Tensor reshaping

As explained in Grokking Machine Learning

An array operation that changes the dimensions of stored values without changing their underlying elements.

Reshaping changes an array’s dimensions without changing its stored values. For neural-network input, a 28-by-28 MNIST image can be reshaped into a vector of 784 values by joining its rows. section 10.3

Flattening MNIST images

Use NumPy’s `reshape(-1, 28*28)` on the training and test images to turn each image into a 784-value vector. section 10.3

Figure 10.24 Before training the neural network, we preprocess the images and the labels in the following way. We shape the rectangular image into a long vector by concatenating the rows. We then convert each label into a vector of length 10 with only one non-zero entry in the position of the corresponding label.

Shows image rows concatenated into a long vector before neural-network training. section 10.3

How Grokking Machine Learning covers it

How deep it goes

Demonstrates flattening 28-by-28 images into 784-value vectors, without discussing reshaping internals.

Examples

Flattens MNIST images from 28-by-28 matrices into vectors of length 784.

What you can do after

Apply NumPy’s reshape function to convert MNIST image matrices into neural-network input vectors.

How it connects

Connects NumPy arrays and neural networks through MNIST image preprocessing.

liveBookmanning.com

Read Grokking Machine Learning on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsAn operation that changes a tensor's shape without changing its total number of values, used here to turn a network output into an image-shaped tensor.
• 

  liveBookmanning.com
  Grokking StatisticsA NumPy array operation that changes an array’s dimensions without changing its element values.

Compare how 3 books explain tensor reshaping →

Related concepts

• transpositionincludes · Transposition is an operation that exchanges a matrix’s rows and columns or, more generally, reorders the axes of a tensor without changing its values.
• tensoruses · A tensor is a multidimensional, array-like structure of values indexed along zero or more dimensions and used for numerical computation.
• viewequivalent to · A view is an alternate representation or access interface for data derived from or backed by underlying storage without necessarily creating an independent copy.
• vectorproduces · A vector is an ordered, indexed sequence of elements, often numerical, represented as a mathematical quantity or a computational collection.
• grayscale imageproduces · A grayscale image represents each pixel with a single achromatic intensity value rather than separate color components.

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning. The section links point to the parts of the book it draws on.