From the course: Deep Learning: Model Optimization and Tuning
Join today to access over 24,700 courses taught by industry experts.
Epoch and batch size experiment
From the course: Deep Learning: Model Optimization and Tuning
Epoch and batch size experiment
- [Narrator] Let's run some experiments now. The code for this chapter is available in the notebook code-02-XX, Tuning the Deep Learning Network. We first import the common experiments functions into this notebook. Please be aware that if you change the common experiments function notebook, you will have to save that notebook and import it again. The Epoch and Batch sizes exercise is in section 2.1. This code is a standard template for all our experiments. We first initialized the accuracy Mitchell's collection to empty. We've done experiments with Batch sizes ranging from 16 to 128 incrementing by 16. We'll get the base model configuration with the default setup for all the values from the common library. We will also load up the training data with the get data method. Now we set the Epochs to a value of 20. For all our experiments, we will anyway capture the output after each Epoch so we can see the trend for…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
