How deeply does Graph Neural Networks in Action cover floating-point operation count?

Defines the metric and demonstrates model profiling, but does not derive operation counts internally.

Floating-point operation count

As explained in Graph Neural Networks in Action

A floating-point operation is a numerical operation on floating-point values, with FLOPs denoting the count required by a computation.

Floating-point operation count, commonly written as FLOPs, measures the numerical operations required by a computation. It serves as a scalability metric alongside memory usage, time per epoch, and convergence speed. section 7.2.3

Profiling a model

Use THOP to profile a PyTorch model with a representative input, then inspect the reported operation count alongside other resource measurements. section 7.2.3

from thop import profile   #1

input = torch.randn(1, 3, 224, 224) 
macs, params = profile(model, inputs=(input, )) 
print(f"FLOPs: {macs}")

A compact THOP example creates an input tensor, profiles the model, and prints the returned operation count. section 7.2.3

How Graph Neural Networks in Action covers it

Cover of Graph Neural Networks in Action

liveBook manning.com

Read Graph Neural Networks in Action on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Introduction to Generative AI, Second EditionFLOPs are floating-point operations used to quantify computational work performed by a system or model.

Compare how 2 books explain floating-point operation count →

Related concepts

language modelmeasures · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
pretrainingconfigures · Pretraining is the initial training of a model on broad data to learn general patterns or capabilities before adaptation to specific tasks or domains.
floating-point arithmeticmeasures · Floating-point arithmetic is computation using finite-precision representations of real numbers, which can introduce rounding and range errors.

This explainer was generated by Manning's knowledge graph from the text of Graph Neural Networks in Action. The section links point to the parts of the book it draws on.