nbatch>1的多变量非线性分布

Question

我试图将How to use a MultiVariateNormal distribution in the latest version of Tensorflow中给出的例子推广到二维正态分布，但有多个批次。当我运行以下命令时：

from tensorflow_probability import distributions as tfd
import tensorflow as tf

tf.compat.v1.enable_eager_execution()

mu = [[1, 2],
        [-1,-2]]

cov = [[1, 3./5],
        [3./5, 2]]

cov = [cov, cov] # for demonstration purpose, use same cov for both batches

mvn = tfd.MultivariateNormalFullCovariance(
        loc=mu,
        covariance_matrix=cov)

# generate the pdf
X, Y = tf.meshgrid(tf.range(-3, 3, 0.1), tf.range(-3, 3, 0.1))
idx = tf.concat([tf.reshape(X, [-1, 1]), tf.reshape(Y,[-1,1])], axis =1)
prob = tf.reshape(mvn.prob(idx), tf.shape(X))

我得到一个不兼容的形状错误：

tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [3600,2] vs. [2,2] [Op:Sub] name: MultivariateNormalFullCovariance/log_prob/affine_linear_operator/inverse/sub/

我对文档（https://www.tensorflow.org/api_docs/python/tf/contrib/distributions/MultivariateNormalFullCovariance）的理解是，要计算pdf，需要一个[n\u观测，n\u维]张量（这个例子就是这样：idx.shape=TensorShape([Dimension(3600), Dimension(2)])）。我的数学错了吗？你知道吗

Answer 1

您需要在倒数第二个位置向idx张量添加一个批处理轴，因为60x60不能针对(2,)的mvn.batch_shape进行广播。你知道吗

# TF/TFP Imports
!pip install  quiet tfp-nightly tf-nightly
import tensorflow.compat.v2 as tf
tf.enable_v2_behavior()
import tensorflow_probability as tfp
tfd = tfp.distributions

mu = [[1, 2],
      [-1, -2]]

cov = [[1, 3./5],
       [3./5, 2]]

cov = [cov, cov] # for demonstration purpose, use same cov for both batches

mvn = tfd.MultivariateNormalFullCovariance(
    loc=mu, covariance_matrix=cov)
print(mvn.batch_shape, mvn.event_shape)

# generate the pdf
X, Y = tf.meshgrid(tf.range(-3, 3, 0.1), tf.range(-3, 3, 0.1))
print(X.shape)
idx = tf.stack([X, Y], axis=-1)[..., tf.newaxis, :]
print(idx.shape)

probs = mvn.prob(idx)
print(probs.shape)

输出：

(2,) (2,)   # mvn.batch_shape, mvn.event_shape
(60, 60)    # X.shape
(60, 60, 1, 2)   # idx.shape == X.shape + (1 "broadcast against batch", 2 "event")
(60, 60, 2)  # probs.shape == X.shape + (2 "mvn batch shape")