使用占位符从 MultivariateNormalDiag 采样答案

【问题标题】：sampling from MultivariateNormalDiag with placeholders使用占位符从 MultivariateNormalDiag 采样
【发布时间】：2020-02-08 00:59:20
【问题描述】：

我正在运行 tensorflow 2.1 和 tensorflow_probability 0.9。我想用占位符参数化多元正态分布并从中采样。这是我尝试过的方法

import tensorflow as tf
import tensorflow_probability as tfp

@tf.function()
def sample_vae(dist):
    return dist.sample()

vae_mu = tf.keras.layers.Input(shape=(5), dtype=tf.float16)
vae_logvar = tf.keras.layers.Input(shape=(5), dtype=tf.float16)
dist = tfp.distributions.MultivariateNormalDiag(loc=vae_mu, scale_diag=tf.exp(vae_logvar))
z = sample_vae(dist)

上面给了我以下错误

TypeError                                 Traceback (most recent call last)

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     60                                                op_name, inputs, attrs,
---> 61                                                num_outputs)
     62   except core._NotOkStatusException as e:

TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
  @tf.function
  def has_init_scope():
    my_constant = tf.constant(1.)
    with tf.init_scope():
      added = my_constant * 2
The graph tensor has name: BroadcastArgs_3:0


During handling of the above exception, another exception occurred:

_SymbolicException                        Traceback (most recent call last)

6 frames

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     73       raise core._SymbolicException(
     74           "Inputs to eager execution function cannot be Keras symbolic "
---> 75           "tensors, but found {}".format(keras_symbolic_tensors))
     76     raise e
     77   # pylint: enable=protected-access

_SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'BroadcastArgs_3:0' shape=(1,) dtype=int32>, <tf.Tensor 'Exp_3:0' shape=(None, 5) dtype=float16>, <tf.Tensor 'input_7:0' shape=(None, 5) dtype=float16>]

【问题讨论】：

标签： tensorflow2.0 tensorflow-probability

【解决方案1】：

我可以使用 DistributionLambda 解决这个问题

vae_mu = tf.keras.layers.Input(shape=(1, 5), dtype=tf.float16)
vae_logvar = tf.keras.layers.Input(shape=(1, 5), dtype=tf.float16)
mu_logvar = tf.concat([vae_mu, vae_logvar], axis=1)
l = vae_mu.shape[1]
dist = tfp.layers.DistributionLambda(lambda theta: tfp.distributions.MultivariateNormalDiag(loc=theta[:, :l], scale_diag=theta[:, l:]))
z = dist(mu_logvar)

【讨论】：