def encode(self, inputs, labels, condition=None):
## Dequantization by adding uniform noise
with tf.variable_scope("preprocess"):
self.y = tf.one_hot(labels,
depth=self.num_classes,
dtype=tf.float32)
inputs = tf.cast(inputs, 'float32')
self.height, self.width, self.channels = inputs.get_shape(
).as_list()[1:]
if self.hps.num_bits_x < 8:
inputs = tf.floor(inputs / 2**(8 - self.hps.num_bits_x))
inputs = inputs / self.num_bins - 0.5
inputs = inputs + tf.random_uniform(tf.shape(inputs), 0,
1. / self.num_bins)
objective = tf.zeros(tf.shape(inputs)[0])
objective += -np.log(self.num_bins) * np.prod(
ops.shape(inputs)[1:])
inputs = squeeze2d(inputs)
## Encoder
if self.hps.conditioning and condition is None:
condition = self.y
# with tf.variable_scope("cond_preprocess"):
# condition = tf.layers.dense(condition, units=10, use_bias=False)
z, objective, eps = codec(inputs,
cond=condition,
objective=objective,
hps=self.hps,
reverse=False)
## Prior
with tf.variable_scope("prior"):
self.hps.top_shape = z.get_shape().as_list()[1:]
logp, sample, get_eps = prior(self.y, self.hps)
obj = logp(z)
eps.append(get_eps(z))
objective += obj
self.objective = -objective
# Class label predict with latent representation
if self.hps.ycond:
z_y = tf.reduce_mean(z, axis=[1, 2])
self.logits = linear_zeros(z_y,
self.num_classes,
name="classifier")
return eps
def prior(y_onehot, hps, name=None):
n_z = hps.top_shape[-1]
h = tf.zeros([tf.shape(y_onehot)[0]]+hps.top_shape[:2]+[2*n_z])
h = conv2d_zeros(h, 2*n_z, name="p")
if hps.ycond:
h += tf.reshape(linear_zeros(y_onehot, 2*n_z, name="y_emb"), [-1, 1, 1, 2 * n_z])
mean, logsd = tf.split(h, 2, axis=-1)
rescale = tf.get_variable("rescale", [], initializer=tf.constant_initializer(1.))
scale_shift = tf.get_variable("scale_shift", [], initializer=tf.constant_initializer(0.))
logsd = tf.tanh(logsd) * rescale + scale_shift
pz = gaussian_diag(mean, logsd)
logp = lambda z1: pz.logp(z1)
eps = lambda z1: pz.get_eps(z1)
sample = lambda eps: pz.sample(eps)
return logp, sample, eps
def prior(y_onehot, hps, name=None):
n_z = hps.top_shape[-1]
h = tf.zeros([tf.shape(y_onehot)[0]] + hps.top_shape[:2] + [2 * n_z])
h = conv2d_zeros(h, 2 * n_z, name="p")
if hps.ycond:
h += tf.reshape(linear_zeros(y_onehot, 2 * n_z, name="y_emb"),
[-1, 1, 1, 2 * n_z])
mean, logsd = tf.split(h, 2, axis=-1)
rescale = tf.get_variable("rescale", [],
initializer=tf.constant_initializer(1.))
scale_shift = tf.get_variable("scale_shift", [],
initializer=tf.constant_initializer(0.))
logsd = tf.tanh(logsd) * rescale + scale_shift
pz = gaussian_diag(mean, logsd)
logp = lambda z1: pz.logp(z1)
eps = lambda z1: pz.get_eps(z1)
sample = lambda eps: pz.sample(eps)
return logp, sample, eps
def encode(self, inputs, labels, condition=None):
## Dequantization by adding uniform noise
with tf.variable_scope("preprocess"):
self.y = tf.one_hot(labels, depth=self.num_classes, dtype=tf.float32)
inputs = tf.cast(inputs, 'float32')
self.height, self.width, self.channels = inputs.get_shape().as_list()[1:]
if self.hps.num_bits_x < 8:
inputs = tf.floor(inputs/2**(8-self.hps.num_bits_x))
inputs = inputs / self.num_bins - 0.5
inputs = inputs + tf.random_uniform(tf.shape(inputs), 0, 1./self.num_bins)
objective = tf.zeros(tf.shape(inputs)[0])
objective += -np.log(self.num_bins) * np.prod(ops.shape(inputs)[1:])
inputs = squeeze2d(inputs)
## Encoder
if self.hps.conditioning and condition is None:
condition = self.y
# with tf.variable_scope("cond_preprocess"):
# condition = tf.layers.dense(condition, units=10, use_bias=False)
z, objective, eps = codec(inputs, cond=condition, objective=objective, hps=self.hps, reverse=False)
## Prior
with tf.variable_scope("prior"):
self.hps.top_shape = z.get_shape().as_list()[1:]
logp, sample, get_eps = prior(self.y, self.hps)
obj = logp(z)
eps.append(get_eps(z))
objective += obj
self.objective = -objective
# Class label predict with latent representation
if self.hps.ycond:
z_y = tf.reduce_mean(z, axis=[1, 2])
self.logits = linear_zeros(z_y, self.num_classes, name="classifier")
return eps
def encode(self, inputs, labels, condition=None):
# line268
# Dequantization by adding uniform noise 加入均匀噪声来反量化
with tf.variable_scope("preprocess"):
# 采用One-hot编码
self.y = tf.one_hot(labels,
depth=self.num_classes,
dtype=tf.float32)
inputs = tf.cast(inputs, 'float32')
# tf.cast()数据类型转换
self.height, self.width, self.channels = inputs.get_shape(
).as_list()[1:]
# num_bits、num_bin：？？？
if self.hps.num_bits_x < 8:
inputs = tf.floor(inputs / 2**(8 - self.hps.num_bits_x))
inputs = inputs / self.num_bins - 0.5
# 输入加入随机正态分布
inputs = inputs + tf.random_uniform(tf.shape(inputs), 0,
1. / self.num_bins)
# objective：？？？
objective = tf.zeros(tf.shape(inputs)[0])
# np.prod：计算数组中所有元素的乘积
objective += -np.log(self.num_bins) * np.prod(
ops.shape(inputs)[1:])
# 使用Squeezing操作（在进入Squeezing之前的操作未知）
print("before inter squeeze2d, input.shape=" + inputs.shape())
inputs = squeeze2d(inputs)
# inputs的shape为[图片数, 高度, 宽度, 通道数]
# Encoder 编码
# 下面作用未知
if self.hps.conditioning and condition is None:
condition = self.y
# with tf.variable_scope("cond_preprocess"):
# condition = tf.layers.dense(condition, units=10, use_bias=False)
print("before inter model.codec, inputs.shape=" + inputs.shape())
z, objective, eps = codec(inputs,
cond=condition,
objective=objective,
hps=self.hps,
reverse=False)
# line 11
# Prior 先验
with tf.variable_scope("prior"):
self.hps.top_shape = z.get_shape().as_list()[1:]
logp, sample, get_eps = prior(self.y, self.hps)
obj = logp(z)
eps.append(get_eps(z))
objective += obj
self.objective = -objective
# Class label predict with latent representation：潜变量标签预测
if self.hps.ycond:
z_y = tf.reduce_mean(z, axis=[1, 2])
self.logits = linear_zeros(z_y,
self.num_classes,
name="classifier")
return eps