alwaysAI Announces Model Training Feature

By Stephanie Casola • Oct 01, 2020

Here at alwaysAI, we love to engage with our community of over 10K developers. We have been listening closely to the feedback and are proud to announce the launch of the most requested feature: Model Training.

With the alwaysAI Model Training Toolkit, you can do code-less model training based on Tensorflow. With this powerful tool, you can get to an object detection model faster and easier than with Keras or Pytorch. You can train on your local machine and use either CPU or GPU, and the resulting model is integrated into the workflow of the alwaysAI platform. 

Use our Model Training Toolkit for your AutoML needs. We cover the entire model training pipeline from raw dataset to edge deployable models. We provide COCO Dataset pre-trained models and our pre-tuned hyper parameters allow non-experts to achieve model training success with little experience.

Build your app, customize it, train your unique model and run it on the edge. The toolkit leverages transfer learning to modify an existing model instead of creating a model from scratch, so use the alwaysAI model training tool to save time.

Achieve model training in five steps:

  1. Data Collection: Our Image Capture application helps you with your data collection, so that you can collect videos and images directly from your edge device. See this GitHub repo for more on this. 
  2. Data Annotation: We have CVAT, a data annotation tool, built right into our model training toolkit so that you can easily annotate your data. 
  3. Transfer Learning: Train a custom MobileNet SSD model. Use transfer learning to take the knowledge of the COCO Dataset and improve upon it or modify it to your unique dataset. This way, you don’t have to train a model from scratch. 
  4. Upload to Model Catalog
  5. Use in an alwaysAI app and run on the edge. 

Check out this article to learn more about model training and be sure to check out our docs to learn how to get started with our Model Training Toolkit. Please reach out to our team on Discord if you have any questions or need help getting started. 

To get started make sure that you are logged into your alwaysAI account and that you have alwaysAI installed on your machine. To do this, you can go to the Development Computer Set-Up in the “Get Started” section of our docs. 

Sign-up for an alwaysAI account here if you haven’t already.

We will continue to upload helpful tutorials to our blog and docs to stay tuned for that! 

We look forward to seeing you train your own computer vision models with alwaysAI!

By Stephanie Casola • Oct 01, 2020

Developer stories to your inbox.

Subscribe to the Developer Digest, a monthly dose of all things code.

You may unsubscribe at any time using the unsubscribe link in the digest email. See our privacy policy for more information.

alwaysAI Ad
stylized image of a computer chip

Sign up today and start your project

We can't wait to see what you'll build!