Creating TF Lite Object Detection Model with Google Cloud AutoML

In this article, I will share you an awesome tutorial about how to train your own TF Lite model wtih AutoML.

Last September I successfully trained my own YOLOv3 Model, I spend almost a month to trial and error. Finally all the hard work paid off. I feel so exciting at that time. But I also wasted so much time. I also wrote a series of my journey to train YOLOv3. You can read them from the following links.

Python影像辨識筆記(九):分別在Windows和Ubuntu 18.04上安裝並執行YOLOv3(使用GPU)
Python影像辨識筆記(九之三):YOLOv3結合深度學習的Object Detector
Python影像辨識筆記(九之四):可視化YOLOv3訓練過程中的loss、IOU、avg Recall等的曲線圖
Python影像辨識筆記(九之五):透過Google Colab在雲端運行YOLOv3
NVIDIA Jetson TX2學習筆記(三):執行YOLOv3
The Complete YOLOv3 Reproduce List on GitHub

Let’s move on to our topic.

AutoML is a pretty convenient tool, you can train the model on the platform, all you need to do is just collecting pictures, annotating pictures, training the model and export the TF Lite model.

It seems pretty easy to train the model and definitely save you so much time.

If you think this article is helpful, please don’t hesitate to click the clap button and share this article with your friends so that I can have more motivation to write more articles.

Thanks, see you in the next article.

Written by

Machine Learning / Deep Learning / Python / Flutter

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store