def build_model(input_shape, input_var, dense=True):
net = {}
net['input'] = InputLayer(input_shape, input_var=input_var)
net['input'].num_filters = input_shape[1]
net['conv1'] = ConvLayer(net['input'], num_filters=128, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv2'] = ConvLayer(net['conv1'], num_filters=256, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['pool1'] = ConvLayer(net['conv2'], num_filters=256, filter_size=3, stride=2, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv3'] = ConvLayer(net['pool1'], num_filters=512, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['pool2'] = ConvLayer(net['conv3'], num_filters=512, filter_size=3, stride=2, nonlinearity=nonlinearities.leaky_rectify, pad='same')
if dense:
net['dense'] = dropout(DenseLayer(net['pool2'], num_units=1024, nonlinearity=nonlinearities.leaky_rectify), 0.5)
# Deconv
net['dense/inverse'] = inverse_dense_layer(net['dense'], net['dense'], net['pool2'].output_shape)
net['pool2/inverse'] = inverse_convolution_strided_layer(net['dense/inverse'], net['pool2'])
else:
net['pool2/inverse'] = inverse_convolution_strided_layer(net['pool2'], net['pool2'])
net['conv3/inverse'] = inverse_convolution_layer(net['pool2/inverse'], net['conv3'])
net['pool1/inverse'] = inverse_convolution_strided_layer(net['conv3/inverse'], net['pool1'])
net['conv2/inverse'] = inverse_convolution_layer(net['pool1/inverse'], net['conv2'])
net['conv1/inverse'] = inverse_convolution_layer(net['conv2/inverse'], net['conv1'])
net['conv0/inverse'] = ConvLayer(net['conv1/inverse'], num_filters=input_shape[1], filter_size=1, nonlinearity=nonlinearities.linear, pad='same')
net['prob'] = net['conv0/inverse']
for layer in get_all_layers(net['prob']):
print layer
print layer.output_shape
return net
def build_model_small(input_shape, input_var):
net = {}
net['input'] = InputLayer(input_shape, input_var=input_var)
net['input'].num_filters = input_shape[1]
net['conv1'] = batch_norm(
ConvLayer(net['input'],
num_filters=256,
filter_size=11,
nonlinearity=nonlinearities.leaky_rectify,
pad='same'))
net['pool1'] = dropout(PoolLayer(net['conv1'], 2, mode='max'), 0.5)
net['conv2'] = batch_norm(
ConvLayer(net['pool1'],
num_filters=256,
filter_size=7,
nonlinearity=nonlinearities.leaky_rectify,
pad='same'))
net['pool2'] = dropout(PoolLayer(net['conv2'], 2, mode='max'), 0.5)
net['conv3'] = batch_norm(
ConvLayer(net['pool2'],
num_filters=396,
filter_size=5,
nonlinearity=nonlinearities.leaky_rectify,
pad='same'))
net['pool3'] = dropout(PoolLayer(net['conv3'], 2, mode='max'), 0.5)
net['conv4'] = dropout(
batch_norm(
ConvLayer(net['pool3'],
num_filters=512,
filter_size=3,
nonlinearity=nonlinearities.leaky_rectify,
pad='same')), 0.5)
net['conv5'] = dropout(
batch_norm(
ConvLayer(net['conv4'],
num_filters=1024,
filter_size=1,
nonlinearity=nonlinearities.leaky_rectify,
pad='same')), 0.5)
net['dense1'] = dropout(
batch_norm(
DenseLayer(net['conv5'],
num_units=1024,
nonlinearity=nonlinearities.leaky_rectify)), 0.5)
net['dense2'] = DenseLayer(net['dense1'],
num_units=11,
nonlinearity=nonlinearities.softmax)
net['prob'] = net['dense2']
for layer in get_all_layers(net['prob']):
print layer
print layer.output_shape
return net
def build_model_dense(input_shape, input_var):
net = {}
net['input'] = InputLayer(input_shape, input_var=input_var)
net['input'].num_filters = input_shape[1]
net['conv1'] = ConvLayer(net['input'], num_filters=256, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv2'] = ConvLayer(net['conv1'], num_filters=256, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv2/reshape'] = ReshapeLayer(net['conv2'], (-1, net['conv2'].output_shape[1] * net['conv2'].output_shape[2]))
net['dense'] = dropout(DenseLayer(net['conv2/reshape'], num_units=1024, nonlinearity=nonlinearities.leaky_rectify), 0.5)
net['dense/inverse'] = inverse_dense_layer(net['dense'], net['dense'], net['conv2'].output_shape)
net['conv2/inverse'] = inverse_convolution_layer(net['dense/inverse'], net['conv2'])
net['conv1/inverse'] = inverse_convolution_layer(net['conv2/inverse'], net['conv1'])
net['conv0/inverse'] = ConvLayer(net['conv1/inverse'], num_filters=input_shape[1], filter_size=1,nonlinearity=nonlinearities.linear, pad='same')
net['prob'] = net['conv0/inverse']
for layer in get_all_layers(net['prob']):
print layer
print layer.output_shape
return net
def build_model_small(input_shape, input_var):
net = {}
net['input'] = InputLayer(input_shape, input_var=input_var)
net['input'].num_filters = input_shape[1]
net['conv1'] = batch_norm(ConvLayer(net['input'], num_filters=256, filter_size=11, nonlinearity=nonlinearities.leaky_rectify, pad='same'))
net['pool1'] = dropout(PoolLayer(net['conv1'], 2, mode='max'), 0.5)
net['conv2'] = batch_norm(ConvLayer(net['pool1'], num_filters=256, filter_size=7, nonlinearity=nonlinearities.leaky_rectify, pad='same'))
net['pool2'] = dropout(PoolLayer(net['conv2'], 2, mode='max'), 0.5)
net['conv3'] = batch_norm(ConvLayer(net['pool2'], num_filters=396, filter_size=5, nonlinearity=nonlinearities.leaky_rectify, pad='same'))
net['pool3'] = dropout(PoolLayer(net['conv3'], 2, mode='max'), 0.5)
net['conv4'] = dropout(batch_norm(ConvLayer(net['pool3'], num_filters=512, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')), 0.5)
net['conv5'] = dropout(batch_norm(ConvLayer(net['conv4'], num_filters=1024, filter_size=1, nonlinearity=nonlinearities.leaky_rectify,pad='same')), 0.5)
net['dense1'] = dropout(batch_norm(DenseLayer(net['conv5'], num_units=1024, nonlinearity=nonlinearities.leaky_rectify)), 0.5)
net['dense2'] = DenseLayer(net['dense1'], num_units=11, nonlinearity=nonlinearities.softmax)
net['prob'] = net['dense2']
for layer in get_all_layers(net['prob']):
print layer
print layer.output_shape
return net
def build_model_small(input_shape, input_var):
net = {}
net['input'] = InputLayer(input_shape, input_var=input_var)
net['input'].num_filters = input_shape[1]
net['conv1'] = ConvLayer(net['input'], num_filters=256, filter_size=11, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv2'] = ConvLayer(net['conv1'], num_filters=256, filter_size=7, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv3'] = ConvLayer(net['conv2'], num_filters=396, filter_size=5, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv4'] = ConvLayer(net['conv3'], num_filters=512, filter_size=3, nonlinearity=nonlinearities.leaky_rectify, pad='same')
net['conv5'] = ConvLayer(net['conv4'], num_filters=1024, filter_size=1, nonlinearity=nonlinearities.leaky_rectify,pad='same')
net['conv5/inverse'] = inverse_convolution_layer(net['conv5'], net['conv5'])
net['conv4/inverse'] = inverse_convolution_layer(net['conv5/inverse'], net['conv4'])
net['conv3/inverse'] = inverse_convolution_layer(net['conv4/inverse'], net['conv3'])
net['conv2/inverse'] = inverse_convolution_layer(net['conv3/inverse'], net['conv2'])
net['conv1/inverse'] = inverse_convolution_layer(net['conv2/inverse'], net['conv1'])
net['conv0/inverse'] = ConvLayer(net['conv1/inverse'], num_filters=input_shape[1], filter_size=1,nonlinearity=nonlinearities.linear, pad='same')
net['prob'] = net['conv0/inverse']
for layer in get_all_layers(net['prob']):
print layer
print layer.output_shape
return net