn_pre_conv = BatchNormLayer(l)
bn_pre_relu = NonlinearityLayer(bn_pre_conv, rectify)
# contains the weight -> BN -> ReLU portion, steps 3 to 5
conv_1 = batch_norm(ConvLayer(bn_pre_relu, num_filters=out_num_filters, filter_size=(3, 3), stride=first_stride,
nonlinearity=rectify, pad='same', W=he_norm))
# contains the last weight portion, step 6
conv_2 = ConvLayer(conv_1, num_filters=out_num_filters, filter_size=(3, 3), stride=(1, 1), nonlinearity=None,
pad='same', W=he_norm)
# add shortcut connections
if increase_dim:
# projection shortcut, as option B in paper
projection = ConvLayer(l, num_filters=out_num_filters, filter_size=(1, 1), stride=(2, 2), nonlinearity=None,
pad='same', b=None)
block = ElemwiseSumLayer([conv_2, projection])
else:
block = ElemwiseSumLayer([conv_2, l])
return block
Example #19
| Source File: layers.py From Neural-Photo-Editor with MIT License | 5 votes |
|
def MDBLOCK(incoming,num_filters,scales,name,nonlinearity):
return NL(BN(ESL([incoming,
MDCL(NL(BN(MDCL(NL(BN(incoming,name=name+'bnorm0'),nonlinearity),num_filters,scales,name),name=name+'bnorm1'),nonlinearity),
num_filters,
scales,
name+'2')]),name=name+'bnorm2'),nonlinearity)
# Gaussian Sample Layer for VAE from Tencia Lee
Example #20
| Source File: ensemble_model6.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDropNoPre(incoming, IB, p):
return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #21
| Source File: ensemble_model3.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResLayer(incoming, IB):
return NL(ESL([IB,incoming]),elu)
Example #22
| Source File: ensemble_model3.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def get_output_for(self, input, deterministic=False, **kwargs):
if deterministic:
return self.p*input
else:
return theano.ifelse.ifelse(
T.lt(self._srng.uniform( (1,), 0, 1)[0], self.p),
input,
T.zeros(input.shape)
)
# def ResDrop(incoming, IB, p):
# return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #23
| Source File: ensemble_model3.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDrop(incoming, IB, p):
return ESL([IfElseDropLayer(IB,survival_p=p),incoming])
Example #24
| Source File: ensemble_model3.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResDropNoPre(incoming, IB, p):
return NL(ESL([IfElseDropLayer(IB,survival_p=p),incoming]),elu)
Example #25
| Source File: ensemble_model6.py From Generative-and-Discriminative-Voxel-Modeling with MIT License | 5 votes |
|
def ResLayer(incoming, IB):
return NL(ESL([IB,incoming]),elu)
Example #26
| Source File: deep_conv_ae_spsparse_alt26.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_autoencoder_network():
input_var = T.tensor4('input_var');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 180, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 120, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
maskm = batch_norm(layers.Conv2DLayer(prely, 120, filter_size=(1,1), nonlinearity=leaky_rectify));
mask_rep = batch_norm(layers.Conv2DLayer(maskm, 1, filter_size=(1,1), nonlinearity=None), beta=None, gamma=None);
mask_map = SoftThresPerc(mask_rep, perc=99.9, alpha=0.5, beta=init.Constant(0.5), tight=100.0, name="mask_map");
layer = ChInnerProdMerge(feat_map, mask_map, name="encoder");
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.Deconv2DLayer(layer, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
glblf = batch_norm(layers.Conv2DLayer(prely, 100, filter_size=(1,1), nonlinearity=leaky_rectify));
glblf = layers.Pool2DLayer(glblf, pool_size=(5,5), stride=5, mode='average_inc_pad');
glblf = batch_norm(layers.Conv2DLayer(glblf, 64, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Conv2DLayer(glblf, 3, filter_size=(1,1), nonlinearity=rectify), name="global_feature");
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(9,9), stride=5, crop=(2,2), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = layers.Deconv2DLayer(glblf, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
layer = layers.ElemwiseSumLayer([layer, glblf]);
network = ReshapeLayer(layer, ([0], -1));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #27
| Source File: deep_conv_ae_spsparse_alt26_recon.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_autoencoder_network():
input_var = T.tensor4('input_var');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 180, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 120, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
maskm = batch_norm(layers.Conv2DLayer(prely, 120, filter_size=(1,1), nonlinearity=leaky_rectify));
mask_rep = batch_norm(layers.Conv2DLayer(maskm, 1, filter_size=(1,1), nonlinearity=None), beta=None, gamma=None);
mask_map = SoftThresPerc(mask_rep, perc=99.9, alpha=0.5, beta=init.Constant(0.5), tight=100.0, name="mask_map");
layer = ChInnerProdMerge(feat_map, mask_map, name="encoder");
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.Deconv2DLayer(layer, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
glblf = batch_norm(layers.Conv2DLayer(prely, 100, filter_size=(1,1), nonlinearity=leaky_rectify));
glblf = layers.Pool2DLayer(glblf, pool_size=(5,5), stride=5, mode='average_inc_pad');
glblf = batch_norm(layers.Conv2DLayer(glblf, 64, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Conv2DLayer(glblf, 3, filter_size=(1,1), nonlinearity=rectify), name="global_feature");
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(9,9), stride=5, crop=(2,2), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = layers.Deconv2DLayer(glblf, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
layer = layers.ElemwiseSumLayer([layer, glblf]);
network = ReshapeLayer(layer, ([0], -1));
layers.set_all_param_values(network, pickle.load(open(filename_model_ae, 'rb')));
feat_var = lasagne.layers.get_output(feat_map, deterministic=True);
mask_var = lasagne.layers.get_output(mask_map, deterministic=True);
outp_var = lasagne.layers.get_output(network, deterministic=True);
return network, input_var, feat_var, mask_var, outp_var;
Example #28
| Source File: deep_conv_ae_spsparse_alt46.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_autoencoder_network():
input_var = T.tensor4('input_var');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(2,2), stride=2, mode='average_inc_pad');
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(2,2), stride=2, mode='average_inc_pad');
layer = batch_norm(layers.Conv2DLayer(layer, 640, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 1024, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 640, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 100, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
layer = feat_map;
layer = batch_norm(layers.Deconv2DLayer(layer, 1024, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 640, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 640, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 320, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 320, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 240, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 120, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.Deconv2DLayer(layer, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
glblf = batch_norm(layers.Conv2DLayer(prely, 128, filter_size=(1,1), nonlinearity=leaky_rectify));
glblf = layers.Pool2DLayer(glblf, pool_size=(5,5), stride=5, mode='average_inc_pad');
glblf = batch_norm(layers.Conv2DLayer(glblf, 64, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Conv2DLayer(glblf, 5, filter_size=(1,1), nonlinearity=rectify), name="global_feature");
glblf = batch_norm(layers.Deconv2DLayer(glblf, 256, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 128, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 128, filter_size=(9,9), stride=5, crop=(2,2), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 128, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 128, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = layers.Deconv2DLayer(glblf, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
layer = layers.ElemwiseSumLayer([layer, glblf]);
network = ReshapeLayer(layer, ([0], -1));
output_var = lasagne.layers.get_output(network);
return network, input_var, output_var;
Example #29
| Source File: deep_conv_ae_spsparse_alt27.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_autoencoder_network():
input_var = T.tensor4('input_var');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 180, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 120, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
mask_map = feat_map;
layer = feat_map;
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.Deconv2DLayer(layer, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
glblf = batch_norm(layers.Conv2DLayer(prely, 100, filter_size=(1,1), nonlinearity=leaky_rectify));
glblf = layers.Pool2DLayer(glblf, pool_size=(5,5), stride=5, mode='average_inc_pad');
glblf = batch_norm(layers.Conv2DLayer(glblf, 64, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Conv2DLayer(glblf, 3, filter_size=(1,1), nonlinearity=rectify), name="global_feature");
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(9,9), stride=5, crop=(2,2), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = layers.Deconv2DLayer(glblf, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
layer = layers.ElemwiseSumLayer([layer, glblf]);
network = ReshapeLayer(layer, ([0], -1));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #30
| Source File: deep_conv_ae_spsparse_alt34.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_autoencoder_network():
input_var = T.tensor4('input_var');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 140, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 100, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 100, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
maskm = batch_norm(layers.Conv2DLayer(prely, 100, filter_size=(1,1), nonlinearity=leaky_rectify));
mask_rep = batch_norm(layers.Conv2DLayer(maskm, 1, filter_size=(1,1), nonlinearity=None), beta=None, gamma=None);
mask_map = SoftThresPerc(mask_rep, perc=99.9, alpha=0.5, beta=init.Constant(0.1), tight=100.0, name="mask_map");
layer = ChInnerProdMerge(feat_map, mask_map, name="encoder");
layer = batch_norm(layers.Deconv2DLayer(layer, 140, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 120, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.Deconv2DLayer(layer, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
glblf = batch_norm(layers.Conv2DLayer(prely, 100, filter_size=(1,1), nonlinearity=leaky_rectify));
glblf = layers.Pool2DLayer(glblf, pool_size=(20,20), stride=20, mode='average_inc_pad');
glblf = batch_norm(layers.Conv2DLayer(glblf, 64, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Conv2DLayer(glblf, 3, filter_size=(1,1), nonlinearity=rectify), name="global_feature");
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = layers.Upscale2DLayer(glblf, scale_factor=20);
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = layers.Deconv2DLayer(glblf, 3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);
layer = layers.ElemwiseSumLayer([layer, glblf]);
network = ReshapeLayer(layer, ([0], -1));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
