cntk - CNTK - reshape an axis to matrix

Question

Given a Tensor whose shape is known only at the compute time, how to convert a Tensor of shape, for e.g., (n1, n2, m*n) to (n1, n2, m, n) assuming there is a prior condition that, the last dimension is strictly a multiple of n.

标签： cntk

Answer 1

因为，我们拥有的唯一信息是最后一个维度是 n 的倍数，所以下面的代码行就可以解决问题。这里，x 是一个张量变量，其形状是在网络编译时计算的。

x = C.reshape(x, x.shape[:-1] + (-1, n))