Hi All, With the current Reshape operator in MXNet, it is not possible to reshape an input array when the shape is generated at runtime. I have created a github issue describing the problem with examples - https://github.com/apache/incubator-mxnet/issues/10789
Briefly stated, MXNet should support the usecase where both the input array and the shape tuple are fed to the "reshape" operator as input arguments. The proposed solution is to modify the existing reshape_like operator to accept another boolean parameter called infer_shape. And based on this parameter we can either infer the shape of second input( as it is done now) or take the second input as the shape array itself. Please let me know your comments and feedback. Regards Anirudh Acharya