Python lasagne.init.HeNormal() Examples
The following are 10
code examples of lasagne.init.HeNormal().
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.init
, or try the search function
.
.
Example #1
| Source File: lasagne_net.py From BirdCLEF-Baseline with MIT License | 6 votes |
|
def initialization(name):
initializations = {'sigmoid':init.HeNormal(gain=1.0),
'softmax':init.HeNormal(gain=1.0),
'elu':init.HeNormal(gain=1.0),
'relu':init.HeNormal(gain=math.sqrt(2)),
'lrelu':init.HeNormal(gain=math.sqrt(2/(1+0.01**2))),
'vlrelu':init.HeNormal(gain=math.sqrt(2/(1+0.33**2))),
'rectify':init.HeNormal(gain=math.sqrt(2)),
'identity':init.HeNormal(gain=math.sqrt(2))
}
return initializations[name]
#################### BASELINE MODEL #####################
Example #2
| Source File: fr3dnet.py From luna16 with BSD 2-Clause "Simplified" License | 5 votes |
|
def define_network(inputs):
network = lasagne.layers.InputLayer(shape=(None, params.CHANNELS, params.INPUT_SIZE, params.INPUT_SIZE, params.INPUT_SIZE),
input_var=inputs)
network = Conv3DDNNLayer(
network, num_filters=64, filter_size=(5, 5, 5),
nonlinearity=lasagne.nonlinearities.leaky_rectify,
W=HeNormal(gain='relu'))
network = MaxPool3DDNNLayer(network, pool_size=(2, 2, 2))
if params.BATCH_NORMALIZATION:
network = lasagne.layers.batch_norm(network)
network = Conv3DDNNLayer(
network, num_filters=64, filter_size=(5, 5, 5),
nonlinearity=lasagne.nonlinearities.leaky_rectify,
W=HeNormal(gain='relu'))
network = Conv3DDNNLayer(
network, num_filters=96, filter_size=(5, 5, 5),
nonlinearity=lasagne.nonlinearities.leaky_rectify,
W=HeNormal(gain='relu'))
if params.BATCH_NORMALIZATION:
network = lasagne.layers.batch_norm(network)
network = lasagne.layers.DenseLayer(
network,
num_units=420,
nonlinearity=lasagne.nonlinearities.leaky_rectify,
W=HeNormal(gain='relu')
)
network = lasagne.layers.DenseLayer(
network, num_units=params.N_CLASSES,
nonlinearity=lasagne.nonlinearities.softmax)
return network
Example #3
| Source File: res_net_blocks.py From dcase_task2 with MIT License | 5 votes |
|
def ResNet_FullPreActivation(input_shape=(None, 3, PIXELS, PIXELS), input_var=None, n_classes=10, n=18):
"""
Adapted from https://github.com/Lasagne/Recipes/tree/master/papers/deep_residual_learning.
Tweaked to be consistent with 'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)
Formula to figure out depth: 6n + 2
"""
# Building the network
l_in = InputLayer(shape=input_shape, input_var=input_var)
# first layer, output is 16 x 32 x 32
l = batch_norm(ConvLayer(l_in, num_filters=16, filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=he_norm))
# first stack of residual blocks, output is 16 x 32 x 32
l = residual_block(l, first=True)
for _ in range(1, n):
l = residual_block(l)
# second stack of residual blocks, output is 32 x 16 x 16
l = residual_block(l, increase_dim=True)
for _ in range(1, n):
l = residual_block(l)
# third stack of residual blocks, output is 64 x 8 x 8
l = residual_block(l, increase_dim=True)
for _ in range(1, n):
l = residual_block(l)
bn_post_conv = BatchNormLayer(l)
bn_post_relu = NonlinearityLayer(bn_post_conv, rectify)
# average pooling
avg_pool = GlobalPoolLayer(bn_post_relu)
# fully connected layer
network = DenseLayer(avg_pool, num_units=n_classes, W=HeNormal(), nonlinearity=softmax)
return network
Example #4
| Source File: Unet.py From Recipes with MIT License | 4 votes |
|
def build_UNet(n_input_channels=1, BATCH_SIZE=None, num_output_classes=2, pad='same', nonlinearity=lasagne.nonlinearities.elu, input_dim=(128, 128), base_n_filters=64, do_dropout=False):
net = OrderedDict()
net['input'] = InputLayer((BATCH_SIZE, n_input_channels, input_dim[0], input_dim[1]))
net['contr_1_1'] = batch_norm(ConvLayer(net['input'], base_n_filters, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['contr_1_2'] = batch_norm(ConvLayer(net['contr_1_1'], base_n_filters, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['pool1'] = Pool2DLayer(net['contr_1_2'], 2)
net['contr_2_1'] = batch_norm(ConvLayer(net['pool1'], base_n_filters*2, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['contr_2_2'] = batch_norm(ConvLayer(net['contr_2_1'], base_n_filters*2, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['pool2'] = Pool2DLayer(net['contr_2_2'], 2)
net['contr_3_1'] = batch_norm(ConvLayer(net['pool2'], base_n_filters*4, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['contr_3_2'] = batch_norm(ConvLayer(net['contr_3_1'], base_n_filters*4, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['pool3'] = Pool2DLayer(net['contr_3_2'], 2)
net['contr_4_1'] = batch_norm(ConvLayer(net['pool3'], base_n_filters*8, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['contr_4_2'] = batch_norm(ConvLayer(net['contr_4_1'], base_n_filters*8, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
l = net['pool4'] = Pool2DLayer(net['contr_4_2'], 2)
# the paper does not really describe where and how dropout is added. Feel free to try more options
if do_dropout:
l = DropoutLayer(l, p=0.4)
net['encode_1'] = batch_norm(ConvLayer(l, base_n_filters*16, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['encode_2'] = batch_norm(ConvLayer(net['encode_1'], base_n_filters*16, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['upscale1'] = batch_norm(Deconv2DLayer(net['encode_2'], base_n_filters*16, 2, 2, crop="valid", nonlinearity=nonlinearity, W=HeNormal(gain="relu")))
net['concat1'] = ConcatLayer([net['upscale1'], net['contr_4_2']], cropping=(None, None, "center", "center"))
net['expand_1_1'] = batch_norm(ConvLayer(net['concat1'], base_n_filters*8, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['expand_1_2'] = batch_norm(ConvLayer(net['expand_1_1'], base_n_filters*8, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['upscale2'] = batch_norm(Deconv2DLayer(net['expand_1_2'], base_n_filters*8, 2, 2, crop="valid", nonlinearity=nonlinearity, W=HeNormal(gain="relu")))
net['concat2'] = ConcatLayer([net['upscale2'], net['contr_3_2']], cropping=(None, None, "center", "center"))
net['expand_2_1'] = batch_norm(ConvLayer(net['concat2'], base_n_filters*4, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['expand_2_2'] = batch_norm(ConvLayer(net['expand_2_1'], base_n_filters*4, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['upscale3'] = batch_norm(Deconv2DLayer(net['expand_2_2'], base_n_filters*4, 2, 2, crop="valid", nonlinearity=nonlinearity, W=HeNormal(gain="relu")))
net['concat3'] = ConcatLayer([net['upscale3'], net['contr_2_2']], cropping=(None, None, "center", "center"))
net['expand_3_1'] = batch_norm(ConvLayer(net['concat3'], base_n_filters*2, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['expand_3_2'] = batch_norm(ConvLayer(net['expand_3_1'], base_n_filters*2, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['upscale4'] = batch_norm(Deconv2DLayer(net['expand_3_2'], base_n_filters*2, 2, 2, crop="valid", nonlinearity=nonlinearity, W=HeNormal(gain="relu")))
net['concat4'] = ConcatLayer([net['upscale4'], net['contr_1_2']], cropping=(None, None, "center", "center"))
net['expand_4_1'] = batch_norm(ConvLayer(net['concat4'], base_n_filters, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['expand_4_2'] = batch_norm(ConvLayer(net['expand_4_1'], base_n_filters, 3, nonlinearity=nonlinearity, pad=pad, W=HeNormal(gain="relu")))
net['output_segmentation'] = ConvLayer(net['expand_4_2'], num_output_classes, 1, nonlinearity=None)
net['dimshuffle'] = DimshuffleLayer(net['output_segmentation'], (1, 0, 2, 3))
net['reshapeSeg'] = ReshapeLayer(net['dimshuffle'], (num_output_classes, -1))
net['dimshuffle2'] = DimshuffleLayer(net['reshapeSeg'], (1, 0))
net['output_flattened'] = NonlinearityLayer(net['dimshuffle2'], nonlinearity=lasagne.nonlinearities.softmax)
return net
Example #5
| Source File: AED_train.py From AcousticEventDetection with MIT License | 4 votes |
|
def buildModel():
print "BUILDING MODEL TYPE..."
#default settings
filters = 64
first_stride = 2
last_filter_multiplier = 16
#input layer
net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0]))
#conv layers
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net)
#dense layers
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.DropoutLayer(net, DROPOUT)
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.DropoutLayer(net, DROPOUT)
#Classification Layer
if MULTI_LABEL:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1))
else:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1))
print "...DONE!"
#model stats
print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS"
print "MODEL HAS", l.count_params(net), "PARAMS"
return net
Example #6
| Source File: res_net_blocks.py From dcase_task2 with MIT License | 4 votes |
|
def ResNet_BottleNeck_FullPreActivation(input_shape=(None, 3, PIXELS, PIXELS), input_var=None, n_classes=10, n=18):
'''
Adapted from https://github.com/Lasagne/Recipes/tree/master/papers/deep_residual_learning.
Tweaked to be consistent with 'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)
Judging from https://github.com/KaimingHe/resnet-1k-layers/blob/master/resnet-pre-act.lua.
Number of filters go 16 -> 64 -> 128 -> 256
Forumala to figure out depth: 9n + 2
'''
# Building the network
l_in = InputLayer(shape=input_shape, input_var=input_var)
# first layer, output is 16x16x16
l = batch_norm(ConvLayer(l_in, num_filters=16, filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=he_norm))
# first stack of residual blocks, output is 64x16x16
l = residual_bottleneck_block(l, first=True)
for _ in range(1, n):
l = residual_bottleneck_block(l)
# second stack of residual blocks, output is 128x8x8
l = residual_bottleneck_block(l, increase_dim=True)
for _ in range(1, n):
l = residual_bottleneck_block(l)
# third stack of residual blocks, output is 256x4x4
l = residual_bottleneck_block(l, increase_dim=True)
for _ in range(1, n):
l = residual_bottleneck_block(l)
bn_post_conv = BatchNormLayer(l)
bn_post_relu = NonlinearityLayer(bn_post_conv, rectify)
# average pooling
avg_pool = GlobalPoolLayer(bn_post_relu)
# fully connected layer
network = DenseLayer(avg_pool, num_units=n_classes, W=HeNormal(), nonlinearity=softmax)
return network
Example #7
| Source File: res_net_blocks.py From dcase_task2 with MIT License | 4 votes |
|
def ResNet_FullPre_Wide(input_shape=(None, 3, PIXELS, PIXELS), input_var=None, n_classes=10, n=6, k=4):
"""
Adapted from https://github.com/Lasagne/Recipes/tree/master/papers/deep_residual_learning.
Tweaked to be consistent with 'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)
And 'Wide Residual Networks', Sergey Zagoruyko, Nikos Komodakis 2016 (http://arxiv.org/pdf/1605.07146v1.pdf)
Depth = 6n + 2
"""
n_filters = {0: 16, 1: 16*k, 2: 32*k, 3: 64*k}
# Building the network
l_in = InputLayer(shape=input_shape, input_var=input_var)
# first layer, output is 16 x 64 x 64
l = batch_norm(ConvLayer(l_in, num_filters=n_filters[0], filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=he_norm))
# first stack of residual blocks, output is 32 x 64 x 64
l = residual_wide_block(l, first=True, filters=n_filters[1])
for _ in range(1, n):
l = residual_wide_block(l, filters=n_filters[1])
# second stack of residual blocks, output is 64 x 32 x 32
l = residual_wide_block(l, increase_dim=True, filters=n_filters[2])
for _ in range(1, (n+2)):
l = residual_wide_block(l, filters=n_filters[2])
# third stack of residual blocks, output is 128 x 16 x 16
l = residual_wide_block(l, increase_dim=True, filters=n_filters[3])
for _ in range(1, (n+2)):
l = residual_wide_block(l, filters=n_filters[3])
bn_post_conv = BatchNormLayer(l)
bn_post_relu = NonlinearityLayer(bn_post_conv, rectify)
# average pooling
avg_pool = GlobalPoolLayer(bn_post_relu)
# fully connected layer
network = DenseLayer(avg_pool, num_units=n_classes, W=HeNormal(), nonlinearity=softmax)
return network
Example #8
| Source File: birdCLEF_evaluate.py From BirdCLEF2017 with MIT License | 4 votes |
|
def buildModel(mtype=1):
print "BUILDING MODEL TYPE", mtype, "..."
#default settings (Model 1)
filters = 64
first_stride = 2
last_filter_multiplier = 16
#specific model type settings (see working notes for details)
if mtype == 2:
first_stride = 1
elif mtype == 3:
filters = 32
last_filter_multiplier = 8
#input layer
net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0]))
#conv layers
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
if mtype == 2:
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net)
#dense layers
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
#Classification Layer
if MULTI_LABEL:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1))
else:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1))
print "...DONE!"
#model stats
print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS"
print "MODEL HAS", l.count_params(net), "PARAMS"
return net
Example #9
| Source File: birdCLEF_test.py From BirdCLEF2017 with MIT License | 4 votes |
|
def buildModel(mtype=1):
print "BUILDING MODEL TYPE", mtype, "..."
#default settings (Model 1)
filters = 64
first_stride = 2
last_filter_multiplier = 16
#specific model type settings (see working notes for details)
if mtype == 2:
first_stride = 1
elif mtype == 3:
filters = 32
last_filter_multiplier = 8
#input layer
net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0]))
#conv layers
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
if mtype == 2:
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net)
#dense layers
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
#Classification Layer
if MULTI_LABEL:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1))
else:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1))
print "...DONE!"
#model stats
print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS"
print "MODEL HAS", l.count_params(net), "PARAMS"
return net
Example #10
| Source File: birdCLEF_train.py From BirdCLEF2017 with MIT License | 4 votes |
|
def buildModel(mtype=1):
print "BUILDING MODEL TYPE", mtype, "..."
#default settings (Model 1)
filters = 64
first_stride = 2
last_filter_multiplier = 16
#specific model type settings (see working notes for details)
if mtype == 2:
first_stride = 1
elif mtype == 3:
filters = 32
last_filter_multiplier = 8
#input layer
net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0]))
#conv layers
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
if mtype == 2:
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.MaxPool2DLayer(net, pool_size=2)
print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net)
#dense layers
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.DropoutLayer(net, DROPOUT)
net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY))
net = l.DropoutLayer(net, DROPOUT)
#Classification Layer
if MULTI_LABEL:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1))
else:
net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1))
print "...DONE!"
#model stats
print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS"
print "MODEL HAS", l.count_params(net), "PARAMS"
return net
