After months of hard work, we are excited to introduce Lobe, a free, easy-to-use app that has everything you need to train custom machine learning models.
Machine learning is such a transformative tool. It's redefining how we build software and allowing us to do things with technology that just a few years ago, we didn't even think were possible. But machine learning is complicated, and that means that right now, it's only being used by a small group of experts. We think machine learning should be accessible to anyone, and that's why we introduced Lobe.
Lobe is an easy-to-use tool that helps you train machine learning models on your own computer, for free, without any prior experience required. It runs locally on both Mac and PC, and you can ship your model to any platform you choose.
Machine Learning Made Easy
Lobe takes a new humane approach to machine learning by putting your images in the foreground and receding to the background, serving as the main bridge between your ideas and your machine learning model.
Lobe also simplifies the process of machine learning into three easy steps. Collect and label your images. Train and understand your results. Then play with your model and improve it.
Label your images
The first step to creating a machine learning model is to collect your images, import them, and give them a name. Lobe allows you to collect bursts of images using your webcam or drag in a folder of images from your computer. While the images are being imported, you can quickly label them to create a dataset.
Making data collection and labeling easy simplifies one of the biggest pain points when building machine learning models, and it allows you to focus on solving your problem and understanding your machine learning model better.
Train your model
After you have imported and labeled images, Lobe will automatically start training a machine learning model without any setup or configuration. Because training recedes to the background and happens automatically, you can keep using Lobe to label images and improve your dataset.
Lobe is fluid and reactive, so as soon as you get results from training, it will give you live feedback on your model's performance. This will allow you to understand your model's strengths and weaknesses more quickly.
Play with it
The best way to understand your model's performance is to use it in the real world so you can test it with images it has never seen before. Lobe lets you try out your model using your webcam or images from your computer.
This allows you to see how your model is performing on brand new images. Lobe additionally lets you improve your results by giving your model feedback when its predictions are correct or incorrect.
Building a machine learning model is just the first step when solving a problem, prototyping an idea, or even just learning. The next step is to export your model and use it in your app.
Lobe makes it easy to export your model to a variety of industry standard formats and ship it on any platform you choose whether that’s a Raspberry Pi, a mobile phone, or even a server. To make it even easier, you can use one of our starter projects that seamlessly integrates your model with an Android, iOS, Python, or web app.
Machine learning can be complicated and tedious, which is why Lobe aims to make it simple, allowing anyone with an idea to collect images, train a model, play with it, and ship it on any platform they choose.
To make machine learning accessible to everyone, we started with a local, free, easy-to-use app that would distill down the complicated parts of machine learning to make it simple and humane for anyone.