Plainsight February 2022 Release Notes

Published on 1/31/22

We are excited to share the notes for our latest release of the Plainsight vision AI platform. This update includes the public release of SmartML, our no-code model training feature, the ability to deploy models via API endpoint within the platform, updates to our platform pricing  and much more. 

We’d love to hear what you think about these new features and hear about your experience with the Plainsight vision AI platform. Join the official Plainsight Slack Channel.

Sources

  • Video File Support: Upload video files from local files or cloud storage buckets. 
  • Clip and Convert: Users can now convert local video files to MP4 to create video clips and convert video into frames for annotation from the Data Source tab of a project. 

Dataset

  • Use custom models with AutoLabel: Users can now choose from user-created custom models when using AutoLabel (our AI-assisted labeling feature). 
  • Versioning: Create locked versions of datasets for project traceability.
  • Multi-Class Labels: Projects can now accommodate label schemas with a large number classes.

SmartML Custom Model Training

  • No-Code Model Training with SmartML: Labeled datasets can now be used for model training directly in the platform! Without writing a single line of code, users can now train vision AI models for object detection and instance segmentation.
  • One-Click Training: Customize hyperparameters or use the default settings to start training in one click. 
  • Auto-Stop: SmartML’s auto stop feature will automatically stop model training when the model stop measurably improving , helping to conserve usage. 
  • SmartML Dashboard View: Review model training results in our dashboard view to evaluate individual performance on test and validation datasets. Manage model versions for traceability.
  • Model Version Testing: Test your model against local files by setting up a temporary live API endpoint and uploading your files.

Deployment

  • Live API Endpoint: Deploy vision AI models using a live API endpoint for nearly instant prediction results.
  • Batch Inferencing: Connect API model deployment to a Pub/Sub topic to get inference results..
  • Test Modal: Add a single file to test the model and view the predictions on the image.

Other

  • New Team Roles: Organizations can now designate 3 levels of permission in the platform: Administrator, Project Manager, and Labeler. 
  • Domain and Name Change: The Sense platform formerly accessed at http://sense.sixgill.com is now called the Plainsight vision AI platform and can be accessed at app.plainsight.ai 

Pay-As-You-Go Pricing

We have replaced our 30 day free trial with a pay-as-you-go consumption model but for a limited time you will have access to the full platform before we start our new pricing plan.

All projects that were created in Sense will still be available in the updated platform and all accounts will also have their usage reset.

More Plainsight Blog Posts:

5 Ways Agribusinesses Can Prevent Recalls, Shutdowns, and Delays with Vision AI

5 Ways Agribusinesses Can Prevent Recalls, Shutdowns, and Delays with Vision AI

Investments in computer vision technology can help agribusinesses and food manufacturers of all types spot signs of trouble early and stop costly, potentially deadly recalls before they happen. Deployed across the production and manufacturing cycles, these models can detect hazards ranging from contaminants and foreign objects to defective equipment and non-compliant behavior. Organizations capture hundreds of thousands of hours of visual data in the form of video footage and imagery every day, and computer vision allows these businesses to put this data to work for process transformation.

How Can Vision AI Predict and Prevent Supply Chain Disruptions?

How Can Vision AI Predict and Prevent Supply Chain Disruptions?

Introducing computer vision across the supply chain can help manufacturers predict and prevent the types of conditions that lead to these kinds of disruptions. From potential contaminants and foreign objects to defective products and packaging to unsafe or unsanitary behavior, computer vision is the key to recognizing supply chain obstacles early and stopping shortages in their tracks. AI solutions could prove especially useful in volatile, high-production periods where errors and disruptions are both especially likely and especially costly.