Review Tensor

A tensor is a structured collection of numbers arranged across one or more dimensions, commonly used to represent model inputs, weights, or outputs.

A tensor is an array of values arranged along one or more dimensions. Machine-learning systems use tensors to represent inputs, model parameters, and intermediate calculations.

Tensor shape and data type determine which operations are possible and how much memory and computation they require. Many model errors are really mismatches in shape, type, or device.

A batch of 32 color images that are 224 pixels high and wide can be represented as a four-dimensional tensor with shape 32 by 3 by 224 by 224.

A tensor in machine-learning software is often a multidimensional array; it is not automatically the same mathematical object used in every branch of physics or geometry.

A tensor is numbers arranged by dimensions.

* [[parameters|Parameters]] * [[weights|Weights]] * [[compute|Compute]] * [[batch|Batch]]

* [PyTorch, “Tensors”](https://docs.pytorch.org/docs/stable/tensors.html) — documents tensors as multidimensional arrays used for data and computation in PyTorch.

* Compare [[parameters|Parameters]], [[weights|Weights]], [[compute|Compute]], and [[batch|Batch]] to place Tensor in the surrounding system. * Follow the cited source material above for the method, standard, or research context behind this draft.