Python lasagne.layers.DropoutLayer() Examples
The following are 25
code examples of lasagne.layers.DropoutLayer().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
lasagne.layers
, or try the search function
.
.
Example #1
| Source File: nn_adagrad_log.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden / 2, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_hidden3 = DenseLayer(l_hidden2_dropout, num_units=self.n_hidden / 4, nonlinearity=rectify)
l_hidden3_dropout = DropoutLayer(l_hidden3, p=self.dropout)
l_out = DenseLayer(l_hidden3_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #2
| Source File: bidnn.py From BiDNN with GNU Affero General Public License v3.0 | 5 votes |
|
def __create_toplogy__(self, input_var_first=None, input_var_second=None):
# define network topology
if (self.conf.rep % 2 != 0):
raise ValueError("Representation size should be divisible by two as it's formed by combining two crossmodal translations", self.conf.rep)
# input layers
l_in_first = InputLayer(shape=(self.conf.batch_size, self.conf.mod1size), input_var=input_var_first)
l_in_second = InputLayer(shape=(self.conf.batch_size, self.conf.mod2size), input_var=input_var_second)
# first -> second
l_hidden1_first = DenseLayer(l_in_first, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # enc1
l_hidden2_first = DenseLayer(l_hidden1_first, num_units=self.conf.rep//2, nonlinearity=self.conf.act, W=GlorotUniform()) # enc2
l_hidden2_first_d = DropoutLayer(l_hidden2_first, p=self.conf.dropout)
l_hidden3_first = DenseLayer(l_hidden2_first_d, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # dec1
l_out_first = DenseLayer(l_hidden3_first, num_units=self.conf.mod2size, nonlinearity=self.conf.act, W=GlorotUniform()) # dec2
if self.conf.untied:
# FREE
l_hidden1_second = DenseLayer(l_in_second, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # enc1
l_hidden2_second = DenseLayer(l_hidden1_second, num_units=self.conf.rep//2, nonlinearity=self.conf.act, W=GlorotUniform()) # enc2
l_hidden2_second_d = DropoutLayer(l_hidden2_second, p=self.conf.dropout)
l_hidden3_second = DenseLayer(l_hidden2_second_d, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # dec1
l_out_second = DenseLayer(l_hidden3_second, num_units=self.conf.mod1size, nonlinearity=self.conf.act, W=GlorotUniform()) # dec2
else:
# TIED middle
l_hidden1_second = DenseLayer(l_in_second, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # enc1
l_hidden2_second = DenseLayer(l_hidden1_second, num_units=self.conf.rep//2, nonlinearity=self.conf.act, W=l_hidden3_first.W.T) # enc2
l_hidden2_second_d = DropoutLayer(l_hidden2_second, p=self.conf.dropout)
l_hidden3_second = DenseLayer(l_hidden2_second_d, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=l_hidden2_first.W.T) # dec1
l_out_second = DenseLayer(l_hidden3_second, num_units=self.conf.mod1size, nonlinearity=self.conf.act, W=GlorotUniform()) # dec2
l_out = concat([l_out_first, l_out_second])
return l_out, l_hidden2_first, l_hidden2_second
Example #3
| Source File: benchmark_lasagne.py From vgg-benchmarks with MIT License | 5 votes |
|
def build_model(input_var):
net = {}
net['input'] = InputLayer((None, 3, 224, 224), input_var=input_var)
net['conv1_1'] = ConvLayer(net['input'], 64, 3, pad=1, flip_filters=False)
net['conv1_2'] = ConvLayer(net['conv1_1'], 64, 3, pad=1, flip_filters=False)
net['pool1'] = PoolLayer(net['conv1_2'], 2)
net['conv2_1'] = ConvLayer(net['pool1'], 128, 3, pad=1, flip_filters=False)
net['conv2_2'] = ConvLayer(net['conv2_1'], 128, 3, pad=1, flip_filters=False)
net['pool2'] = PoolLayer(net['conv2_2'], 2)
net['conv3_1'] = ConvLayer(net['pool2'], 256, 3, pad=1, flip_filters=False)
net['conv3_2'] = ConvLayer(net['conv3_1'], 256, 3, pad=1, flip_filters=False)
net['conv3_3'] = ConvLayer(net['conv3_2'], 256, 3, pad=1, flip_filters=False)
net['pool3'] = PoolLayer(net['conv3_3'], 2)
net['conv4_1'] = ConvLayer(net['pool3'], 512, 3, pad=1, flip_filters=False)
net['conv4_2'] = ConvLayer(net['conv4_1'], 512, 3, pad=1, flip_filters=False)
net['conv4_3'] = ConvLayer(net['conv4_2'], 512, 3, pad=1, flip_filters=False)
net['pool4'] = PoolLayer(net['conv4_3'], 2)
net['conv5_1'] = ConvLayer(net['pool4'], 512, 3, pad=1, flip_filters=False)
net['conv5_2'] = ConvLayer(net['conv5_1'], 512, 3, pad=1, flip_filters=False)
net['conv5_3'] = ConvLayer(net['conv5_2'], 512, 3, pad=1, flip_filters=False)
net['pool5'] = PoolLayer(net['conv5_3'], 2)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['fc6_dropout'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['fc6_dropout'], num_units=4096)
net['fc7_dropout'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['fc7_dropout'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
return net
Example #4
| Source File: nn_adagrad.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_hidden3 = DenseLayer(l_hidden2_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden3_dropout = DropoutLayer(l_hidden3, p=self.dropout)
l_out = DenseLayer(l_hidden3_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #5
| Source File: bagging_nn_rmsprop.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_out = DenseLayer(l_hidden2_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #6
| Source File: bagging_nn_nesterov.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_out = DenseLayer(l_hidden2_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #7
| Source File: nn_rmsprop_features.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden / 2, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_hidden3 = DenseLayer(l_hidden2_dropout, num_units=self.n_hidden / 2, nonlinearity=rectify)
l_hidden3_dropout = DropoutLayer(l_hidden3, p=self.dropout)
l_out = DenseLayer(l_hidden3_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #8
| Source File: nn_adagrad_pca.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_hidden3 = DenseLayer(l_hidden2_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden3_dropout = DropoutLayer(l_hidden3, p=self.dropout)
l_out = DenseLayer(l_hidden3_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #9
| Source File: nn_adagrad_pca.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def build_model(self, input_dim):
l_in = InputLayer(shape=(self.batch_size, input_dim))
l_hidden1 = DenseLayer(l_in, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden1_dropout = DropoutLayer(l_hidden1, p=self.dropout)
l_hidden2 = DenseLayer(l_hidden1_dropout, num_units=self.n_hidden / 2, nonlinearity=rectify)
l_hidden2_dropout = DropoutLayer(l_hidden2, p=self.dropout)
l_hidden3 = DenseLayer(l_hidden2_dropout, num_units=self.n_hidden, nonlinearity=rectify)
l_hidden3_dropout = DropoutLayer(l_hidden3, p=self.dropout)
l_out = DenseLayer(l_hidden3_dropout, num_units=self.n_classes_, nonlinearity=softmax)
return l_out
Example #10
| Source File: model.py From BirdNET with MIT License | 5 votes |
|
def classificationBranch(net, kernel_size):
# Post Convolution
branch = l.batch_norm(l.Conv2DLayer(net,
num_filters=int(FILTERS[-1] * RESNET_K),
filter_size=kernel_size,
nonlinearity=nl.rectify))
#log.p(("\t\tPOST CONV SHAPE:", l.get_output_shape(branch), "LAYER:", len(l.get_all_layers(branch)) - 1))
# Dropout Layer
branch = l.DropoutLayer(branch)
# Dense Convolution
branch = l.batch_norm(l.Conv2DLayer(branch,
num_filters=int(FILTERS[-1] * RESNET_K * 2),
filter_size=1,
nonlinearity=nl.rectify))
#log.p(("\t\tDENSE CONV SHAPE:", l.get_output_shape(branch), "LAYER:", len(l.get_all_layers(branch)) - 1))
# Dropout Layer
branch = l.DropoutLayer(branch)
# Class Convolution
branch = l.Conv2DLayer(branch,
num_filters=len(cfg.CLASSES),
filter_size=1,
nonlinearity=None)
return branch
Example #11
| Source File: Deopen_regression.py From Deopen with MIT License | 5 votes |
|
def create_network():
l = 1000
pool_size = 5
test_size1 = 13
test_size2 = 7
test_size3 = 5
kernel1 = 128
kernel2 = 128
kernel3 = 128
layer1 = InputLayer(shape=(None, 1, 4, l+1024))
layer2_1 = SliceLayer(layer1, indices=slice(0, l), axis = -1)
layer2_2 = SliceLayer(layer1, indices=slice(l, None), axis = -1)
layer2_3 = SliceLayer(layer2_2, indices = slice(0,4), axis = -2)
layer2_f = FlattenLayer(layer2_3)
layer3 = Conv2DLayer(layer2_1,num_filters = kernel1, filter_size = (4,test_size1))
layer4 = Conv2DLayer(layer3,num_filters = kernel1, filter_size = (1,test_size1))
layer5 = Conv2DLayer(layer4,num_filters = kernel1, filter_size = (1,test_size1))
layer6 = MaxPool2DLayer(layer5, pool_size = (1,pool_size))
layer7 = Conv2DLayer(layer6,num_filters = kernel2, filter_size = (1,test_size2))
layer8 = Conv2DLayer(layer7,num_filters = kernel2, filter_size = (1,test_size2))
layer9 = Conv2DLayer(layer8,num_filters = kernel2, filter_size = (1,test_size2))
layer10 = MaxPool2DLayer(layer9, pool_size = (1,pool_size))
layer11 = Conv2DLayer(layer10,num_filters = kernel3, filter_size = (1,test_size3))
layer12 = Conv2DLayer(layer11,num_filters = kernel3, filter_size = (1,test_size3))
layer13 = Conv2DLayer(layer12,num_filters = kernel3, filter_size = (1,test_size3))
layer14 = MaxPool2DLayer(layer13, pool_size = (1,pool_size))
layer14_d = DenseLayer(layer14, num_units= 256)
layer3_2 = DenseLayer(layer2_f, num_units = 128)
layer15 = ConcatLayer([layer14_d,layer3_2])
#layer16 = DropoutLayer(layer15,p=0.5)
layer17 = DenseLayer(layer15, num_units=256)
network = DenseLayer(layer17, num_units= 1, nonlinearity=None)
return network
#random search to initialize the weights
Example #12
| Source File: Deopen_classification.py From Deopen with MIT License | 5 votes |
|
def create_network():
l = 1000
pool_size = 5
test_size1 = 13
test_size2 = 7
test_size3 = 5
kernel1 = 128
kernel2 = 128
kernel3 = 128
layer1 = InputLayer(shape=(None, 1, 4, l+1024))
layer2_1 = SliceLayer(layer1, indices=slice(0, l), axis = -1)
layer2_2 = SliceLayer(layer1, indices=slice(l, None), axis = -1)
layer2_3 = SliceLayer(layer2_2, indices = slice(0,4), axis = -2)
layer2_f = FlattenLayer(layer2_3)
layer3 = Conv2DLayer(layer2_1,num_filters = kernel1, filter_size = (4,test_size1))
layer4 = Conv2DLayer(layer3,num_filters = kernel1, filter_size = (1,test_size1))
layer5 = Conv2DLayer(layer4,num_filters = kernel1, filter_size = (1,test_size1))
layer6 = MaxPool2DLayer(layer5, pool_size = (1,pool_size))
layer7 = Conv2DLayer(layer6,num_filters = kernel2, filter_size = (1,test_size2))
layer8 = Conv2DLayer(layer7,num_filters = kernel2, filter_size = (1,test_size2))
layer9 = Conv2DLayer(layer8,num_filters = kernel2, filter_size = (1,test_size2))
layer10 = MaxPool2DLayer(layer9, pool_size = (1,pool_size))
layer11 = Conv2DLayer(layer10,num_filters = kernel3, filter_size = (1,test_size3))
layer12 = Conv2DLayer(layer11,num_filters = kernel3, filter_size = (1,test_size3))
layer13 = Conv2DLayer(layer12,num_filters = kernel3, filter_size = (1,test_size3))
layer14 = MaxPool2DLayer(layer13, pool_size = (1,pool_size))
layer14_d = DenseLayer(layer14, num_units= 256)
layer3_2 = DenseLayer(layer2_f, num_units = 128)
layer15 = ConcatLayer([layer14_d,layer3_2])
layer16 = DropoutLayer(layer15,p=0.5)
layer17 = DenseLayer(layer16, num_units=256)
network = DenseLayer(layer17, num_units= 2, nonlinearity=softmax)
return network
#random search to initialize the weights
Example #13
| Source File: lasagne_net.py From BirdCLEF-Baseline with MIT License | 4 votes |
|
def build_pi_model():
log.i('BUILDING RASBPERRY PI MODEL...')
# Random Seed
lasagne_random.set_rng(cfg.getRandomState())
# Input layer for images
net = l.InputLayer((None, cfg.IM_DIM, cfg.IM_SIZE[1], cfg.IM_SIZE[0]))
# Convolutinal layer groups
for i in range(len(cfg.FILTERS)):
# 3x3 Convolution + Stride
net = batch_norm(l.Conv2DLayer(net,
num_filters=cfg.FILTERS[i],
filter_size=cfg.KERNEL_SIZES[i],
num_groups=cfg.NUM_OF_GROUPS[i],
pad='same',
stride=2,
W=initialization(cfg.NONLINEARITY),
nonlinearity=nonlinearity(cfg.NONLINEARITY)))
log.i(('\tGROUP', i + 1, 'OUT SHAPE:', l.get_output_shape(net)))
# Fully connected layers + dropout layers
net = l.DenseLayer(net, cfg.DENSE_UNITS, nonlinearity=nonlinearity(cfg.NONLINEARITY), W=initialization(cfg.NONLINEARITY))
net = l.DropoutLayer(net, p=cfg.DROPOUT)
net = l.DenseLayer(net, cfg.DENSE_UNITS, nonlinearity=nonlinearity(cfg.NONLINEARITY), W=initialization(cfg.NONLINEARITY))
net = l.DropoutLayer(net, p=cfg.DROPOUT)
# Classification Layer (Softmax)
net = l.DenseLayer(net, len(cfg.CLASSES), nonlinearity=nonlinearity('softmax'), W=initialization('softmax'))
log.i(("\tFINAL NET OUT SHAPE:", l.get_output_shape(net)))
log.i("...DONE!")
# Model stats
log.i(("MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS"))
log.i(("MODEL HAS", l.count_params(net), "PARAMS"))
return net
################## BUILDING THE MODEL ###################
Example #14
| Source File: res_net_blocks.py From dcase_task2 with MIT License | 4 votes |
|
def residual_wide_block(l, increase_dim=False, projection=True, first=False, filters=16):
""" Create a residual learning building block with two stacked 3x3 conv layers as in paper """
if increase_dim:
first_stride = (2, 2)
else:
first_stride = (1, 1)
if first:
# hacky solution to keep layers correct
bn_pre_relu = l
else:
# contains the BN -> ReLU portion, steps 1 to 2
bn_pre_conv = BatchNormLayer(l)
bn_pre_relu = NonlinearityLayer(bn_pre_conv, rectify)
# contains the weight -> BN -> ReLU portion, steps 3 to 5
conv_1 = batch_norm(
ConvLayer(bn_pre_relu, num_filters=filters, filter_size=(3, 3), stride=first_stride, nonlinearity=rectify,
pad='same', W=he_norm))
dropout = DropoutLayer(conv_1, p=0.3)
# contains the last weight portion, step 6
conv_2 = ConvLayer(dropout, num_filters=filters, filter_size=(3, 3), stride=(1, 1), nonlinearity=None, pad='same',
W=he_norm)
# add shortcut connections
if increase_dim:
# projection shortcut, as option B in paper
projection = ConvLayer(l, num_filters=filters, filter_size=(1, 1), stride=(2, 2), nonlinearity=None, pad='same',
b=None)
block = ElemwiseSumLayer([conv_2, projection])
elif first:
# projection shortcut, as option B in paper
projection = ConvLayer(l, num_filters=filters, filter_size=(1, 1), stride=(1, 1), nonlinearity=None, pad='same',
b=None)
block = ElemwiseSumLayer([conv_2, projection])
else:
block = ElemwiseSumLayer([conv_2, l])
return block
Example #15
| Source File: cifar10_nin.py From Recipes with MIT License | 4 votes |
|
def build_model():
net = {}
net['input'] = InputLayer((None, 3, 32, 32))
net['conv1'] = ConvLayer(net['input'],
num_filters=192,
filter_size=5,
pad=2,
flip_filters=False)
net['cccp1'] = ConvLayer(
net['conv1'], num_filters=160, filter_size=1, flip_filters=False)
net['cccp2'] = ConvLayer(
net['cccp1'], num_filters=96, filter_size=1, flip_filters=False)
net['pool1'] = PoolLayer(net['cccp2'],
pool_size=3,
stride=2,
mode='max',
ignore_border=False)
net['drop3'] = DropoutLayer(net['pool1'], p=0.5)
net['conv2'] = ConvLayer(net['drop3'],
num_filters=192,
filter_size=5,
pad=2,
flip_filters=False)
net['cccp3'] = ConvLayer(
net['conv2'], num_filters=192, filter_size=1, flip_filters=False)
net['cccp4'] = ConvLayer(
net['cccp3'], num_filters=192, filter_size=1, flip_filters=False)
net['pool2'] = PoolLayer(net['cccp4'],
pool_size=3,
stride=2,
mode='average_exc_pad',
ignore_border=False)
net['drop6'] = DropoutLayer(net['pool2'], p=0.5)
net['conv3'] = ConvLayer(net['drop6'],
num_filters=192,
filter_size=3,
pad=1,
flip_filters=False)
net['cccp5'] = ConvLayer(
net['conv3'], num_filters=192, filter_size=1, flip_filters=False)
net['cccp6'] = ConvLayer(
net['cccp5'], num_filters=10, filter_size=1, flip_filters=False)
net['pool3'] = PoolLayer(net['cccp6'],
pool_size=8,
mode='average_exc_pad',
ignore_border=False)
net['output'] = FlattenLayer(net['pool3'])
return net
Example #16
| 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 #17
| Source File: network.py From cnn_workshop with Apache License 2.0 | 4 votes |
|
def get_net():
return NeuralNet(
layers=[
('input', layers.InputLayer),
('conv1', Conv2DLayer),
('pool1', MaxPool2DLayer),
('dropout1', layers.DropoutLayer),
('conv2', Conv2DLayer),
('pool2', MaxPool2DLayer),
('dropout2', layers.DropoutLayer),
('conv3', Conv2DLayer),
('pool3', MaxPool2DLayer),
('dropout3', layers.DropoutLayer),
('hidden4', layers.DenseLayer),
('dropout4', layers.DropoutLayer),
('hidden5', layers.DenseLayer),
('output', layers.DenseLayer),
],
input_shape=(None, 1, 96, 96),
conv1_num_filters=32, conv1_filter_size=(3, 3), pool1_pool_size=(2, 2),
dropout1_p=0.1,
conv2_num_filters=64, conv2_filter_size=(2, 2), pool2_pool_size=(2, 2),
dropout2_p=0.2,
conv3_num_filters=128, conv3_filter_size=(2, 2), pool3_pool_size=(2, 2),
dropout3_p=0.3,
hidden4_num_units=1000,
dropout4_p=0.5,
hidden5_num_units=1000,
output_num_units=30, output_nonlinearity=None,
update_learning_rate=theano.shared(float32(0.03)),
update_momentum=theano.shared(float32(0.9)),
regression=True,
batch_iterator_train=FlipBatchIterator(batch_size=128),
on_epoch_finished=[
AdjustVariable('update_learning_rate', start=0.03, stop=0.0001),
AdjustVariable('update_momentum', start=0.9, stop=0.999),
EarlyStopping(patience=200),
],
max_epochs=3000,
verbose=1,
)
Example #18
| Source File: vgg19.py From Recipes with MIT License | 4 votes |
|
def build_model():
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1_1'] = ConvLayer(
net['input'], 64, 3, pad=1, flip_filters=False)
net['conv1_2'] = ConvLayer(
net['conv1_1'], 64, 3, pad=1, flip_filters=False)
net['pool1'] = PoolLayer(net['conv1_2'], 2)
net['conv2_1'] = ConvLayer(
net['pool1'], 128, 3, pad=1, flip_filters=False)
net['conv2_2'] = ConvLayer(
net['conv2_1'], 128, 3, pad=1, flip_filters=False)
net['pool2'] = PoolLayer(net['conv2_2'], 2)
net['conv3_1'] = ConvLayer(
net['pool2'], 256, 3, pad=1, flip_filters=False)
net['conv3_2'] = ConvLayer(
net['conv3_1'], 256, 3, pad=1, flip_filters=False)
net['conv3_3'] = ConvLayer(
net['conv3_2'], 256, 3, pad=1, flip_filters=False)
net['conv3_4'] = ConvLayer(
net['conv3_3'], 256, 3, pad=1, flip_filters=False)
net['pool3'] = PoolLayer(net['conv3_4'], 2)
net['conv4_1'] = ConvLayer(
net['pool3'], 512, 3, pad=1, flip_filters=False)
net['conv4_2'] = ConvLayer(
net['conv4_1'], 512, 3, pad=1, flip_filters=False)
net['conv4_3'] = ConvLayer(
net['conv4_2'], 512, 3, pad=1, flip_filters=False)
net['conv4_4'] = ConvLayer(
net['conv4_3'], 512, 3, pad=1, flip_filters=False)
net['pool4'] = PoolLayer(net['conv4_4'], 2)
net['conv5_1'] = ConvLayer(
net['pool4'], 512, 3, pad=1, flip_filters=False)
net['conv5_2'] = ConvLayer(
net['conv5_1'], 512, 3, pad=1, flip_filters=False)
net['conv5_3'] = ConvLayer(
net['conv5_2'], 512, 3, pad=1, flip_filters=False)
net['conv5_4'] = ConvLayer(
net['conv5_3'], 512, 3, pad=1, flip_filters=False)
net['pool5'] = PoolLayer(net['conv5_4'], 2)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['fc6_dropout'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['fc6_dropout'], num_units=4096)
net['fc7_dropout'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(
net['fc7_dropout'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
return net
Example #19
| Source File: vgg16_lymph.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_model():
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1_1'] = ConvLayer(
net['input'], 64, 3, pad=1, flip_filters=False)
net['conv1_2'] = ConvLayer(
net['conv1_1'], 64, 3, pad=1, flip_filters=False)
net['pool1'] = PoolLayer(net['conv1_2'], 2)
net['conv2_1'] = ConvLayer(
net['pool1'], 128, 3, pad=1, flip_filters=False)
net['conv2_2'] = ConvLayer(
net['conv2_1'], 128, 3, pad=1, flip_filters=False)
net['pool2'] = PoolLayer(net['conv2_2'], 2)
net['conv3_1'] = ConvLayer(
net['pool2'], 256, 3, pad=1, flip_filters=False)
net['conv3_2'] = ConvLayer(
net['conv3_1'], 256, 3, pad=1, flip_filters=False)
net['conv3_3'] = ConvLayer(
net['conv3_2'], 256, 3, pad=1, flip_filters=False)
net['pool3'] = PoolLayer(net['conv3_3'], 2)
net['conv4_1'] = ConvLayer(
net['pool3'], 512, 3, pad=1, flip_filters=False)
net['conv4_2'] = ConvLayer(
net['conv4_1'], 512, 3, pad=1, flip_filters=False)
net['conv4_3'] = ConvLayer(
net['conv4_2'], 512, 3, pad=1, flip_filters=False)
net['pool4'] = PoolLayer(net['conv4_3'], 2)
net['conv5_1'] = ConvLayer(
net['pool4'], 512, 3, pad=1, flip_filters=False)
net['conv5_2'] = ConvLayer(
net['conv5_1'], 512, 3, pad=1, flip_filters=False)
net['conv5_3'] = ConvLayer(
net['conv5_2'], 512, 3, pad=1, flip_filters=False)
net['pool5'] = PoolLayer(net['conv5_3'], 2)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['fc6_dropout'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['fc6_dropout'], num_units=4096)
net['fc7_dropout'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(
net['fc7_dropout'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
output_layer = net['prob'];
return output_layer
Example #20
| Source File: vgg16.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_model():
net = {}
input_var = theano.tensor.tensor4('input_var');
net['input'] = InputLayer((None, 3, 224, 224), input_var=input_var)
net['conv1_1'] = ConvLayer(
net['input'], 64, 3, pad=1, flip_filters=False)
net['conv1_2'] = ConvLayer(
net['conv1_1'], 64, 3, pad=1, flip_filters=False)
net['pool1'] = PoolLayer(net['conv1_2'], 2)
net['conv2_1'] = ConvLayer(
net['pool1'], 128, 3, pad=1, flip_filters=False)
net['conv2_2'] = ConvLayer(
net['conv2_1'], 128, 3, pad=1, flip_filters=False)
net['pool2'] = PoolLayer(net['conv2_2'], 2)
net['conv3_1'] = ConvLayer(
net['pool2'], 256, 3, pad=1, flip_filters=False)
net['conv3_2'] = ConvLayer(
net['conv3_1'], 256, 3, pad=1, flip_filters=False)
net['conv3_3'] = ConvLayer(
net['conv3_2'], 256, 3, pad=1, flip_filters=False)
net['pool3'] = PoolLayer(net['conv3_3'], 2)
net['conv4_1'] = ConvLayer(
net['pool3'], 512, 3, pad=1, flip_filters=False)
net['conv4_2'] = ConvLayer(
net['conv4_1'], 512, 3, pad=1, flip_filters=False)
net['conv4_3'] = ConvLayer(
net['conv4_2'], 512, 3, pad=1, flip_filters=False)
net['pool4'] = PoolLayer(net['conv4_3'], 2)
net['conv5_1'] = ConvLayer(
net['pool4'], 512, 3, pad=1, flip_filters=False)
net['conv5_2'] = ConvLayer(
net['conv5_1'], 512, 3, pad=1, flip_filters=False)
net['conv5_3'] = ConvLayer(
net['conv5_2'], 512, 3, pad=1, flip_filters=False)
net['pool5'] = PoolLayer(net['conv5_3'], 2)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['fc6_dropout'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['fc6_dropout'], num_units=4096)
net['fc7_dropout'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(
net['fc7_dropout'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
output_layer = net['prob'];
return net, output_layer, input_var;
Example #21
| Source File: vgg16_full.py From u24_lymphocyte with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def build_model():
net = {}
input_var = theano.tensor.tensor4('input_var');
net['input'] = InputLayer((None, 3, 224, 224), input_var=input_var)
net['conv1_1'] = ConvLayer(
net['input'], 64, 3, pad=1, flip_filters=False)
net['conv1_2'] = ConvLayer(
net['conv1_1'], 64, 3, pad=1, flip_filters=False)
net['pool1'] = PoolLayer(net['conv1_2'], 2)
net['conv2_1'] = ConvLayer(
net['pool1'], 128, 3, pad=1, flip_filters=False)
net['conv2_2'] = ConvLayer(
net['conv2_1'], 128, 3, pad=1, flip_filters=False)
net['pool2'] = PoolLayer(net['conv2_2'], 2)
net['conv3_1'] = ConvLayer(
net['pool2'], 256, 3, pad=1, flip_filters=False)
net['conv3_2'] = ConvLayer(
net['conv3_1'], 256, 3, pad=1, flip_filters=False)
net['conv3_3'] = ConvLayer(
net['conv3_2'], 256, 3, pad=1, flip_filters=False)
net['pool3'] = PoolLayer(net['conv3_3'], 2)
net['conv4_1'] = ConvLayer(
net['pool3'], 512, 3, pad=1, flip_filters=False)
net['conv4_2'] = ConvLayer(
net['conv4_1'], 512, 3, pad=1, flip_filters=False)
net['conv4_3'] = ConvLayer(
net['conv4_2'], 512, 3, pad=1, flip_filters=False)
net['pool4'] = PoolLayer(net['conv4_3'], 2)
net['conv5_1'] = ConvLayer(
net['pool4'], 512, 3, pad=1, flip_filters=False)
net['conv5_2'] = ConvLayer(
net['conv5_1'], 512, 3, pad=1, flip_filters=False)
net['conv5_3'] = ConvLayer(
net['conv5_2'], 512, 3, pad=1, flip_filters=False)
net['pool5'] = PoolLayer(net['conv5_3'], 2)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['fc6_dropout'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['fc6_dropout'], num_units=4096)
net['fc7_dropout'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(
net['fc7_dropout'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
output_layer = net['prob'];
return net, output_layer, input_var;
Example #22
| Source File: vgg16.py From Recipes with MIT License | 4 votes |
|
def build_model():
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1_1'] = ConvLayer(
net['input'], 64, 3, pad=1, flip_filters=False)
net['conv1_2'] = ConvLayer(
net['conv1_1'], 64, 3, pad=1, flip_filters=False)
net['pool1'] = PoolLayer(net['conv1_2'], 2)
net['conv2_1'] = ConvLayer(
net['pool1'], 128, 3, pad=1, flip_filters=False)
net['conv2_2'] = ConvLayer(
net['conv2_1'], 128, 3, pad=1, flip_filters=False)
net['pool2'] = PoolLayer(net['conv2_2'], 2)
net['conv3_1'] = ConvLayer(
net['pool2'], 256, 3, pad=1, flip_filters=False)
net['conv3_2'] = ConvLayer(
net['conv3_1'], 256, 3, pad=1, flip_filters=False)
net['conv3_3'] = ConvLayer(
net['conv3_2'], 256, 3, pad=1, flip_filters=False)
net['pool3'] = PoolLayer(net['conv3_3'], 2)
net['conv4_1'] = ConvLayer(
net['pool3'], 512, 3, pad=1, flip_filters=False)
net['conv4_2'] = ConvLayer(
net['conv4_1'], 512, 3, pad=1, flip_filters=False)
net['conv4_3'] = ConvLayer(
net['conv4_2'], 512, 3, pad=1, flip_filters=False)
net['pool4'] = PoolLayer(net['conv4_3'], 2)
net['conv5_1'] = ConvLayer(
net['pool4'], 512, 3, pad=1, flip_filters=False)
net['conv5_2'] = ConvLayer(
net['conv5_1'], 512, 3, pad=1, flip_filters=False)
net['conv5_3'] = ConvLayer(
net['conv5_2'], 512, 3, pad=1, flip_filters=False)
net['pool5'] = PoolLayer(net['conv5_3'], 2)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['fc6_dropout'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['fc6_dropout'], num_units=4096)
net['fc7_dropout'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(
net['fc7_dropout'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
return net
Example #23
| 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
Example #24
| Source File: neuralforest.py From ShallowNeuralDecisionForest with MIT License | 4 votes |
|
def __init__(self, n_inputs, n_outputs, regression, multiclass=False, depth=5, n_estimators=20, n_hidden=128, learning_rate=0.01, num_epochs=500, pi_iters=20, sgd_iters=10, batch_size=1000, momentum=0.0, dropout=0.0, loss=None, update=adagrad):
"""
Parameters
----------
n_inputs : number of input features
n_outputs : number of classes to predict (1 for regression)
for 2 class classification n_outputs should be 2, not 1
regression : True for regression, False for classification
multiclass : not used
depth : depth of each tree in the ensemble
n_estimators : number of trees in the ensemble
n_hidden : number of neurons in the hidden layer
pi_iters : number of iterations for the iterative algorithm that updates pi
sgd_iters : number of full iterations of sgd between two consequtive updates of pi
loss : theano loss function. If None, squared error will be used for regression and
cross entropy will be used for classification
update : theano update function
"""
self._depth = depth
self._n_estimators = n_estimators
self._n_hidden = n_hidden
self._n_outputs = n_outputs
self._loss = loss
self._regression = regression
self._multiclass = multiclass
self._learning_rate = learning_rate
self._num_epochs = num_epochs
self._pi_iters = pi_iters
self._sgd_iters = sgd_iters
self._batch_size = batch_size
self._momentum = momentum
self._update = update
self.t_input = T.matrix('input')
self.t_label = T.matrix('output')
self._cached_trainable_params = None
self._cached_params = None
self._n_net_out = n_estimators * ((1 << depth) - 1)
self.l_input = InputLayer((None, n_inputs))
self.l_dense1 = DenseLayer(self.l_input, self._n_hidden, nonlinearity=rectify)
if dropout != 0:
self.l_dense1 = DropoutLayer(self.l_dense1, p=dropout)
if not __DEBUG_NO_FOREST__:
self.l_dense2 = DenseLayer(self.l_dense1, self._n_net_out, nonlinearity=sigmoid)
self.l_forest = NeuralForestLayer(self.l_dense2, self._depth, self._n_estimators, self._n_outputs, self._pi_iters)
else:
self.l_forest = DenseLayer(self.l_dense1, self._n_outputs, nonlinearity=softmax)
Example #25
| Source File: vgg_cnn_s.py From Recipes with MIT License | 4 votes |
|
def build_model():
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
# caffe has alpha = alpha * pool_size
net['norm1'] = NormLayer(net['conv1'], alpha=0.0001)
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['drop7'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
return net
