From the course: Building Deep Learning Applications with Keras
Join today to access over 24,400 courses taught by industry experts.
Visualize results and save the model
From the course: Building Deep Learning Applications with Keras
Visualize results and save the model
- [Instructor] Let's move on visualizing results and talk about plot training and validation loss. So for that, find chapter four and find Plot Training And Validation Loss Begin Python file. First of all, let's go ahead and run this as is and see the epochs here. So we should see 50 epochs, and we will go over in more conceptually what these mean. So first of all, what is a loss? Well, loss is a number indicating how bad the model's prediction was on a single example, which we will see in a bit. If the model's prediction is perfect, then the loss is zero, otherwise the loss is greater. The goal of training is to minimize this number, and training loss is calculated from the data that the model learns from. So as the model gets better at predicting the training data, this number should go down. And validation loss is calculated from part of the data that the model hasn't seen during training. This is to check how well the model is doing on new, unseen data. Well, what should we look…
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.
