Reshape Backward Layer

The forward reshape layer generates a tensor from input argument X of size n 1 x n 2 x ... x n p with modified size of dimensions m 1 x m 2 x ... x m q without modifying data and its order. For more details, see Forward Reshape Layer. The backward reshape layer generates output tensor Z of size n 1 x n 2 x ... x n p from input tensor G of dimensions m 1 x m 2 x ... x m q .

Problem Statement

Given the dimension sizes of the output tensor n 1 x n 2 x ... x n p , such that



The p-dimensional result tensor Z of size n 1 x n 2 x ... x n p contains the same data from G in unmodified order.

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)