tensorflow逐元素矩阵乘法 [英] tensorflow element-wise matrix multiplication
问题描述
说我在张量流中有两个张量,第一个维代表一批训练实例的索引,其他维代表数据矩阵的一些向量.例如
Say I have two tensors in tensorflow, with the first dimension representing the index of a training example in a batch, and the others representing some vectors of matrices of data. Eg
vector_batch = tf.ones([64, 50])
matrix_batch = tf.ones([64, 50, 50])
我很好奇执行向量*矩阵的最惯用方式是,对于向量的每对向量,矩阵沿第一个维度共享一个索引.
I'm curious what the most idiomatic way to perform a vector*matrix multiply, for each of the pairs of vectors, matrices that share an index along the first dimension.
又是最惯用的书写方式:
Aka a the most idiomatic way to write:
result = tf.empty([64,50])
for i in range(64):
result[i,:] = tf.matmul(vector_batch[i,:], matrix_batch[i,:,:])
组织输入矢量形状以使此过程尽可能简单/干净的最佳方法是什么?
What would be the best way to organize the shape of the input vectors to make this process as simple/clean as possible?
推荐答案
可能最惯用的方法是使用 tf.expand_dims()
和
Probably the most idiomatic way to do this is using tf.batch_matmul()
operator (in conjunction with tf.expand_dims()
and tf.squeeze()
:
vector_batch = tf.placeholder(tf.float32, shape=[64, 50])
matrix_batch = tf.placeholder(tf.float32, shape=[64, 50, 50])
vector_batch_as_matrices = tf.expand_dims(vector_batch, 1)
# vector_batch_as_matrices.get_shape() ==> [64, 1, 50]
result = tf.batch_matmul(vector_batch_as_matrices, matrix_batch)
# result.get_shape() ==> [64, 1, 50]
result = tf.squeeze(result, [1])
# result.get_shape() ==> [64, 50]
这篇关于tensorflow逐元素矩阵乘法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!