From the course: TensorFlow 2.0: Working with Images
Join today to access over 23,200 courses taught by industry experts.
Transfer learning with TensorFlow Hub
From the course: TensorFlow 2.0: Working with Images
Transfer learning with TensorFlow Hub
- [Instructor] Let's head over to the Colab Notebook and look at another dataset and an example of image classification. For this example, we will need to use the GPU, so I'm going to head over to Runtime, change the runtime type. I'm already using a GPU. And I'm going to go ahead and run all the cells in the notebook. Now we're going to be using the flower's dataset in this example. And the flowers dataset has five classes. And our job is to look at an image of a flower and predict which of these five types of flowers it is. So we store all of our data in the data_dir directory. And you can see that we've got five different directories here, and each of these directories corresponds to a flower. So you've got tulips, sunflowers, roses, dandelions and daisies. Now each of the images is of size 224 by 224. And our batch size is going to be 128. The TensorFlow dataset API offers the dataset abstraction, so we will be…
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.