Reshape also change the value?

[UrDailyCs]

so from your vidoe explanation you says that view changes the tensor value and thats what differentiate view from reshape. but,as you can see, not only view changes the tensor value but reshape also does change the tensor value. based on this link. it says that reshape also shares memory with the original tensor. so whats the different between the 2?

[nazarPuriy]

In general purposes there are the same. If want independent data add .clone() or multiply by .... = reshape(...)*1
https://stackoverflow.com/questions/49643225/whats-the-difference-between-reshape-and-view-in-pytorch

[mrdbourke]

Hi @UrDailyCs,

@nazarPuriy is correct.

For most purposes they are the same.

However, this is one of the main differences (shared memory):

If you just want to reshape tensors, use torch.reshape. If you're also concerned about memory usage and want to ensure that the two tensors share the same data, use torch.view.

See this answer for more details: https://stackoverflow.com/a/54507446/7900723