def deconv2d(x, num_filters, filter_size=[3, 3], stride=[1, 1], pad='SAME', nonlinearity=None, init_scale=1., counters={}, init=False, ema=None, **kwargs):
''' transposed convolutional layer '''
name = get_name('deconv2d', counters)
xs = int_shape(x)
if pad == 'SAME':
target_shape = [xs[0], xs[1] * stride[0],
xs[2] * stride[1], num_filters]
else:
target_shape = [xs[0], xs[1] * stride[0] + filter_size[0] -
1, xs[2] * stride[1] + filter_size[1] - 1, num_filters]
with tf.variable_scope(name):
if init:
# data based initialization of parameters
V = tf.get_variable('V', filter_size + [num_filters, int(x.get_shape(
)[-1])], tf.float32, tf.random_normal_initializer(0, 0.05), trainable=True)
V_norm = tf.nn.l2_normalize(V.initialized_value(), [0, 1, 3])
x_init = tf.nn.conv2d_transpose(x, V_norm, target_shape, [
1] + stride + [1], padding=pad)
m_init, v_init = tf.nn.moments(x_init, [0, 1, 2])
scale_init = init_scale / tf.sqrt(v_init + 1e-8)
g = tf.get_variable('g', dtype=tf.float32,
initializer=scale_init, trainable=True)
b = tf.get_variable('b', dtype=tf.float32,
initializer=-m_init * scale_init, trainable=True)
x_init = tf.reshape(scale_init, [
1, 1, 1, num_filters]) * (x_init - tf.reshape(m_init, [1, 1, 1, num_filters]))
if nonlinearity is not None:
x_init = nonlinearity(x_init)
return x_init
else:
V, g, b = get_vars_maybe_avg(['V', 'g', 'b'], ema)
tf.assert_variables_initialized([V, g, b])
# use weight normalization (Salimans & Kingma, 2016)
W = tf.reshape(g, [1, 1, num_filters, 1]) * \
tf.nn.l2_normalize(V, [0, 1, 3])
# calculate convolutional layer output
x = tf.nn.conv2d_transpose(
x, W, target_shape, [1] + stride + [1], padding=pad)
x = tf.nn.bias_add(x, b)
# apply nonlinearity
if nonlinearity is not None:
x = nonlinearity(x)
return x
评论列表
文章目录
