# How can i train the image recognizer?

**URL:** <https://community.thunkable.com/t/how-can-i-train-the-image-recognizer/2443767>\
**Category:** Questions about Thunkable X\
**Created:** [May 30, 2023, 6:06pm UTC](https://community.thunkable.com/t/how-can-i-train-the-image-recognizer/2443767 "2023-05-30T18:06:21Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![tatiang](https://sea1.discourse-cdn.com/flex015/user_avatar/community.thunkable.com/tatiang/32/55482_2.png) [@tatiang](https://community.thunkable.com/u/tatiang)\
**Post date:** [May 30, 2023, 6:42pm UTC](https://community.thunkable.com/t/how-can-i-train-the-image-recognizer/2443767/2 "2023-05-30T18:42:51Z")

</div>

You can’t. But I assume you can use Microsoft Azure to train a model on your images and then connect to that model using their API.

I’ve gone through that process with Ximilar and it’s extensive. I spent dozens of hours on it and wrote about it here: [Image Recognition & Classification using Artificial Intelligence](https://community.thunkable.com/t/image-recognition-classification-using-artificial-intelligence/1850102).

Ultimately, I gave up because it was going to be expensive to train it on enough images (thousands at least) to get it to work well enough.

---

_[View the full topic](https://community.thunkable.com/t/how-can-i-train-the-image-recognizer/2443767)._