Reshaping (view, reshape, squeeze, unsqueeze) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does the view() function do in PyTorch?

view() changes the shape of a tensor without copying data. It returns a new tensor with the same data but a different shape.

intermediate

How is reshape() different from view() in PyTorch?

reshape() also changes tensor shape but can return a copy if needed, while view() requires the tensor to be contiguous and does not copy data.

beginner

What does squeeze() do to a tensor?

squeeze() removes all dimensions of size 1 from a tensor, making it smaller in shape but keeping the same data.

beginner

How does unsqueeze() modify a tensor?

unsqueeze() adds a dimension of size 1 at a specified position, increasing the tensor's number of dimensions.

beginner

Why is reshaping tensors important in machine learning?

Reshaping helps match tensor shapes for operations like matrix multiplication, batching data, or preparing inputs for models.

Which PyTorch function removes dimensions of size 1 from a tensor?

A squeeze()

B unsqueeze()

C reshape()

D view()

squeeze() removes all dimensions with size 1.

What will tensor.view(-1, 3) do?

A Change tensor shape to have 3 columns and infer rows

B Add a new dimension of size 3

C Remove all size 1 dimensions

D Copy tensor data to a new tensor

-1 lets PyTorch infer the size for that dimension, so the tensor reshapes to have 3 columns.

Which function can return a copy of the tensor if needed when reshaping?

A view()

B reshape()

C squeeze()

D unsqueeze()

reshape() may return a copy if the tensor is not contiguous.

What does unsqueeze(0) do to a tensor?

A Removes the first dimension

B Flattens the tensor

C Adds a new dimension at position 0

D Changes tensor data

unsqueeze(0) adds a new dimension of size 1 at the start.

Why must tensor shapes match for matrix multiplication?

A To ensure data types match

B To speed up training

C To reduce memory usage

D To align rows and columns correctly

Matrix multiplication requires matching inner dimensions to align rows and columns properly.

Explain how view() and reshape() differ when changing tensor shapes in PyTorch.

Think about memory layout and copying.

Describe a real-life example where you might use squeeze() and unsqueeze() when working with image data.

Consider how images are stored and fed into models.