# Deep learning

In this tutorial we are going to go through all the steps required to visualize the predictions on your data in VR. We are going to use Fast.ai (that sits on Pytorch) in a jupyter notebook. The data needed for the visualization will be sent with HTTP requests in python, in this tutorial you will learn to use that too. After this tutorial you are going to be able to get visual feedback on the learning process of your neural network. We aren't going to go through how to build or train your model. We are focusing solely on the learning model's output.

![82% accuracy cat dog prediction/loss](/files/-Lo4jDkNQfKg2Mcxi5Vp)

We will be generating an image just like above. The positions will be updated as the model learns. So you can see each and every image getting to their right (or in bad cases to the wrong) place.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://apertus.gitbook.io/vr/samples/deep-learning.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.