Easy Framework

Create a Tensor from a List

Convert a table of numbers into a float32 tensor without changing its row or column order.

Your task

Implement create_tensor(data). The input is a nonempty Python list of rows, where each row is a nonempty list of numbers. All rows have the same length. Return a two-dimensional float32 tensor with one tensor row per input row. Leave the input list unchanged.

For data=[[1, 2, 3], [4, 5, 6]], return shape (2, 3) and values [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]. The outer list determines the number of rows; each inner list determines the columns.

Keep both dimensions even when one has size 1: [[5, 6]] gives (1, 2), while [[5], [6]] gives (2, 1).

Use torch.tensor(data, dtype=torch.float32) or jnp.array(data, dtype=jnp.float32). Specify the dtype explicitly so integer inputs also produce floating-point output. Values are represented at float32 precision, so fractions such as 0.1 may be rounded.

Return the tensor itself, not the input list or a dictionary of shape and values.

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…

Create a Tensor from a List

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