Using deep learning- from project setup to report building
In this section, you will implement a practical example that performs an image classification task. The objective of this example is to build a TensorFlow model that predicts the type of dress represented in an image. The model is fitted with some images representing clothes, and then it is used to predict the type of dress. You will track the model in Comet, and you will build a simple demo interface using Gradio to test the model performance interactively.
The full code of the example described in this section is available at the following link: https://github.com/PacktPublishing/Comet-for-Data-Science/tree/main/10.
You will focus on the following aspects:
- Introducing Gradio
- Loading the dataset
- Implementing a basic model
- Exploring results in Comet
- Building a prediction interface
- Building the final report
Let’s start from the first point: introducing Gradio.
