What's New

SAHI + Layer integration

With this integration, you can now instantiate SAHI models from Layer.For example, you can pass the path of a YOLOv5 model trained on Layer to instantiate a DetectionModel. Here we fetch the yolo5vs pretrained model from this Layer project.

Book a demo ->

‍

Blog | What is a metadata store?

In this article, we dive into how you can start using Layer to store metadata for your current or upcoming projects. You can store metadata about your model training runs, datasets, and execution to mention a few. Furthermore Layer stores other metadata data automatically. Such as model and dataset versions that are automatically generated every time you run your project. Layer also saves the resulting models and datasets and makes them available for use immediately.

Read more ->

‍

Project Runs UI

Layer UI now has a “Runs” view on project pages to show all runs in your projects. This view allows you to track every time you execute layer.run.  With this view, you can see a complete list of runs within a project, most recent runs appearing first. If you’d like to dig in to any particular run, just click to expand the corresponding row to see the status and logs about each entity within that pipeline run. It’s also easy to send a summary of any given pipeline run to teammate, so that you can discuss an experiment in detail.

View sample ->

‍

Blog | How to Operationalise E-Commerce Product Recommendation System

One of the most common challenges in an e-commerce business to build a well-performing product recommender and categorisation model. A product recommender is used to recommend similar products to users so that total time and money spent on platform per user will be increased. There is also a need to have a model to categorise products correctly since there might be some wrongly categorised products in those platforms especially where most of content is generated by users as in case of classified websites. A product categorisation model is used to catch those products and place them back into their right categories to improve overall user experience on the platform.

Learn more ->

‍

Today, we announce our open-source dbt Adapter which runs ML pipelines inside dbt DAG.

This adapter runs ML pipelines inside dbt dag with BigQuery as the backing data warehouse. With Layer dbt Adapter you can:

• Score your data with a machine learning model from Layer.
• Train an AutoML model with your data.
• Train a custom machine learning model with your data [coming soon...]

To immediately start using Layer inside your dbt DAG, install the Layer dbt Adapter for BigQuery:

You can then automatically build state-of-the-art ML models using your own dbt models with plain SQL.

Learn more ->