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 a unified workflow.
Install, build, and run Weightslab documentation locally in minutes.
Understand how model, data, hyperparameters, and logger workflows connect.
Learn how to wrap training components and iterate on difficult samples.
Reference all public SDK functions with usage-oriented explanations.
The weightslab CLI and its interactive console — every command,
flag, and default.
Classification, detection, segmentation, clustering, anomaly detection, LiDAR, and Lightning — all with WeightsLab wired in.
Integrate Weightslab with Lightning.
Integrate Weightslab with Ultralytics.
Deploy and operate the UI: architecture, ports, TLS, and actions.
All environment variables for WeightsLab and Weights Studio with defaults and explanations.
Drive UI actions (sort, dump, load), data analysis, tagging/discarding, and model freeze/reset with natural language.
All RPC handlers, parameters, and behavior. Comprehensive audit logging for user interactions.
Weightslab in one sentence
Wrap your training script once, then monitor, tag/discard, adjust, and improve continuously.