Welcome to Deepchecks!

Deepchecks is the leading tool for testing and for validating your machine learning models and data, and it enables doing so with minimal effort. Deepchecks accompanies you through various validation and testing needs such as verifying your data’s integrity, inspecting its distributions, validating data splits, evaluating your model and comparing between different models.

Note

In addition to perusing the documentation, please feel free to to ask questions on our Slack Community, or to post a issue or start a discussion on Github.

⏩ Getting Started

Head over to the Getting Started section to learn how to get up and running with deepchecks in 5 minutes.

🏃‍♀️ See It in Action

For a quick start, check out the following pages in the tutorials section:

Tabular Data Quickstart

• Quickstart in 5 minutes

Computer Vision Quickstart

CV Beta Release

• Deepchecks Example - Simple Image Classification Tutorial

• Deepchecks for Object Detection Tutorial

• Deepchecks for Classification Tutorial

Note

Deepchecks’ Computer Vision subpackage is in beta release. It is available for installation from PyPi, use at your own discretion. Github Issues are welcome!

🙋🏼 When Should You Use Deepchecks?

While you’re in the research phase, and want to validate your data, find potential methodological problems, and/or validate your model and evaluate it.

See the When Should You Use Section for an elaborate explanation of the typical scenarios.

🔎 See More

• Getting Started

• User Guide
  • General
    • Deepchecks Hierarchy
    • Customizations
    • Exporting Results
  • Tabular
    • Tabular Tutorials
    • The Dataset Object
    • Supported Models
    • Feature Importance
  • Vision
    • Computer Vision Tutorials
    • Data Classes
    • Data Properties
  • Integrations
    • Spark & Databricks
    • Pytest
    • H2O

• Tabular Checks
  • Distribution
    • Train Test Feature Drift
    • Train Test Label Drift
    • Train Test Prediction Drift
    • Whole Dataset Drift
  • Integrity
    • New Category
    • Conflicting Labels
    • Data Duplicates
    • Dominant Frequency Change
    • Is Single Value
    • Mixed Data Types
    • Mixed Nulls
    • New Label
    • Outlier Sample Detection
    • Special Characters
    • String Length Out Of Bounds
    • String Mismatch
    • String Mismatch Comparison
  • Methodology
    • Boosting Overfit
    • Datasets Size Comparison
    • Date Train Validation Leakage Duplicates
    • Date Train Validation Leakage Overlap
    • Identifier Leakage
    • Index Leakage
    • Model Inference Time
    • Single Feature Contribution
    • Single Feature Contribution Train Test
    • Train Test Samples Mix
    • Unused Features
  • Overview
    • Columns Info
    • Model Info
  • Performance
    • Calibration Score
    • Confusion Matrix Report
    • Model Error Analysis
    • Multi Model Performance Report
    • Performance Report
    • Regression Error Distribution
    • Regression Systematic Error
    • ROC Report
    • Segment Performance
    • Simple Model Comparison

• Vision Checks
  • Distribution
    • Heatmap Comparison
    • Image Dataset Drift
    • Image Property Drift Check
    • Image Property Outliers
    • Label Property Outliers
    • New Labels
    • Train Test Label Drift
    • Train Test Prediction Drift
  • Methodology
    • Similar Image Leakage
    • Simple Feature Contribution
  • Performance
    • Class Performance
    • Confusion Matrix
    • Image Segment Performance
    • Mean Average Precision Report
    • Mean Average Recall Report
    • Model Error Analysis check
    • Robustness Report
    • Simple Model Comparison

• API Reference

For additional usage examples and for understanding the best practices of how to use the package, stay tuned, as this package is in active development!

next

Getting Started