Weightslab Documentation

Weightslab is a Python SDK to inspect, monitor, and edit training behavior for computer vision workflows.

Inspect, edit, and optimize model training with one workflow.

Agent Quickstart

Start using the AI agent to analyze and optimize your training.

Agent Quickstart
Good Practices

Standardize your training code for WeightsLab integration.

Good Practice
Weights Studio UI

Take control of a running experiment from the browser.

Weights Studio UI
Weights Studio CLI

Take control of a running experiment from the terminal.

Weights Studio CLI
Core Concepts

Understand the 4-level workflow and each part independently.

Four-Way SDK Approach
Notebooks

Colab, local notebooks, and in-training notebook workflows.

Notebook integrations
Configuration

Environment variables and runtime toggles.

Configuration
AI Agent

Drive UI actions (sort, dump, load), data analysis, tagging/discarding, and model freeze/reset with natural language.

Experiment Agent Assistant
Experiment Reports

Ask the agent for a branded HTML report: signal health plots, dataset stats, and a written analysis.

Experiment Reports
Annotation Export

Export bounding boxes and segmentation masks to CVAT, Label Studio, or V7 for relabeling.

Annotation Export
Reference

Complete SDK, CLI, and gRPC documentation.

User Functions Reference