def create_discriminator(discrim_inputs, discrim_targets):
n_layers = 3
layers = []
ndf = 64
# 2x [batch, height, width, in_channels] => [batch, height, width, in_channels * 2]
input = tf.concat([discrim_inputs, discrim_targets], axis=3)
# layer_1: [batch, 256, 256, in_channels * 2] => [batch, 128, 128, ndf]
with tf.variable_scope("layer_1"):
convolved = tools.conv(input, ndf, stride=2)
rectified = tools.lrelu(convolved, 0.2)
layers.append(rectified)
# layer_2: [batch, 128, 128, ndf] => [batch, 64, 64, ndf * 2]
# layer_3: [batch, 64, 64, ndf * 2] => [batch, 32, 32, ndf * 4]
# layer_4: [batch, 32, 32, ndf * 4] => [batch, 31, 31, ndf * 8]
for i in range(n_layers):
with tf.variable_scope("layer_%d" % (len(layers) + 1)):
out_channels = ndf * min(2**(i + 1), 8)
stride = 1 if i == n_layers - 1 else 2 # last layer here has stride 1
convolved = tools.conv(layers[-1], out_channels, stride=stride)
normalized = tools.batchnorm(convolved)
rectified = tools.lrelu(normalized, 0.2)
layers.append(rectified)
# layer_5: [batch, 31, 31, ndf * 8] => [batch, 30, 30, 1]
with tf.variable_scope("layer_%d" % (len(layers) + 1)):
convolved = tools.conv(rectified, out_channels=1, stride=1)
output = tf.sigmoid(convolved)
layers.append(output)
return layers[-1]
def SVHN(x, n_classes):
import tools
'''
Args:
images: 4D tensor [batch_size, img_width, img_height, img_channel]
Notes:
In each conv layer, the kernel size is:
[kernel_size, kernel_size, number of input channels, number of output channels].
number of input channels are from previuous layer, if previous layer is THE input
layer, number of input channels should be image's channels.
'''
x = tools.conv('conv1', x, 64)
x = tools.pool('pool1', x)
x = tools.conv('conv2', x, 64)
x = tools.pool('pool2', x)
x = tools.conv('conv3', x, 128)
x = tools.pool('pool3', x)
x = tools.FC_layer('fc4', x, out_nodes=64)
x = tools.drop_out('drop_out', x, keep_prob=0.5)
x = tools.final_layer('softmax', x, out_nodes=n_classes)
return x
def lenet5(self):
with tf.name_scope('LeNet5'):
self.conv1 = tools.conv('conv1',
self.input,
32,
kernel_size=[5, 5],
stride=[1, 1, 1, 1],
is_trainable=self.is_trainable)
self.pool1 = tools.pool('pool1',
self.conv1,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.conv2 = tools.conv('conv2',
self.pool1,
64,
kernel_size=[5, 5],
stride=[1, 1, 1, 1],
is_trainable=self.is_trainable)
self.pool2 = tools.pool('pool2',
self.conv2,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.fc1 = tools.fc_layer('fc1', self.pool2, out_nodes=512)
self.dropout1 = tools.dropout('dropout1', self.fc1, self.keep_prob)
self.logits = tools.fc_layer('fc2',
self.dropout1,
use_relu=False,
out_nodes=self.n_classes)
def VGG16(x, isSty, is_pretrain=False):
x = x - np.array([ 123.68 , 116.779, 103.939])
every_layer_output = {}
x = tools.conv('conv1_1', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv1_2', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
every_layer_output['conv1_2'] = x #conv1_2
x = tools.pool('pool1', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv2_1', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv2_2', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
every_layer_output['conv2_2'] = x #conv2_2
if isSty:
x = tools.pool('pool2', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv3_1', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_2', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_3', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
every_layer_output['conv3_3'] = x #conv3_3
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv4_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
every_layer_output['conv4_3'] = x #conv4_3
# x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
#
# x = tools.conv('conv5_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# x = tools.conv('conv5_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# x = tools.conv('conv5_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
#
# x = tools.FC_layer('fc6', x, out_nodes=4096)
# #x = tools.batch_norm(x)
# x = tools.FC_layer('fc7', x, out_nodes=4096)
# #x = tools.batch_norm(x)
# x = tools.FC_layer('fc8', x, out_nodes=n_classes)
return every_layer_output
def Network(x, n_classes, dropout):
global is_training
x = tf.reshape(x, [-1, 28, 28, 1])
x = tools.conv('conv1', x, 32, kernel_size=[5, 5], is_pretrain=is_pretrain)
x = tools.pool('pool1', x, is_max_pool=True)
x = tools.conv('conv2', x, 64, is_pretrain=is_pretrain)
x = tools.pool('pool2', x, is_max_pool=True)
fc_x = tools.FC_layer('FC1', x, 1024)
fc_x = tf.layers.dropout(fc_x, rate=dropout, training=is_training)
out = tools.FC_layer('FC2', fc_x, n_classes)
return out
def Model_finetune(layer, n_classes, is_pretrain=True):
# '''
# Model_finetune: that uses varies tools.py function to setup CNN and returns the logits
# Arg: layer(tensor), n_classes(int), is_pretrain(Booleen)
# layer: list of images that are decoded in tensor
# n_classes: batch size for the training
# is_pretrain: number of classification for output
# Return: layer(logits)
# '''
with tf.name_scope('Model_finetune'):
# first conv + pool
layer = tools.conv('conv1_1', layer, 64, kernel_size=[7,7], stride=[1,1,1,1], is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
layer = tools.pool('pool1', layer, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
# second conv + pool
layer = tools.conv('conv2_1', layer, 128, kernel_size=[7,7], stride=[1,1,1,1], is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
layer = tools.pool('pool2', layer, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
# thrid conv + pool
layer = tools.conv('conv3_1', layer, 256, kernel_size=[7,7], stride=[1,1,1,1], is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
layer = tools.pool('pool3', layer, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
# fourth conv + pool
layer = tools.conv('conv4_1', layer, 512, kernel_size=[7,7], stride=[1,1,1,1], is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
layer = tools.pool('pool4', layer, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
# fifth conv + pool
layer = tools.conv('conv5_1', layer, 512, kernel_size=[7,7], stride=[1,1,1,1], is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
layer = tools.pool('pool5', layer, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
# 3 fully connected layers, last one is softmax
layer = tools.FC_layer('fc6', layer, out_nodes=2048)
with tf.name_scope('batch_norm1'):
layer = tools.batch_norm(layer)
layer = tools.FC_layer('fc7', layer, out_nodes=2048)
with tf.name_scope('batch_norm2'):
layer = tools.batch_norm(layer)
layer = tools.FC_layer('fc8', layer, out_nodes=n_classes)
return layer
def build_renet(inputs,
num_classes,
use_bottleneck=False,
num_residual_units=5,
relu_leakiness=0.0):
with tf.variable_scope('init'):
x = inputs
x = tools.conv('init_conv', x, 3, 3, 16, _stride_arr(1))
strides = [1, 2, 2]
activate_before_residual = [True, False, False]
if use_bottleneck:
res_func = tools.bottleneck_residual
filters = [16, 64, 128, 256]
else:
res_func = tools.residual
filters = [16, 16, 32, 64]
# first group
with tf.variable_scope('unit_1_0'):
x = res_func(x, filters[0], filters[1], _stride_arr(strides[0]),
activate_before_residual[0])
for i in six.moves.range(1, num_residual_units):
with tf.variable_scope('unit_1_%d' % i):
x = res_func(x, filters[1], filters[1], _stride_arr(1), False)
# second group
with tf.variable_scope('unit_2_0'):
x = res_func(x, filters[1], filters[2], _stride_arr(strides[1]),
activate_before_residual[1])
for i in six.moves.range(1, num_residual_units):
with tf.variable_scope('unit_2_%d' % i):
x = res_func(x, filters[2], filters[2], _stride_arr(1), False)
# third group
with tf.variable_scope('unit_3_0'):
x = res_func(x, filters[2], filters[3], _stride_arr(strides[2]),
activate_before_residual[2])
for i in six.moves.range(1, num_residual_units):
with tf.variable_scope('unit_3_%d' % i):
x = res_func(x, filters[3], filters[3], _stride_arr(1), False)
# all pool layer
with tf.variable_scope('unit_last'):
x = tools.batch_norm('final_bn', x)
x = tools.relu(x, relu_leakiness)
x = tools.global_avg_pool(x)
# fc_layer + softmax
with tf.variable_scope('logit'):
logits = tools.fully_connected(x, num_classes)
predictions = tf.nn.softmax(logits)
return logits, predictions
def Network(x, n_classes, dropout, reuse, is_training):
with tf.variable_scope('ConvNet', reuse=reuse):
x = x['images']
x = tf.reshape(x, [-1, 28, 28, 1])
x = tools.conv('conv1',
x,
32,
kernel_size=[5, 5],
is_pretrain=is_pretrain)
x = tools.pool('pool1', x, is_max_pool=True)
x = tools.conv('conv2', x, 64, is_pretrain=is_pretrain)
x = tools.pool('pool2', x, is_max_pool=True)
fc_x = tools.FC_layer('FC1', x, 1024)
fc_x = tf.layers.dropout(fc_x, rate=dropout, training=is_training)
out = tools.FC_layer('FC2', fc_x, n_classes)
return out
def LeNet5(self):
with tf.name_scope('LeNet5'):
self.conv1 = tools.conv('conv1',
self.input,
16,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool1 = tools.pool('pool1',
self.conv1,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
self.conv2 = tools.conv('conv2',
self.pool1,
16,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool2 = tools.pool('pool2',
self.conv2,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
self.fc1 = tools.FC_layer('local3', self.pool2, out_nodes=128)
self.norm1 = tools.batch_norm('batch_norm1', self.fc1)
self.fc2 = tools.FC_layer('local4', self.norm1, out_nodes=128)
self.norm2 = tools.batch_norm('batch_norm2', self.fc2)
self.fc3 = tools.FC_layer('softmax_linear',
self.norm2,
out_nodes=self.n_classes,
use_relu=False)
def AlexNet(x, n_classes, is_pretrain=True):
with tf.name_scope('AlexNet'):
x = tools.conv('conv1',
x,
16,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool1',
x,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
x = tools.conv('conv2',
x,
16,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool2',
x,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
x = tools.FC_layer('local3', x, out_nodes=128)
x = tools.batch_norm('batch_norm1', x)
x = tools.FC_layer('local4', x, out_nodes=128)
x = tools.batch_norm('batch_norm2', x)
x = tools.FC_layer('softmax_linear', x, out_nodes=n_classes)
return x
def mnist_net(x, prob):
with tf.variable_scope('mnist_net'):
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# first convolution layer
x = tools.conv('conv_layer_1',
x,
32,
kernel_size=[5, 5],
stride=[1, 1, 1, 1])
with tf.name_scope('max_pool_1'):
x = tools.pool('max_pool_1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1])
# second convolution layer
x = tools.conv('conv_layer_2',
x,
64,
kernel_size=[5, 5],
stride=[1, 1, 1, 1])
with tf.name_scope('max_pool_2'):
x = tools.pool('max_pool_2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1])
# fully convolution layers
x = tools.FC_layer('fc_layer_1', x, 1024)
x = tf.nn.relu(x)
x = tools.drop(x, prob)
x = tools.FC_layer('fc_layer_2', x, 10)
return x
def VGG16(x, n_classes, is_pretrain=True):
x = tools.conv('conv1_1', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv1_2', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool1', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv2_1', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv2_2', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool2', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv3_1', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_2', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_3', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv4_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv5_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv5_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv5_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
x = tools.batch_norm(x)
x = tools.FC_layer('fc7', x, out_nodes=4096)
x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=n_classes)
return x
def VGG16N(x, n_classes, is_pretrain=True):
with tf.name_scope('VGG16'):
x = tools.conv('conv1_1',
x,
8,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
8,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
x = tools.pool('pool1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
16,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
16,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
x = tools.pool('pool2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
32,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
32,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_3',
x,
32,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv4_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_3',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
x = tools.pool('pool4',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv5_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_3',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
x = tools.pool('pool5',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=512)
x = tf.nn.dropout(x, 0.5)
#with tf.name_scope('batch_norm1'):
#x = tools.batch_norm(x)
x = tools.FC_layer('fc7', x, out_nodes=512)
x = tf.nn.dropout(x, 0.5)
#with tf.name_scope('batch_norm2'):
#x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=512)
x = tf.nn.dropout(x, 0.5)
x = tools.FC_layer('fc9', x, out_nodes=24)
return x
#%%
def create_generator(generator_inputs, generator_outputs_channels):
'''
[<tf.Tensor 'generator/encoder_1/conv/Conv2D:0' shape=(1, 16, 16, 64) dtype=float32>,
<tf.Tensor 'generator/encoder_2/batchnorm/batchnorm/add_1:0' shape=(1, 8, 8, 128) dtype=float32>,
<tf.Tensor 'generator/encoder_3/batchnorm/batchnorm/add_1:0' shape=(1, 4, 4, 256) dtype=float32>,
<tf.Tensor 'generator/encoder_4/batchnorm/batchnorm/add_1:0' shape=(1, 2, 2, 512) dtype=float32>,
<tf.Tensor 'generator/encoder_5/batchnorm/batchnorm/add_1:0' shape=(1, 1, 1, 512) dtype=float32>,
<tf.Tensor 'generator/decoder_5/dropout/mul:0' shape=(1, 2, 2, 512) dtype=float32>,
<tf.Tensor 'generator/decoder_4/batchnorm/batchnorm/add_1:0' shape=(1, 4, 4, 512) dtype=float32>,
<tf.Tensor 'generator/decoder_3/batchnorm/batchnorm/add_1:0' shape=(1, 8, 8, 256) dtype=float32>,
<tf.Tensor 'generator/decoder_2/batchnorm/batchnorm/add_1:0' shape=(1, 16, 16, 64) dtype=float32>,
<tf.Tensor 'generator/decoder_1/Tanh:0' shape=(1, 32, 32, 1) dtype=float32>]
'''
layers = []
ngf = 64
# encoder_1: [batch, 32, 256, in_channels] => [batch, 16, 128, ngf]
with tf.variable_scope("encoder_1"):
output = tools.conv(generator_inputs, ngf, stride=2)
layers.append(output)
layer_specs = [
ngf * 2, # encoder_2: [batch, 16, 128, ngf] => [batch, 8, 64, ngf * 2]
ngf *
4, # encoder_3: [batch, 8, 64, ngf * 2] => [batch, 4, 32, ngf * 4]
ngf *
8, # encoder_4: [batch, 4, 32, ngf * 4] => [batch, 2, 16, ngf * 8]
ngf *
8, # encoder_5: [batch, 2, 16, ngf * 8] => [batch, 1, 8, ngf * 8]
]
for out_channels in layer_specs:
with tf.variable_scope("encoder_%d" % (len(layers) + 1)):
rectified = tools.lrelu(layers[-1], 0.2)
# [batch, in_height, in_width, in_channels] => [batch, in_height/2, in_width/2, out_channels]
convolved = tools.conv(rectified, out_channels, stride=2)
output = tools.batchnorm(convolved)
layers.append(output)
layer_specs = [
(ngf * 8,
0.5), # decoder_5: [batch, 1, 1, ngf * 8] => [batch, 2, 2, ngf * 8 ]
(ngf * 8,
0.0), # decoder_4: [batch, 2, 2, ngf * 8 ] => [batch, 4, 4, ngf * 8 ]
(ngf * 4,
0.0), # decoder_3: [batch, 4, 4, ngf * 8] => [batch, 8, 8, ngf * 4 ]
(ngf,
0.0), # decoder_2: [batch, 8, 8, ngf * 4 ] => [batch, 16, 16, ngf ]
]
num_encoder_layers = len(layers)
for decoder_layer, (out_channels, dropout) in enumerate(layer_specs):
skip_layer = num_encoder_layers - decoder_layer - 1
with tf.variable_scope("decoder_%d" % (skip_layer + 1)):
if decoder_layer == 0:
# first decoder layer doesn't have skip connections
# since it is directly connected to the skip_layer
input = layers[-1]
else:
input = tf.concat([layers[-1], layers[skip_layer]], axis=3)
rectified = tf.nn.relu(input)
# [batch, in_height, in_width, in_channels] => [batch, in_height*2, in_width*2, out_channels]
output = tools.deconv(rectified, out_channels)
output = tools.batchnorm(output)
if dropout > 0.0:
output = tf.nn.dropout(output, keep_prob=1 - dropout)
layers.append(output)
# decoder_1: [batch, 128, 128, ngf * 2] => [batch, 256, 256, generator_outputs_channels]
with tf.variable_scope("decoder_1"):
input = tf.concat([layers[-1], layers[0]], axis=3)
rectified = tf.nn.relu(input)
output = tools.deconv(rectified, generator_outputs_channels)
output = tf.tanh(output)
layers.append(output)
return layers[-1]
def DehazeNet(x):
with tf.variable_scope('DehazeNet'):
x_s = x
# x = tools.conv('DN_conv1_1', x_s, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# x = tools.conv('DN_conv1_2', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# with tf.name_scope('pool1'):
# x = tools.pool('pool1', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
#
# with tf.name_scope('pool2'):
# x = tools.pool('pool2', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
x = tools.conv('upsampling_1',
x_s,
128,
kernel_size=[3, 3],
stride=[1, 2, 2, 1])
x = tools.conv('upsampling_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 2, 2, 1])
x1 = tools.conv('DN_conv2_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv2_2',
x1,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv_nonacti('DN_conv2_3',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tf.add(x, x1)
# x = tools.batch_norm(x)
x = tools.acti_layer(x)
# x = tools.conv('DN_conv2_4', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
x2 = tools.conv('DN_conv3_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv3_2',
x2,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv_nonacti('DN_conv3_3',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tf.add(x, x2)
# x = tools.batch_norm(x)
x = tools.acti_layer(x)
# x = tools.conv('DN_conv3_4', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
x3 = tools.conv('DN_conv4_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv4_2',
x3,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv4_3',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv4_4',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv_nonacti('DN_conv4_5',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tf.add(x, x3)
# x = tools.batch_norm(x)
x = tools.acti_layer(x)
# x = tools.conv('DN_conv4_5', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
x4 = tools.conv('DN_conv5_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv5_2',
x4,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv5_3',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv('DN_conv5_4',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tools.conv_nonacti('DN_conv5_5',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x = tf.add(x, x4)
# x = tools.batch_norm(x)
x = tools.acti_layer(x)
# x5 = tools.conv('DN_conv5_6', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# x = tools.conv('DN_conv5_7', x5, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# x = tools.conv_nonacti('DN_conv5_8', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# x = tf.add(x, x5)
# x = tools.acti_layer(x)
x = tools.deconv('DN_deconv1',
x,
64,
output_shape=[35, 112, 112, 64],
kernel_size=[3, 3],
stride=[1, 2, 2, 1])
x = tools.deconv('DN_deconv2',
x,
64,
output_shape=[35, 224, 224, 64],
kernel_size=[3, 3],
stride=[1, 2, 2, 1])
# x = tools.conv('DN_conv6_1', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# x = tools.conv('DN_conv6_1', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1])
# x = tf.add(x, x_s)
# # # x = tools.batch_norm(x)
# x = tools.acti_layer(x)
x_r = tools.conv_nonacti('DN_conv7_1',
x,
3,
kernel_size=[3, 3],
stride=[1, 1, 1, 1])
x_r = tf.add(x_r, x_s)
x_r = tools.acti_layer(x_r)
return x_r
def VGG16_DP(x, n_classes, is_pretrain=True, flag=0):
with tf.name_scope('VGG16'):
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
x = tools.pool('pool1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
x = tools.pool('pool2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_3',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv4_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
x = tools.pool('pool4',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv5_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
x = tools.pool('pool5',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
with tf.name_scope('dropout1'):
if flag == 0:
dropout1 = tf.nn.dropout(x, 0.5)
else:
dropout1 = tf.nn.dropout(x, 1)
x = tf.nn.relu(dropout1)
x = tools.FC_layer('fc7', x, out_nodes=4096)
with tf.name_scope('dropout2'):
if flag == 0:
dropout2 = tf.nn.dropout(x, 0.5)
else:
dropout2 = tf.nn.dropout(x, 1)
x = tf.nn.relu(dropout2)
x = tools.last_FC('fc8', x, out_nodes=n_classes)
return x
is_pretrain = False
learning_rate = 0.5
MAX_STEP = 5000
train_log_dir = './/logs//train//'
val_log_dir = './/logs//val//'
with tf.Graph().as_default():
with tf.name_scope('inputs'):
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
x_images = tf.reshape(x, [-1, 28, 28, 1])
with tf.name_scope('conv_net'):
outputs = tools.conv('conv1_1',
x_images,
32,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
#outputs = tools.conv('conv1_2', outputs, 32, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
outputs = tools.pool('pool1',
outputs,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
outputs = tools.conv('conv2_1',
outputs,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
def Myvgg(x, n_class, is_pretrain=True):
with tf.name_scope('Myvgg'):
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
x = tools.pool('pool1',
x,
ksize=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
x = tools.pool('pool2',
x,
ksize=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
# x = tools.conv('conv3_3', x, 128, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3',
x,
ksize=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=2048)
with tf.name_scope('batch_norma1'):
x = tools.batch_norm(
x) # batch norm can avoid overfit, more efficient than dropout
x = tools.FC_layer('fc7', x, out_nodes=2048)
#x = tools.dropout(x,0.5)
with tf.name_scope('batch_norm2'):
x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=n_class)
return x
def VGG16(x, n_classes, is_pretrain=True):
x = tools.conv('conv1_1', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv1_2', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool1', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv2_1', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv2_2', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool2', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv3_1', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_2', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_3', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv4_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv5_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv5_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv5_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
#x = tools.batch_norm(x)
x = tools.FC_layer('fc7', x, out_nodes=4096)
#x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=n_classes)
return x
def MyResNet(x, n_class, is_pretrain=True):
with tf.name_scope('MyResNet'):
x1 = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x2 = tools.conv_no_relu('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x3 = tf.add(x1, x2)
x = tf.nn.relu(x3, name='relu')
with tf.name_scope('pool1'):
x = tools.pool('pool1',
x,
ksize=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x1 = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x2 = tools.conv_no_relu('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x3 = tf.add(x1, x2)
x = tf.nn.relu(x3, name='relu')
with tf.name_scope('pool2'):
x = tools.pool('pool2',
x,
ksize=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x1 = tools.conv('conv3_1',
x,
256,
kernel_size=[1, 1],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x2 = tools.conv_no_relu('conv3_2',
x,
256,
kernel_size=[1, 1],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x3 = tf.add(x1, x2)
x = tf.nn.relu(x3, name='relu')
# x = tools.conv('conv3_3', x, 128, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3',
x,
ksize=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=512)
with tf.name_scope('batch_norma1'):
x = tools.batch_norm(
x) # batch norm can avoid overfit, more efficient than dropout
x = tools.FC_layer('fc7', x, out_nodes=512)
#x = tools.dropout(x,0.5)
with tf.name_scope('batch_norm2'):
x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=n_class)
return x
def vgg16(x, CLASS_NUM, _dropout, is_training):
with tf.variable_scope('layer1_1'):
conv1_1 = tools.conv2d(x, [3, 3], 64, 1, is_training, True, True, True)
with tf.variable_scope('layer1_2'):
conv1_2 = tools.conv2d(conv1_1, [3, 3], 64, 1, is_training, True, True,
True)
with tf.variable_scope('pool1'):
pool1 = tf.nn.max_pool(conv1_2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
with tf.variable_scope('layer2_1'):
conv2_1 = tools.conv2d(pool1, [3, 3], 128, 1, is_training, True, True,
True)
with tf.variable_scope('layer2_2'):
conv2_2 = tools.conv2d(conv2_1, [3, 3], 128, 1, is_training, True,
True, True)
with tf.variable_scope('pool2'):
pool2 = tf.nn.max_pool(conv2_2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
with tf.variable_scope('layer3_1'):
conv3_1 = tools.conv2d(pool2, [3, 3], 256, 1, is_training, True, True,
True)
with tf.variable_scope('layer3_2'):
conv3_2 = tools.conv2d(conv3_1, [3, 3], 256, 1, is_training, True,
True, True)
with tf.variable_scope('layer3_3'):
conv3_3 = tools.conv2d(conv3_2, [3, 3], 256, 1, is_training, True,
True, True)
with tf.variable_scope('pool3'):
pool3 = tf.nn.max_pool(conv3_3,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
with tf.variable_scope('layer4_1'):
conv4_1 = tools.conv2d(pool3, [3, 3], 512, 1, is_training, True, True,
True)
with tf.variable_scope('layer4_2'):
conv4_2 = tools.conv2d(conv4_1, [3, 3], 512, 1, is_training, True,
True, True)
with tf.variable_scope('layer4_3'):
conv4_3 = tools.conv2d(conv4_2, [3, 3], 512, 1, is_training, True,
True, True)
with tf.variable_scope('pool4'):
pool4 = tf.nn.max_pool(conv4_3,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
with tf.variable_scope('layer5_1'):
conv5_1 = tools.conv2d(pool4, [3, 3], 512, 1, is_training, True, False,
True)
with tf.variable_scope('layer5_2'):
conv5_2 = tools.conv2d(conv5_1, [3, 3], 512, 1, is_training, True,
False, True)
with tf.variable_scope('layer5_3'):
conv5_3 = tools.conv2d(conv5_2, [3, 3], 512, 1, is_training, True,
False, True)
fmp_3 = conv(conv3_3,
kernel_size=[1, 1],
out_channels=256,
stride=[1, 1, 1, 1],
is_pretrain=_training,
bias=False,
bn=False,
layer_name='conv_3')
fmp_3 = tf.image.resize_bilinear(fmp_3, [56, 56])
fmp_4 = conv(conv4_3,
kernel_size=[1, 1],
out_channels=256,
stride=[1, 1, 1, 1],
is_pretrain=_training,
bias=False,
bn=False,
layer_name='conv_4')
fmp_4 = tf.image.resize_bilinear(fmp_4, [56, 56])
fmp_5 = conv(conv5_3,
kernel_size=[1, 1],
out_channels=256,
stride=[1, 1, 1, 1],
is_pretrain=_training,
bias=False,
bn=False,
layer_name='conv_5')
fmp_5 = tf.image.resize_bilinear(fmp_5, [56, 56])
fmp = tf.concat([fmp_3, fmp_4, fmp_5], -1)
with tf.variable_scope('dilation'):
fmp_dil_1 = dil_conv(fmp,
kernel_size=[3, 3],
out_channels=256,
rate=1,
is_pretrain=_training,
bias=False,
bn=False,
layer_name='dilation1')
fmp_dil_2 = dil_conv(fmp,
kernel_size=[3, 3],
out_channels=256,
rate=2,
is_pretrain=_training,
bias=False,
bn=False,
layer_name='dilation2')
fmp_dil_3 = dil_conv(fmp,
kernel_size=[3, 3],
out_channels=256,
rate=4,
is_pretrain=_training,
bias=False,
bn=False,
layer_name='dilation3')
fmp_dil_4 = dil_conv(fmp,
kernel_size=[3, 3],
out_channels=256,
rate=8,
is_pretrain=_training,
bias=False,
bn=False,
layer_name='dilation4')
fmp_dilation = tf.concat([fmp_dil_1, fmp_dil_2, fmp_dil_3, fmp_dil_4],
-1)
fmp = tools.conv(fmp_dilation,
kernel_size=[1, 1],
out_channels=512,
stride=[1, 1, 1, 1],
is_pretrain=_training,
bias=False,
bn=False,
layer_name='conv_dilation')
gap = tf.reduce_mean(fmp, [1, 2])
with tf.variable_scope('CAM_fc'):
cam_w = tf.get_variable(
'CAM_W',
shape=[512, CLASS_NUM],
initializer=tf.contrib.layers.xavier_initializer(0.0))
output = tf.matmul(gap, cam_w)
annotation_pred = tf.argmax(output, axis=-1)
fmp = tf.image.resize_bilinear(fmp, [224, 224])
return annotation_pred, output, fmp
def VGG19(x, n_classes, is_pretrain=True):
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool1', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1])
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool2', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1])
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_3',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_4',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool3', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1])
x = tools.conv('conv4_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_4',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool4', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1])
x = tools.conv('conv5_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_4',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool5', x, kernel=[1, 2, 2, 1], stride=[1, 2, 2, 1])
x = tools.FC_layer('fc6', x, out_nodes=4096)
x = tf.nn.dropout(x, keep_prob=0.5)
x = tools.FC_layer('fc7', x, out_nodes=4096)
x = tf.nn.dropout(x, keep_prob=0.5)
x = tools.FC_layer('fc8', x, out_nodes=n_classes)
return x
def VGG16PlanInferencet(x, keep_prob, n_classes=12, is_pretrain=True):
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_3',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv4_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv5_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
x = tools.batch_norm(x)
x = tools.FC_layer('fc7', x, out_nodes=4096)
x = tools.batch_norm(x)
x_drop = tf.nn.dropout(x, keep_prob)
x = tools.FC_layer('fc8', x_drop, out_nodes=n_classes)
return x
def VGG16N(x, n_classes, IS_PRETRAIN):
import tools
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[0])
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[1])
x = tools.pool('pool1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[2])
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[3])
x = tools.pool('pool2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[4])
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[5])
x = tools.conv('conv3_3',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[6])
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv4_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[7])
x = tools.conv('conv4_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[8])
x = tools.conv('conv4_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[9])
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv5_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[10])
x = tools.conv('conv5_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[11])
x = tools.conv('conv5_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=IS_PRETRAIN[12])
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096, is_pretrain=IS_PRETRAIN[13])
x = tools.batch_norm(x)
x = tools.FC_layer('fc7', x, out_nodes=4096, is_pretrain=IS_PRETRAIN[14])
x = tools.batch_norm(x)
x = tools.final_layer('fc8', x, out_nodes=n_classes)
return x
def VGG16N(x, n_classes, is_pretrain=True):
with tf.name_scope('VGG16'):
conv1_1 = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv1_2 = tools.conv('conv1_2',
conv1_1,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
pool1 = tools.pool('pool1',
conv1_2,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
conv2_1 = tools.conv('conv2_1',
pool1,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv2_2 = tools.conv('conv2_2',
conv2_1,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
pool2 = tools.pool('pool2',
conv2_2,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
conv3_1 = tools.conv('conv3_1',
pool2,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv3_2 = tools.conv('conv3_2',
conv3_1,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv3_3 = tools.conv('conv3_3',
conv3_2,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
pool3 = tools.pool('pool3',
conv3_3,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
conv4_1 = tools.conv('conv4_1',
pool3,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv4_2 = tools.conv('conv4_2',
conv4_1,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv4_3 = tools.conv('conv4_3',
conv4_2,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
pool4 = tools.pool('pool4',
conv4_3,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
conv5_1 = tools.conv('conv5_1',
pool4,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv5_2 = tools.conv('conv5_2',
conv5_1,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
conv5_3 = tools.conv('conv5_3',
conv5_2,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
pool5 = tools.pool('pool5',
conv5_3,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
fc6 = tools.FC_layer('fc6', pool5, out_nodes=4096)
with tf.name_scope('batch_norm1'):
batch_norm1 = tools.batch_norm(fc6)
fc7 = tools.FC_layer('fc7', batch_norm1, out_nodes=4096)
with tf.name_scope('batch_norm2'):
batch_norm2 = tools.batch_norm(fc7)
fc8 = tools.FC_layer('fc8', batch_norm2, out_nodes=n_classes)
return fc8
def VGG16N(x, n_classes, is_pretrain=True):
with tf.name_scope('VGG16'): #目的：不想显示的节点做成一个大的节点，美化tensorbroad图像
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
x = tools.pool('pool1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
x = tools.pool('pool2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_3',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv4_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
x = tools.pool('pool4',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv5_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
x = tools.pool('pool5',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
#with tf.name_scope('batch_norm1'):
#x = tools.batch_norm(x)
x = tools.FC_layer('fc7', x, out_nodes=4096)
#with tf.name_scope('batch_norm2'):
#x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=n_classes)
return x
def VGG16(x, n_class, is_pretrain=True):
# using the name scope, the tensorboard maybe look better
with tf.name_scope('VGG16'):
x = tools.conv('conv1_1', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
x = tools.conv('conv1_2', x, 64, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
x = tools.pool('pool1', x, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
x = tools.conv('conv2_1', x, 128, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
x = tools.conv('conv2_2', x, 128, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
x = tools.pool('pool2', x, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
x = tools.conv('conv3_1', x, 256, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
x = tools.conv('conv3_2', x, 256, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
x = tools.conv('conv3_3', x, 256, kernel_size=[3, 3], stride=[1, 1, 1, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3', x, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
x = tools.conv('conv4_1', x, 512, kernel_size=[3, 3], stride=[1, 2, 2, 1], is_pretrain=is_pretrain)
x = tools.conv('conv4_2', x, 512, kernel_size=[3, 3], stride=[1, 2, 2, 1], is_pretrain=is_pretrain)
x = tools.conv('conv4_3', x, 512, kernel_size=[3, 3], stride=[1, 2, 2, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
x = tools.pool('pool4', x, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
x = tools.conv('conv5_1', x, 512, kernel_size=[3, 3], stride=[1, 2, 2, 1], is_pretrain=is_pretrain)
x = tools.conv('conv5_2', x, 512, kernel_size=[3, 3], stride=[1, 2, 2, 1], is_pretrain=is_pretrain)
x = tools.conv('conv5_3', x, 512, kernel_size=[3, 3], stride=[1, 2, 2, 1], is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
x = tools.pool('pool5', x, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
with tf.name_scope('batch_norma1'):
x = tools.batch_norm(x) # batch norm can avoid overfit, more efficient than dropout
x = tools.FC_layer('fc7', x, out_nodes=4096)
with tf.name_scope('batch_norm2'):
x = tools.batch_norm(x)
x = tools.FC_layer('fc8', x, out_nodes=n_class)
return x
def VGG16N(x, n_classes, keep_prob,is_pretrain=True):
with tf.name_scope('VGG16'):
x = tools.conv('conv1_1', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv1_2', x, 64, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# with tf.name_scope('batch_norm1'):
# x = tools.batch_norm(x)
with tf.name_scope('pool1'):
x = tools.pool('pool1', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv2_1', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv2_2', x, 128, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# with tf.name_scope('batch_norm2'):
# x = tools.batch_norm(x)
with tf.name_scope('pool2'):
x = tools.pool('pool2', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv3_1', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_2', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv3_3', x, 256, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# with tf.name_scope('batch_norm3'):
# x = tools.batch_norm(x)
with tf.name_scope('pool3'):
x = tools.pool('pool3', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv4_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv4_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# with tf.name_scope('batch_norm4'):
# x = tools.batch_norm(x)
with tf.name_scope('pool4'):
x = tools.pool('pool4', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.conv('conv5_1', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv5_2', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
x = tools.conv('conv5_3', x, 512, kernel_size=[3,3], stride=[1,1,1,1], is_pretrain=is_pretrain)
# with tf.name_scope('batch_norm5'):
# x = tools.batch_norm(x)
with tf.name_scope('pool5'):
x = tools.pool('pool5', x, kernel=[1,2,2,1], stride=[1,2,2,1], is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
# with tf.name_scope('batch_norm6'):
# x = tools.batch_norm(x)
#dropouut
x=tf.nn.dropout(x, keep_prob)
x = tools.FC_layer('fc7', x, out_nodes=4096)
# with tf.name_scope('batch_norm7'):
# x = tools.batch_norm(x)
#dropout
x=tf.nn.dropout(x, keep_prob)
fc_output=x
x = tools.softmax_layer('fc8', x, out_nodes=n_classes)
return x,fc_output
#%%
def VGG16_BN(x, n_classes, is_pretrain=True, is_training=True):
with tf.name_scope('VGG16'):
x = tools.conv('conv1_1',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv1_2',
x,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool1'):
x = tools.pool('pool1',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv2_1',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv2_2',
x,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool2'):
x = tools.pool('pool2',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv3_1',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_2',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv3_3',
x,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool3'):
x = tools.pool('pool3',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv4_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv4_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool4'):
x = tools.pool('pool4',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.conv('conv5_1',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_2',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
x = tools.conv('conv5_3',
x,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=is_pretrain)
with tf.name_scope('pool5'):
x = tools.pool('pool5',
x,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
x = tools.FC_layer('fc6', x, out_nodes=4096)
with tf.name_scope('batch_norm1'):
x = tools.batch_norm_wrapper(
x, is_training=is_training) # 训练时为True，测试为False
x = tools.FC_layer('fc7', x, out_nodes=4096)
with tf.name_scope('batch_norm2'):
x = tools.batch_norm_wrapper(x, is_training=is_training)
x = tools.last_FC('fc8', x, out_nodes=n_classes)
return x
def VGG16(self):
with tf.name_scope('VGG16'):
self.conv1_1 = tools.conv('conv1_1',
self.input,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv1_2 = tools.conv('conv1_2',
self.conv1_1,
64,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool1 = tools.pool('pool1',
self.conv1_2,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.conv2_1 = tools.conv('conv2_1',
self.pool1,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv2_2 = tools.conv('conv2_2',
self.conv2_1,
128,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool2 = tools.pool('pool2',
self.conv2_2,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.conv3_1 = tools.conv('conv3_1',
self.pool2,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv3_2 = tools.conv('conv3_2',
self.conv3_1,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv3_3 = tools.conv('conv3_3',
self.conv3_2,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool3 = tools.pool('pool3',
self.conv3_3,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.conv4_1 = tools.conv('conv4_1',
self.pool3,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv4_2 = tools.conv('conv4_2',
self.conv4_1,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv4_3 = tools.conv('conv4_3',
self.conv4_2,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool4 = tools.pool('pool4',
self.conv4_3,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.conv5_1 = tools.conv('conv5_1',
self.pool4,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv5_2 = tools.conv('conv5_2',
self.conv5_1,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv5_3 = tools.conv('conv5_3',
self.conv5_2,
512,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool5 = tools.pool('pool5',
self.conv5_3,
kernel=[1, 2, 2, 1],
stride=[1, 2, 2, 1],
is_max_pool=True)
self.fc6 = tools.FC_layer('fc6', self.pool5, out_nodes=4096)
self.batch_norm1 = tools.batch_norm('batch_norm1', self.fc6)
self.fc7 = tools.FC_layer('fc7', self.batch_norm1, out_nodes=4096)
self.batch_norm2 = tools.batch_norm('batch_norm2', self.fc7)
self.fc8 = tools.FC_layer('fc8',
self.batch_norm2,
out_nodes=self.n_classes)
def AlexNet(self):
with tf.name_scope('AlexNet'):
self.conv1 = tools.conv('conv1',
self.input,
96,
kernel_size=[11, 11],
stride=[1, 4, 4, 1],
is_pretrain=self.is_pretrain)
self.pool1 = tools.pool('pool1',
self.conv1,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
self.conv2 = tools.conv('conv2',
self.pool1,
256,
kernel_size=[5, 5],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool2 = tools.pool('pool2',
self.conv2,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
self.conv3 = tools.conv('conv3',
self.pool2,
384,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv4 = tools.conv('conv4',
self.conv3,
384,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.conv5 = tools.conv('conv5',
self.conv4,
256,
kernel_size=[3, 3],
stride=[1, 1, 1, 1],
is_pretrain=self.is_pretrain)
self.pool5 = tools.pool('pool5',
self.conv5,
kernel=[1, 3, 3, 1],
stride=[1, 2, 2, 1],
is_max_pool=True,
is_norm=True)
self.fc1 = tools.FC_layer('fc6', self.pool5, out_nodes=4096)
self.norm1 = tools.batch_norm('batch_norm1', self.fc1)
self.fc2 = tools.FC_layer('fc7', self.norm1, out_nodes=4096)
self.norm2 = tools.batch_norm('batch_norm2', self.fc2)
self.fc3 = tools.FC_layer('softmax_linear',
self.norm2,
out_nodes=self.n_classes,
use_relu=False)