Tensor shape

Q: How deeply does Inside Deep Learning: Math, Algorithms, Models cover tensor shape?

Defines shape notation and implements reshaping through output-size multiplication and View, without developing convolutional layouts.

As explained in Inside Deep Learning: Math, Algorithms, Models

The dimensions of a tensor, used to describe its layout and reshaping operations.

A tensor shape records the dimensions of data and determines how a network output is laid out. In a GAN, out_shape specifies the generator output and discriminator input shape. section 9.1.3

The shape (-1, 28, 28) keeps the batch dimension flexible while arranging each generated MNIST example as a 28-by-28 image. The final linear layer produces abs(np.prod(out_shape)) values, then View(out_shape) reshapes them. section 9.1.3

Reshaping a GAN output

Set out_shape = (-1, 28, 28), pass it to simpleGAN, and obtain G(z) in image-shaped batches rather than flat vectors.

How Inside Deep Learning: Math, Algorithms, Models covers it

Cover of Inside Deep Learning: Math, Algorithms, Models

liveBook manning.com

Read Inside Deep Learning: Math, Algorithms, Models on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Fast Python: High performance techniques for large datasets
liveBook manning.com

Deep Learning with PyTorch, Second EditionThe sizes of an array or tensor along each axis, here specifically the channels-height-width layout for image tensors.
liveBook manning.com

Deep Learning with R, Third EditionAn output shape is the ordered set of dimension sizes describing the tensor produced by a layer.
liveBook manning.com

Learn Generative AI with PyTorchThe tuple of dimension sizes describing the structure of a multidimensional object.

Compare how 5 books explain tensor shape →

Related concepts

stridecontrasts with · A stride is the step interval between successive positions or elements accessed, selected, or processed along a dimension or sequence.
circleincludes · Circle is a book-defined Python class whose instances represent circles with a radius data attribute and operations for changing or retrieving that radius.
broadcastingused by · Broadcasting is the distribution or implicit replication of data from one source across multiple recipients or compatible positions for communication or computation.
collision detectionused by · Collision detection is the computation of whether modeled objects or entities intersect, touch, overlap, or occupy conflicting spatial regions.
tensoruses · A tensor is a multidimensional array-like numerical data structure whose elements are indexed along zero or more dimensions and support numerical computation.

This explainer was generated by Manning's knowledge graph from the text of Inside Deep Learning: Math, Algorithms, Models. The section links point to the parts of the book it draws on.