Analyzing training results (during or after training) is much more convenient if we can visualize the metrics. A great tool for this is TensorBoard. Originally developed for TensorFlow, it can also be used with other frameworks such as Keras and PyTorch. TensorBoard gives us the ability to follow loss, metrics, weights, outputs, and more. In the following recipe, we'll show you how to use TensorBoard with Keras and leverage it to visualize training data interactively.
Visualizing training with TensorBoard and Keras
How to do it...
- First, we import all the libraries in Python, as follows:
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential...
