A Comparison of Neural Network Frameworks
The standard approach to programming neural networks is to use a neural network programming framework. Neural network frameworks are specifically designed to make implementing neural networks easy, and development fast. However, those beginning their journey in programming neural networks may be unfamiliar with the available frameworks, and the advantages of each. In this talk two solutions to the standard CIFAR-10 problem are presented, using two commonly-used neural network frameworks: PyTorch Lightning and Keras/Tensorflow. We compare the two frameworks for ease of implementation, performance, and training speed. The advantages and disadvantages of the two frameworks are discussed. Familiarity with neural network and Python programming is assumed.
-------
This webinar was presented by Erik Spence (SciNet) on January 18th, 2023, as a part of a series of weekly Compute Ontario Colloquia. The webinar was hosted by SciNet. The colloquia cover different advanced research computing (ARC) and high performance computing (HPC) topics, are 45 to 60 minutes in length, and are delivered by experts in the relevant fields. Further details can be found on this web page: https://www.computeontario.ca/trainin... .