Python lasagne.nonlinearities.leaky_rectify() Examples
The following are 30
code examples of lasagne.nonlinearities.leaky_rectify().
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.nonlinearities
, or try the search function
.
.
Example #1
| Source File: deep_conv_classification_alt55.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = (layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = (layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #2
| Source File: sobolev_training.py From DeepLearningImplementations with MIT License | 5 votes |
|
def create_student_model(input_var):
# create a small convolutional neural network
network = lasagne.layers.InputLayer((None, 2), input_var)
network = lasagne.layers.DenseLayer(network, 256, nonlinearity=leaky_rectify)
network = lasagne.layers.DenseLayer(network, 256, nonlinearity=leaky_rectify)
network = lasagne.layers.DenseLayer(network, 1, nonlinearity=linear)
return network
Example #3
| Source File: layers.py From kaggle_diabetic with MIT License | 5 votes |
|
def dense_params(num_units, nonlinearity=leaky_rectify, **kwargs):
args = {
'num_units': num_units,
'nonlinearity': nonlinearity,
'W': init.Orthogonal(1.0),
'b': init.Constant(0.05),
}
args.update(kwargs)
return args
Example #4
| Source File: layers.py From kaggle_diabetic with MIT License | 5 votes |
|
def conv_params(num_filters, filter_size=(3, 3), border_mode='same',
nonlinearity=leaky_rectify, W=init.Orthogonal(gain=1.0),
b=init.Constant(0.05), untie_biases=True, **kwargs):
args = {
'num_filters': num_filters,
'filter_size': filter_size,
'border_mode': border_mode,
'nonlinearity': nonlinearity,
'W': W,
'b': b,
'untie_biases': untie_biases,
}
args.update(kwargs)
return args
Example #5
| Source File: test_native.py From scikit-neuralnetwork with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def test_LeakyRectifier(self):
nn = MLPR(layers=[N(ly.DenseLayer, units=24, nonlinearity=nl.leaky_rectify),
L("Linear")], n_iter=1)
self._run(nn)
Example #6
| Source File: deep_conv_classification_alt64.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #7
| Source File: deep_conv_classification_alt51_luad10_luad10in20_brca10x1.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #8
| Source File: deep_conv_classification_alt57.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = (layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = (layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #9
| Source File: deep_conv_classification_alt51_heatmap.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #10
| Source File: deep_conv_ae_spsparse_alt29.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
mask_map = layer;
layer = batch_norm(layers.Conv2DLayer(layer, 10, filter_size=(1,1), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 1000, filter_size=(76,76), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 10, filter_size=(76,76), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 80, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = layers.Deconv2DLayer(layer, 3, filter_size=(1,1), stride=1, nonlinearity=identity);
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 #11
| Source File: deep_conv_classification_alt51_luad10_luad10in20_brca10x1_heatmap.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #12
| Source File: deep_conv_classification_alt56.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
layer = (layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = (layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = (layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #13
| Source File: deep_conv_classification_alt51_luad10in20_brca10.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #14
| Source File: deep_conv_classification_alt51_luad10_luad10in20_brca10x2.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_network_from_ae(classn):
input_var = T.tensor4('input_var');
target_var = T.imatrix('targets');
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, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(5,5), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(4,4), stride=1, nonlinearity=leaky_rectify));
layer = layers.MaxPool2DLayer(layer, pool_size=(3,3), stride=2);
layer = batch_norm(layers.Conv2DLayer(layer, 240, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = layers.Pool2DLayer(layer, pool_size=(20,20), stride=20, mode='average_inc_pad');
network = layers.DenseLayer(layer, classn, nonlinearity=sigmoid);
return network, input_var, target_var;
Example #15
| Source File: deep_conv_ae_spsparse_alt30.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, 240, 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, 320, 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=(3,3), stride=2, mode='average_inc_pad');
layer = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 480, 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));
layer = batch_norm(layers.Conv2DLayer(layer, 640, 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');
mask_map = layer;
layer = batch_norm(layers.Conv2DLayer(layer, 300, filter_size=(1,1), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 1000, filter_size=(3,3), stride=1, nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 300, filter_size=(3,3), stride=1, 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, 640, 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, 480, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 480, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 480, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 320, filter_size=(3,3), stride=2, crop=(0,0), 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, 240, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 240, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 120, 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);
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 #16
| Source File: deep_conv_ae_spsparse_alt32.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=50.0, 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 #17
| Source File: deep_conv_ae_spsparse_alt21.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"));
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=98.4, alpha=0.1, 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, 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));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #18
| Source File: train_cae.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"));
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=98.4, alpha=0.1, 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, 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));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #19
| Source File: deep_conv_ae_spsparse_alt5.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, 104, 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, 208, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 256, 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, 512, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 720, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 512, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 80, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
maskm = batch_norm(layers.Conv2DLayer(prely, 80, 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 = BNRectifyPerc(mask_rep, perc=97.92, alpha=0.1, beta=init.Constant(0.5), name="mask_map");
layer = ChInnerProdMerge(feat_map, mask_map, name="encoder");
layer = batch_norm(layers.Deconv2DLayer(layer, 720, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 512, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 256, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 256, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 208, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 208, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 104, 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, 64, 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, 32, 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, 128, 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, 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 = batch_norm(layers.Deconv2DLayer(glblf, 16, filter_size=(4,4), stride=2, crop=(1,1), nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 16, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
glblf = batch_norm(layers.Deconv2DLayer(glblf, 16, 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 #20
| Source File: deep_conv_ae_spsparse_alt28.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"));
mask_map = 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));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #21
| Source File: deep_conv_ae_spsparse_alt47.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 = BNRectifyPerc(feat_map, perc=98.4, alpha=0.1, beta=init.Constant(0.5));
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 #22
| Source File: deep_conv_ae_spsparse_alt31.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=110.0, 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 #23
| Source File: deep_conv_ae_spsparse_alt38.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"));
mask_map = SoftThresPerc(feat_map, perc=98.4, alpha=0.1, beta=init.Constant(0.5), tight=20.0, name="mask_map");
layer = mask_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));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #24
| Source File: deep_conv_ae_spsparse_alt25.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 = batch_norm(layers.Conv2DLayer(layer, 120, filter_size=(1,1), stride=1, pad='same', nonlinearity=leaky_rectify));
pool1 = layers.MaxPool2DLayer(layer, (2, 2), 2);
layer = batch_norm(layers.Conv2DLayer(pool1, 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 = batch_norm(layers.Conv2DLayer(layer, 320, filter_size=(1,1), stride=1, pad='same', nonlinearity=leaky_rectify));
pool2 = layers.MaxPool2DLayer(layer, (2, 2), 2);
layer = batch_norm(layers.Conv2DLayer(pool2, 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"));
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=90.0, alpha=0.1, 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, 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, 320, filter_size=(1,1), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.InverseLayer(layer, pool2);
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, 120, filter_size=(1,1), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = layers.InverseLayer(layer, pool1);
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));
mask_var = lasagne.layers.get_output(mask_map);
output_var = lasagne.layers.get_output(network);
return network, input_var, mask_var, output_var;
Example #25
| Source File: deep_conv_ae_spsparse_alt23.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 = batch_norm(layers.Conv2DLayer(layer, 140, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 160, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 180, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 220, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
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 = batch_norm(layers.Conv2DLayer(layer, 360, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 480, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 320, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
maskm = batch_norm(layers.Conv2DLayer(prely, 320, 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=99.0, alpha=0.1, 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, 480, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 360, 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=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 220, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 180, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 160, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 140, filter_size=(5,5), stride=1, crop='same', 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=(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=(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 #26
| Source File: deep_conv_ae_spsparse_alt33.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=0.1, 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_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;
Example #28
| 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 #29
| Source File: deep_conv_ae_spsparse_alt22.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 = batch_norm(layers.Conv2DLayer(layer, 140, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Conv2DLayer(layer, 160, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
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 = batch_norm(layers.Conv2DLayer(layer, 360, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
prely = batch_norm(layers.Conv2DLayer(layer, 480, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
featm = batch_norm(layers.Conv2DLayer(prely, 480, filter_size=(1,1), nonlinearity=leaky_rectify));
feat_map = batch_norm(layers.Conv2DLayer(featm, 320, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
maskm = batch_norm(layers.Conv2DLayer(prely, 320, 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=99.0, alpha=0.1, 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, 480, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 360, 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, 320, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 160, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
layer = batch_norm(layers.Deconv2DLayer(layer, 140, filter_size=(5,5), stride=1, crop='same', 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=(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=(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_alt36.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, 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=90.0, 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, 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=(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;
