TensorFlow Batch 外积 [英] TensorFlow Batch Outer Product

问题描述

我有以下两个张量:

x, with shape [U, N]
y, with shape [N, V]

我想执行批量外积:我想将 x 第一列中的每个元素乘以 y 第一行中的每个元素得到形状为 [U, V] 的张量，然后是 x 的第二列和 y 的第二行，依此类推.最终张量的形状应该是 [N, U, V]，其中 N 是批量大小.

I want to perform a batch outer product: I'd like to multiply each element in the first column of x by each element in the first row of y to get a tensor of shape [U, V], then the second column of x by the second row of y, and so on. The shape of the final tensor should be [N, U, V], where N is the batch size.

有什么简单的方法可以在 TensorFlow 中实现这一点?我尝试使用 batch_matmul() 没有成功.

Is there any simple way to achieve this in TensorFlow? I've tried to use batch_matmul() without success.

推荐答案

使用 tf.batch_matmul()?

print x.get_shape()  # ==> [U, N]
print y.get_shape()  # ==> [N, V]

x_transposed = tf.transpose(x)
print x_transposed.get_shape()  # ==> [N, U]

x_transposed_as_matrix_batch = tf.expand_dims(x_transposed, 2)
print x_transposed_as_matrix_batch.get_shape()  # ==> [N, U, 1]

y_as_matrix_batch = tf.expand_dims(y, 1)
print y_as_matrix_batch.get_shape()  # ==> [N, 1, V]

result = tf.batch_matmul(x_transposed_as_matrix_batch, y_as_matrix_batch)
print result.get_shape()  # ==> [N, U, V]

这篇关于TensorFlow Batch 外积的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！