This feature is not available in the local mode. A view is a virtual table created by joining an internal table with one or more imported tables or tables in the external catalog registered on the External catalog page. Let

For specific datasets, you may have a domain-specific featurizer that best captures the features of that dataset. For such cases, when registering a dataset, you can specify 'Featurizer Type' as 'External.' This article describes the format of the CSV

The video below introduces data exploration and search functionality using PASCAL VOC2012 public dataset.  Data exploration is available within a 'job.'  The 'Jobs' page is reachable through Data Copilot  > Data Visualization  > Explore  on the left navigation panel. The job visualization

Data registration occurs through the execution of a data ingestion pipeline. A data processing pipeline consists of the following modules. Image Preprocessor: Any processing on the image/frame before feeding it to the featurizer. Featurizer: Featurizes each image/frame, typically

The 'Pipelines' page is available on the left navigation panel at Data > Processing Options > Pipelines , as shown below. The default listing has a list of pre-registered pipelines provided by Data Explorer out-of-the-box and can be identified

When creating a new anomaly model, you can clone from an existing model to populate the same set of good images and test images in the new model. You can edit the images, remove or add images, and specify the

The 0.8 version of the software is superseded by latest release 1.0 with many new features and a software-as-a-service(SaaS) web portal. The documentation for version 0.8 is archived below.     Your browser does not

Data Explorer supports the 'Analyze' type of job used for model performance analysis of an image classification or object detection model. This analysis requires ground truth and prediction information to be available in the catalog. Analyze job for classification model

This feature requires an Organization Admin role and is not available in local mode Secrets are used to store security-sensitive credential information needed to access the data and catalog stores. Secrets are supported only in   SaaS mode  setup. The

Data Explorer comes with a Python SDK for programmatic access to Data Explorer functionality to build your custom workflows. The following sets of APIs are provided. Data registration APIs that can be used in any Python environment to register your

Python SDK release - October 30, 2023 Python SDK for API access to Data Explorer has been released, and details are present here . Release 1.14.96 (Maintenance release) - October 27, 2023 Bug fix for an issue where the search was

click Apply . Based on the filter settings for Multi Class, the table displays the detection accuracy results. Select one of the result values from the table, and click the Image icon on the top-right corner of the section

This type of job analyzes object detection model output, which has class, bounding box, and confidence. Catalog This type of job requires the following fields to be present in the catalog. Ground truth class(string) (gt_class) Ground truth bounding

The similarity search is run against all points in a job by default. This can be changed by running a search on a filtered search space based on the catalog filter options in the Search Space drop-down, or by

As described in the Register dataset article, you can attach pipelines to the dataset when the dataset is created. This article describes the steps to attach and detach pipelines after the dataset is successfully registered. Access Pipeline Operations On the

Data Explorer enables you to enrich your data with metadata, referred to as the catalog. The catalog can be imported into the dataset in the following ways. Connect to an SQL-based catalog store, such as MySQL, SQL Server, PostgreSQL

Once the training is complete, you can export the model locally or on a different system. The export model option helps you download and run the model on your system. Refer to Create model training for the step of creating

Once the anomaly segmentation session run is complete, you can export the docker model and download it locally or on a different machine. Export Model In the model screen, click the Export Model button. If you want to apply a

Before configuring and installing the adectl tool, you will need to download the tool. In the navigation panel, navigate to Utilities > CLI/SDK > Download CLI Tool . In the Download ADECTL tool window, click the Download button to download the installer