def vgg_net(weights, image):
layers = ('conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1',
'relu2_1', 'conv2_2', 'relu2_2', 'pool2', 'conv3_1', 'relu3_1',
'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'conv3_4', 'relu3_4',
'pool3', 'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
'relu4_3', 'conv4_4', 'relu4_4', 'pool4', 'conv5_1', 'relu5_1',
'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3', 'conv5_4', 'relu5_4')
net = {}
current = image
for i, name in enumerate(layers):
kind = name[:4]
if kind == 'conv':
# 加载vgg卷积各参数
kernels, bias = weights[i][0][0][0][0]
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)),
name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
# 计算卷积
conv = tf.nn.conv2d(current,
kernels,
strides=[1, 1, 1, 1],
padding="SAME")
current = tf.nn.bias_add(conv, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
elif kind == 'pool':
current = tf.nn.avg_pool(current,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
net[name] = current
return net
def get_output_step(self, cell_output):
with tf.variable_scope('mean', reuse=tf.AUTO_REUSE):
mean_net = DenseNet(input_=cell_output,
hidden_dim=-1,
output_dim=self.output_dim,
num_layers=1,
transfer_fct=None,
act_out=self.act_out_mean,
reuse=tf.AUTO_REUSE,
kinit=self.kinit,
bias_init=self.bias_init)
mean = mean_net.output
with tf.variable_scope('var', reuse=tf.AUTO_REUSE):
if (self.var_shared):
var = utils.get_variable(self.output_dim, 'var')
var = tf.tile(var, [self.batch_size, 1]) # [batch_size, var.dim]
else:
var_net = DenseNet(input_=cell_output,
hidden_dim=-1,
output_dim=self.output_dim,
num_layers=1,
transfer_fct=None,
act_out=self.act_out_var,
reuse=tf.AUTO_REUSE,
kinit=self.kinit,
bias_init=self.bias_init)
var = var_net.output
eps = tf.random_normal((self.batch_size, self.output_dim), 0, 1, dtype=tf.float32)
current_z = tf.add(mean, tf.multiply(tf.sqrt(var), eps))
return mean, var, current_z