Hello trend,
This is Satya Mallick from LearnOpenCV.com.
Last week we shared an introductory post on Tensorflow Lite. In today's post, we will
- Create: We will learn how to create a TensorFlow Lite model using the TF Lite Model Maker Library. We will fine-tune a pre-trained image classification model on the custom dataset and further explore different types of model optimization techniques currently supported by the library and export them to the TF Lite model.
- Compare: Show detailed performance comparison of the TF Lite models with the converted one.
- Deploy: Finally, we will deploy the model using a web app.
Without further ado, let's get started.
TensorFlow Lite Model Maker |
You can download the code by clicking on the button below, and star us on GitHub to say thanks!
Download Code (GitHub) |
Uncool? My bad!
I created some confusion among readers in my last newsletter when I called OpenVINO and TensorRT uncool.
OpenVINO, TensorRT, and Tensorflow Lite are absolutely essential tools for our work, and they all work like magic. We use all three (depending on the platform) in our consulting work.
What I really meant to say is that these tools lack the glitz and glamour of libraries like MediaPipe that help you build cool visual applications.
So, some people may consider these topics boring, but we cover them because these optimizations are very important for deploying applications in the real world.
Sorry for causing confusion with careless words.
Cheers!
Satya
Courses / YouTube / Facebook / LinkedIn / Twitter / Instagram
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.