Python nonlinearities.leaky_rectify方法代碼示例

本文整理匯總了Python中lasagne.nonlinearities.leaky_rectify方法的典型用法代碼示例。如果您正苦於以下問題：Python nonlinearities.leaky_rectify方法的具體用法？Python nonlinearities.leaky_rectify怎麽用？Python nonlinearities.leaky_rectify使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類lasagne.nonlinearities的用法示例。

在下文中一共展示了nonlinearities.leaky_rectify方法的15個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: build_network_from_ae

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:28，代碼來源:deep_conv_classification_alt55.py

示例2: build_network_from_ae

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:28，代碼來源:deep_conv_classification_alt51_luad10_luad10in20_brca10x1_heatmap.py

示例3: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:35，代碼來源:deep_conv_ae_spsparse_alt29.py

示例4: test_LeakyRectifier

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
def test_LeakyRectifier(self):
        nn = MLPR(layers=[N(ly.DenseLayer, units=24, nonlinearity=nl.leaky_rectify),
                          L("Linear")], n_iter=1)
        self._run(nn)

開發者ID:aigamedev，項目名稱:scikit-neuralnetwork，代碼行數:6，代碼來源:test_native.py

示例5: conv_params

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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

開發者ID:sveitser，項目名稱:kaggle_diabetic，代碼行數:16，代碼來源:layers.py

示例6: dense_params

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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

開發者ID:sveitser，項目名稱:kaggle_diabetic，代碼行數:11，代碼來源:layers.py

示例7: create_student_model

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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

開發者ID:tdeboissiere，項目名稱:DeepLearningImplementations，代碼行數:11，代碼來源:sobolev_training.py

示例8: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:55，代碼來源:deep_conv_ae_spsparse_alt32.py

示例9: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:57，代碼來源:deep_conv_ae_spsparse_alt21.py

示例10: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:55，代碼來源:deep_conv_ae_spsparse_alt31.py

示例11: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:61，代碼來源:deep_conv_ae_spsparse_alt25.py

示例12: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:55，代碼來源:deep_conv_ae_spsparse_alt36.py

示例13: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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=1.00, 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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:59，代碼來源:deep_conv_ae_spsparse_alt24.py

示例14: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
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,  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));
    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=99.85, alpha=0.5, beta=init.Constant(0.5), tight=100.0, name="mask_map");
    encod    = ChInnerProdMerge(feat_map, mask_map, name="encoder");

    layer = batch_norm(layers.Deconv2DLayer(encod, 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, 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 = 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, 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=(24,24), stride=20, crop=(2,2), 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 = batch_norm(layers.Deconv2DLayer(glblf, 16, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf,  8, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf,  8, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf,  8, 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;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:59，代碼來源:deep_conv_ae_spsparse_alt48.py

示例15: build_autoencoder_network

# 需要導入模塊: from lasagne import nonlinearities [as 別名]
# 或者: from lasagne.nonlinearities import leaky_rectify [as 別名]
def build_autoencoder_network():
    input_var = T.tensor4('input_var');

    layer = layers.InputLayer(shape=(None, 3, PS, PS), input_var=input_var);
    layer = batch_norm(layers.Conv2DLayer(layer,  80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Conv2DLayer(layer,  80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Conv2DLayer(layer,  80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Conv2DLayer(layer,  80, filter_size=(5,5), stride=1, pad='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
    prely = batch_norm(layers.Conv2DLayer(layer, 100, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));

    featm    = batch_norm(layers.Conv2DLayer(prely, 180, filter_size=(1,1), nonlinearity=leaky_rectify));
    feat_map = batch_norm(layers.Conv2DLayer(featm, 120, filter_size=(1,1), nonlinearity=rectify, name="feat_map"));
    maskm    = batch_norm(layers.Conv2DLayer(prely, 120, filter_size=(1,1), nonlinearity=leaky_rectify));
    mask_rep = batch_norm(layers.Conv2DLayer(maskm,   1, filter_size=(1,1), nonlinearity=None),   beta=None, gamma=None);
    mask_map = SoftThresPerc(mask_rep, perc=99.9, alpha=0.5, beta=init.Constant(0.5), tight=100.0, name="mask_map");
    layer    = ChInnerProdMerge(feat_map, mask_map, name="encoder");

    layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer, 100, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer,  80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer,  80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer,  80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer = batch_norm(layers.Deconv2DLayer(layer,  80, filter_size=(5,5), stride=1, crop='same', nonlinearity=leaky_rectify));
    layer =            layers.Deconv2DLayer(layer,   3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);

    glblf = batch_norm(layers.Conv2DLayer(prely,  100, filter_size=(1,1), nonlinearity=leaky_rectify));
    glblf = layers.Pool2DLayer(glblf, pool_size=(5,5), stride=5, mode='average_inc_pad');
    glblf = batch_norm(layers.Conv2DLayer(glblf,   64, filter_size=(3,3), stride=1, pad='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Conv2DLayer(glblf,    3, filter_size=(1,1), nonlinearity=rectify), name="global_feature");

    glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 64, filter_size=(9,9), stride=5, crop=(2,2),  nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 48, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf = batch_norm(layers.Deconv2DLayer(glblf, 32, filter_size=(3,3), stride=1, crop='same', nonlinearity=leaky_rectify));
    glblf =            layers.Deconv2DLayer(glblf,  3, filter_size=(1,1), stride=1, crop='same', nonlinearity=identity);

    layer = layers.ElemwiseSumLayer([layer, glblf]);

    network = ReshapeLayer(layer, ([0], -1));
    layers.set_all_param_values(network, pickle.load(open(filename_model_ae, 'rb')));
    feat_var = lasagne.layers.get_output(feat_map, deterministic=True);
    mask_var = lasagne.layers.get_output(mask_map, deterministic=True);
    outp_var = lasagne.layers.get_output(network,  deterministic=True);

    return network, input_var, feat_var, mask_var, outp_var;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:57，代碼來源:deep_conv_ae_spsparse_recons.py

注：本文中的lasagne.nonlinearities.leaky_rectify方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。