How To Run Your Fine-Tuned EasyOCR Model In Python

Author(s): Eivind Kjosbakken

Originally published on Towards AI.

After fine-tuning my EasyOCR engine in this tutorial on TowardsAI, I wanted to run my fine-tuned model in Python directly. This, however, proved to be quite difficult without access to all required files. I, therefore, am making this tutorial to show you how you can set up your own local fine-tuned model in EasyOCR.

Run EasyOCR locally in Python with this tutorial! OpenAI. (2024). ChatGPT [Large language model]. https://chat.openai.comPrerequisitesMotivationInstalling required packagesUsing your custom modelRunning the codeConclusion

In this tutorial, I will assume you already have run a fine-tuning of your EasyOCR model, which means you have a .pth model locally you want to use in EasyOCR. You can learn how to do that in this TowardsAI article. Other than that, I recommend having some Python knowledge.

I got EasyOCR running in the terminal with my tutorial on fine-tuning EasyOCR, but getting this to work directly in Python with code proved to be a lot more difficult. I spent a lot of time figuring out how to get a hold of the appropriate files, and where to place them, so I made this article to make the process simpler for you.

You first need to install the required packages. Install torch first from the PyTorch… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI