From the course: Neural Networks and Convolutional Neural Networks Essential Training
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Training the neural network model
From the course: Neural Networks and Convolutional Neural Networks Essential Training
Training the neural network model
- [Narrator] So now that we've complied our model, let's look at training it. So go to model.fit, and we look at the parameters that we need to specify. So, we need to provide the training models. We need to provide the number of epochs, which is the number of times the model goes through the training data. And we need to provide a parameter for the validation data. So, let's start start here with the training data. So, x_train, y_train, the number of epochs you want here is 20, and we want to specify that the validation data is going to be what we have in x_test and y_test. So now, we need to put that into a variable. So, let's call that history, and we run that cell. So, we can see that we have now completed training of our model and this is stored in the history object. We can see that the model is doing pretty well. And we can see for the validation data set that it has an accuracy of about 98.27%. In the next video, we will look at the accuracy of the model.
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.
Contents
-
-
-
-
-
(Locked)
Understanding the components in Keras2m 12s
-
(Locked)
Setting up a Microsoft account on Azure1m 57s
-
(Locked)
Introduction to MNIST5m 33s
-
(Locked)
Preprocessing the training data4m 38s
-
(Locked)
Preprocessing the test data1m 58s
-
(Locked)
Building the Keras model2m 23s
-
(Locked)
Compiling the neural network model2m 18s
-
(Locked)
Training the neural network model1m 27s
-
(Locked)
Accuracy and evaluation of the neural network model2m 4s
-
(Locked)
-
-
-
-
-