Easy Framework

Stack Tensors

Stacking gives each input vector its own row. It adds an axis that identifies which vector a value came from.

Your task

Implement stack_tensors(tensors).

tensors is a nonempty list of one-dimensional tensors, each of shape (n,).
All inputs have the same length, dtype and device.
Return shape (len(tensors), n), preserving the dtype, device and list order. Leave the input tensors unchanged.

For vectors [1, 2, 3] and [4, 5, 6], return [[1, 2, 3], [4, 5, 6]], with shape (2, 3). Each input becomes a row: output[i, j] = tensors[i][j].

Even a list containing just one vector produces a matrix. For [5, 6], the result has shape (1, 2) and values [[5, 6]], not shape (2,).

Use torch.stack(tensors, dim=0) or jnp.stack(tensors, axis=0). Concatenating these vectors would join their values into one longer vector; stacking keeps them separate along a new first axis.

Understand the ideas behind this exercise. The Problem tab contains the exact implementation requirements.

Give each tensor axis a meaning

A tensor's shape tells you how many entries each axis has. It does not tell you what those entries represent. For example, (batch, features) and (features, batch) use different axis orders. Name the axes before choosing an operation.

A reduction combines entries along an axis, for example by summing or averaging. Averaging the features of a (B, D) tensor gives one number per example, with shape (B,). Keeping the reduced axis gives shape (B, 1) instead.

For [[2, 4, 6], [1, 3, 5]], the row means with the axis kept are [[4], [3]]. Subtracting them from the input gives [[-2, 0, 2], [-2, 0, 2]]: each row has been centered using its own mean.

Reshape and transpose do different jobs

A reshape regroups elements using the operation's traversal order. A transpose changes the axis order. For the usual row-major reshape, [[1, 2, 3], [4, 5, 6]] reshaped to (3, 2) becomes [[1, 2], [3, 4], [5, 6]]. Transposing the original instead gives [[1, 4], [2, 5], [3, 6]].

Both results have shape (3, 2), but their entries mean different things. Check values as well as shapes. Unequal axis sizes make many axis mistakes easier to spot than square examples do.

Concatenate along an axis or stack on a new one

Concatenation extends an existing axis. Stacking creates a new axis. For two arrays of shape (2, 3), concatenating on axis zero gives (4, 3). Stacking on a new leading axis gives (2, 2, 3).

Detecting runtime…

Stack Tensors

Your task

Give each tensor axis a meaning

Reshape and transpose do different jobs

Concatenate along an axis or stack on a new one

Your code, saved here

Stuck?

PyTorch reference solution