def deconv_relu_drop(x, kernalshape, scope=None):
with tf.name_scope(scope):
W = weight_xavier_init(shape=kernalshape,
n_inputs=kernalshape[0] * kernalshape[1] *
kernalshape[-1],
n_outputs=kernalshape[-2],
activefuncation='relu',
variable_name=scope + 'W')
B = bias_variable([kernalshape[-2]], variable_name=scope + 'B')
dconv = tf.nn.relu(deconv2d(x, W) + B)
return dconv
def conv_sigmod(x, kernalshape, scope=None):
with tf.name_scope(scope):
W = weight_xavier_init(shape=kernalshape,
n_inputs=kernalshape[0] * kernalshape[1] *
kernalshape[2],
n_outputs=kernalshape[-1],
activefuncation='sigmoid',
variable_name=scope + 'W')
B = bias_variable([kernalshape[-1]], variable_name=scope + 'B')
conv = conv2d(x, W) + B
conv = tf.nn.sigmoid(conv)
return conv
def down_sampling(x,
kernalshape,
phase,
drop_conv,
height=None,
width=None,
scope=None):
with tf.name_scope(scope):
W = weight_xavier_init(shape=kernalshape,
n_inputs=kernalshape[0] * kernalshape[1] *
kernalshape[2],
n_outputs=kernalshape[-1],
activefuncation='relu',
variable_name=scope + 'W')
B = bias_variable([kernalshape[-1]], variable_name=scope + 'B')
conv = conv2d(x, W, 2) + B
conv = normalizationlayer(conv,
phase,
height=height,
width=width,
norm_type='group',
scope=scope)
conv = tf.nn.dropout(tf.nn.relu(conv), drop_conv)
return conv