def setup_model(self, input=None):
"""Use lasagne to create a network of convolution layers, first using VGG19 as the framework
and then adding augmentations for Semantic Style Transfer.
"""
net, self.channels = {}, {}
# Primary network for the main image. These are convolution only, and stop at layer 4_2 (rest unused).
net['img'] = input or InputLayer((None, 3, None, None))
net['conv1_1'] = ConvLayer(net['img'], 64, 3, pad=1)
net['conv1_2'] = ConvLayer(net['conv1_1'], 64, 3, pad=1)
net['pool1'] = PoolLayer(net['conv1_2'], 2, mode='average_exc_pad')
net['conv2_1'] = ConvLayer(net['pool1'], 128, 3, pad=1)
net['conv2_2'] = ConvLayer(net['conv2_1'], 128, 3, pad=1)
net['pool2'] = PoolLayer(net['conv2_2'], 2, mode='average_exc_pad')
net['conv3_1'] = ConvLayer(net['pool2'], 256, 3, pad=1)
net['conv3_2'] = ConvLayer(net['conv3_1'], 256, 3, pad=1)
net['conv3_3'] = ConvLayer(net['conv3_2'], 256, 3, pad=1)
net['conv3_4'] = ConvLayer(net['conv3_3'], 256, 3, pad=1)
net['pool3'] = PoolLayer(net['conv3_4'], 2, mode='average_exc_pad')
net['conv4_1'] = ConvLayer(net['pool3'], 512, 3, pad=1)
net['conv4_2'] = ConvLayer(net['conv4_1'], 512, 3, pad=1)
net['conv4_3'] = ConvLayer(net['conv4_2'], 512, 3, pad=1)
net['conv4_4'] = ConvLayer(net['conv4_3'], 512, 3, pad=1)
net['pool4'] = PoolLayer(net['conv4_4'], 2, mode='average_exc_pad')
net['conv5_1'] = ConvLayer(net['pool4'], 512, 3, pad=1)
net['conv5_2'] = ConvLayer(net['conv5_1'], 512, 3, pad=1)
net['conv5_3'] = ConvLayer(net['conv5_2'], 512, 3, pad=1)
net['conv5_4'] = ConvLayer(net['conv5_3'], 512, 3, pad=1)
net['main'] = net['conv5_4']
# Auxiliary network for the semantic layers, and the nearest neighbors calculations.
net['map'] = InputLayer((1, 1, None, None))
for j, i in itertools.product(range(5), range(4)):
if j < 2 and i > 1: continue
suffix = '%i_%i' % (j+1, i+1)
if i == 0:
net['map%i'%(j+1)] = PoolLayer(net['map'], 2**j, mode='average_exc_pad')
self.channels[suffix] = net['conv'+suffix].num_filters
if args.semantic_weight > 0.0:
net['sem'+suffix] = ConcatLayer([net['conv'+suffix], net['map%i'%(j+1)]])
else:
net['sem'+suffix] = net['conv'+suffix]
net['dup'+suffix] = InputLayer(net['sem'+suffix].output_shape)
net['nn'+suffix] = ConvLayer(net['dup'+suffix], 1, 3, b=None, pad=0, flip_filters=False)
self.network = net
python类Pool2DLayer()的实例源码
def build_model_resnet50(input_shape):
net = {}
net['input'] = InputLayer(input_shape)
sub_net, parent_layer_name = build_simple_block(
net['input'], ['conv1', 'bn_conv1', 'conv1_relu'],
64, 7, 2, 3, use_bias=True)
net.update(sub_net)
net['pool1'] = PoolLayer(net[parent_layer_name], pool_size=3, stride=2, pad=0, mode='max', ignore_border=False)
block_size = list('abc')
parent_layer_name = 'pool1'
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1, 1, True, 4, ix='2%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='2%s' % c)
net.update(sub_net)
# block_size = ['a'] + ['b'+str(i+1) for i in range(7)]
block_size = list('abcd')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='3%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='3%s' % c)
net.update(sub_net)
# block_size = ['a'] + ['b'+str(i+1) for i in range(35)]
block_size = list('abcdef')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='4%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='4%s' % c)
net.update(sub_net)
block_size = list('abc')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='5%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='5%s' % c)
net.update(sub_net)
net['pool5'] = PoolLayer(net[parent_layer_name], pool_size=7, stride=1, pad=0,
mode='average_exc_pad', ignore_border=False)
net['fc1000'] = DenseLayer(net['pool5'], num_units=1000, nonlinearity=None, W=lasagne.init.Normal(std=0.01, mean=0.0))
net['prob'] = NonlinearityLayer(net['fc1000'], nonlinearity=softmax)
return net
# model hyperparams
def build_model_resnet152(input_shape):
net = {}
net['input'] = InputLayer(input_shape)
sub_net, parent_layer_name = build_simple_block(
net['input'], ['conv1', 'bn_conv1', 'conv1_relu'],
64, 7, 2, 3, use_bias=True)
net.update(sub_net)
net['pool1'] = PoolLayer(net[parent_layer_name], pool_size=3, stride=2, pad=0, mode='max', ignore_border=False)
block_size = list('abc')
parent_layer_name = 'pool1'
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1, 1, True, 4, ix='2%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='2%s' % c)
net.update(sub_net)
block_size = ['a'] + ['b'+str(i+1) for i in range(7)]
# block_size = list('abcd')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='3%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='3%s' % c)
net.update(sub_net)
block_size = ['a'] + ['b'+str(i+1) for i in range(35)]
# block_size = list('abcdef')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='4%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='4%s' % c)
net.update(sub_net)
block_size = list('abc')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='5%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='5%s' % c)
net.update(sub_net)
net['pool5'] = PoolLayer(net[parent_layer_name], pool_size=7, stride=1, pad=0,
mode='average_exc_pad', ignore_border=False)
net['fc1000'] = DenseLayer(net['pool5'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc1000'], nonlinearity=softmax)
print('Total number of layers:', len(lasagne.layers.get_all_layers(net['prob'])))
return net
# model hyperparams
def build(input_height, input_width, concat_var):
"""
Build the discriminator, all weights initialized from scratch
:param input_width:
:param input_height:
:param concat_var: Theano symbolic tensor variable
:return: Dictionary that contains the discriminator
"""
net = {'input': InputLayer((None, 4, input_height, input_width), input_var=concat_var)}
print "Input: {}".format(net['input'].output_shape[1:])
net['merge'] = ConvLayer(net['input'], 3, 1, pad=0, flip_filters=False)
print "merge: {}".format(net['merge'].output_shape[1:])
net['conv1'] = ConvLayer(net['merge'], 32, 3, pad=1)
print "conv1: {}".format(net['conv1'].output_shape[1:])
net['pool1'] = PoolLayer(net['conv1'], 4)
print "pool1: {}".format(net['pool1'].output_shape[1:])
net['conv2_1'] = ConvLayer(net['pool1'], 64, 3, pad=1)
print "conv2_1: {}".format(net['conv2_1'].output_shape[1:])
net['conv2_2'] = ConvLayer(net['conv2_1'], 64, 3, pad=1)
print "conv2_2: {}".format(net['conv2_2'].output_shape[1:])
net['pool2'] = PoolLayer(net['conv2_2'], 2)
print "pool2: {}".format(net['pool2'].output_shape[1:])
net['conv3_1'] = nn.weight_norm(ConvLayer(net['pool2'], 64, 3, pad=1))
print "conv3_1: {}".format(net['conv3_1'].output_shape[1:])
net['conv3_2'] = nn.weight_norm(ConvLayer(net['conv3_1'], 64, 3, pad=1))
print "conv3_2: {}".format(net['conv3_2'].output_shape[1:])
net['pool3'] = PoolLayer(net['conv3_2'], 2)
print "pool3: {}".format(net['pool3'].output_shape[1:])
net['fc4'] = DenseLayer(net['pool3'], num_units=100, nonlinearity=tanh)
print "fc4: {}".format(net['fc4'].output_shape[1:])
net['fc5'] = DenseLayer(net['fc4'], num_units=2, nonlinearity=tanh)
print "fc5: {}".format(net['fc5'].output_shape[1:])
net['prob'] = DenseLayer(net['fc5'], num_units=1, nonlinearity=sigmoid)
print "prob: {}".format(net['prob'].output_shape[1:])
return net
def setup_model(self, input=None):
"""Use lasagne to create a network of convolution layers, first using VGG19 as the framework
and then adding augmentations for Semantic Style Transfer.
"""
net, self.channels = {}, {}
# Primary network for the main image. These are convolution only, and stop at layer 4_2 (rest unused).
net['img'] = input or InputLayer((None, 3, None, None))
net['conv1_1'] = ConvLayer(net['img'], 64, 3, pad=1)
net['conv1_2'] = ConvLayer(net['conv1_1'], 64, 3, pad=1)
net['pool1'] = PoolLayer(net['conv1_2'], 2, mode='average_exc_pad')
net['conv2_1'] = ConvLayer(net['pool1'], 128, 3, pad=1)
net['conv2_2'] = ConvLayer(net['conv2_1'], 128, 3, pad=1)
net['pool2'] = PoolLayer(net['conv2_2'], 2, mode='average_exc_pad')
net['conv3_1'] = ConvLayer(net['pool2'], 256, 3, pad=1)
net['conv3_2'] = ConvLayer(net['conv3_1'], 256, 3, pad=1)
net['conv3_3'] = ConvLayer(net['conv3_2'], 256, 3, pad=1)
net['conv3_4'] = ConvLayer(net['conv3_3'], 256, 3, pad=1)
net['pool3'] = PoolLayer(net['conv3_4'], 2, mode='average_exc_pad')
net['conv4_1'] = ConvLayer(net['pool3'], 512, 3, pad=1)
net['conv4_2'] = ConvLayer(net['conv4_1'], 512, 3, pad=1)
net['conv4_3'] = ConvLayer(net['conv4_2'], 512, 3, pad=1)
net['conv4_4'] = ConvLayer(net['conv4_3'], 512, 3, pad=1)
net['pool4'] = PoolLayer(net['conv4_4'], 2, mode='average_exc_pad')
net['conv5_1'] = ConvLayer(net['pool4'], 512, 3, pad=1)
net['conv5_2'] = ConvLayer(net['conv5_1'], 512, 3, pad=1)
net['conv5_3'] = ConvLayer(net['conv5_2'], 512, 3, pad=1)
net['conv5_4'] = ConvLayer(net['conv5_3'], 512, 3, pad=1)
net['main'] = net['conv5_4']
# Auxiliary network for the semantic layers, and the nearest neighbors calculations.
net['map'] = InputLayer((1, 1, None, None))
for j, i in itertools.product(range(5), range(4)):
if j < 2 and i > 1: continue
suffix = '%i_%i' % (j+1, i+1)
if i == 0:
net['map%i'%(j+1)] = PoolLayer(net['map'], 2**j, mode='average_exc_pad')
self.channels[suffix] = net['conv'+suffix].num_filters
if args.semantic_weight > 0.0:
net['sem'+suffix] = ConcatLayer([net['conv'+suffix], net['map%i'%(j+1)]])
else:
net['sem'+suffix] = net['conv'+suffix]
net['dup'+suffix] = InputLayer(net['sem'+suffix].output_shape)
net['nn'+suffix] = ConvLayer(net['dup'+suffix], 1, 3, b=None, pad=0, flip_filters=False)
self.network = net
def build_resnet():
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
sub_net, parent_layer_name = build_simple_block(
net['input'], ['conv1', 'bn_conv1', 'conv1_relu'],
64, 7, 2, 3, use_bias=True)
net.update(sub_net)
net['pool1'] = PoolLayer(net[parent_layer_name], pool_size=3, stride=2,
pad=0, mode='max', ignore_border=False)
block_size = list('abc')
parent_layer_name = 'pool1'
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1, 1, True, 4, ix='2%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/4, 1, False, 4, ix='2%s' % c)
net.update(sub_net)
block_size = list('abcd')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/2, 1.0/2, True, 4, ix='3%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/4, 1, False, 4, ix='3%s' % c)
net.update(sub_net)
block_size = list('abcdef')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/2, 1.0/2, True, 4, ix='4%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/4, 1, False, 4, ix='4%s' % c)
net.update(sub_net)
block_size = list('abc')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/2, 1.0/2, True, 4, ix='5%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name],
1.0/4, 1, False, 4, ix='5%s' % c)
net.update(sub_net)
net['pool5'] = PoolLayer(net[parent_layer_name], pool_size=7, stride=1, pad=0,
mode='average_exc_pad', ignore_border=False)
net['fc1000'] = DenseLayer(net['pool5'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc1000'], nonlinearity=softmax)
return net
def build_model(input_size):
net = {}
net['input'] = InputLayer(input_size)
sub_net, parent_layer_name = build_simple_block(
net['input'], ['conv1', 'bn_conv1', 'conv1_relu'],
64, 7, 2, 3, use_bias=True)
net.update(sub_net)
net['pool1'] = PoolLayer(net[parent_layer_name], pool_size=3, stride=2, pad=0, mode='max', ignore_border=False)
block_size = list('abc')
parent_layer_name = 'pool1'
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1, 1, True, 4, ix='2%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='2%s' % c)
net.update(sub_net)
block_size = list('abcd')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='3%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='3%s' % c)
net.update(sub_net)
block_size = list('abcdef')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='4%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='4%s' % c)
net.update(sub_net)
block_size = list('abc')
for c in block_size:
if c == 'a':
sub_net, parent_layer_name = build_residual_block(
net[parent_layer_name], 1.0/2, 1.0/2, True, 4, ix='5%s' % c)
else:
sub_net, parent_layer_name = build_residual_block(net[parent_layer_name], 1.0/4, 1, False, 4, ix='5%s' % c)
net.update(sub_net)
net['pool5'] = PoolLayer(net[parent_layer_name], pool_size=7, stride=1, pad=0,
mode='average_exc_pad', ignore_border=False)
return net
#Setup the original network
