Guides¶
Task-focused walkthroughs of everything the app does. If you are new, start with the Tutorial instead. For how the pieces fit together (the app, sleap-nn, workers, and the project file), read How SLEAP works.
Labeling¶
-
âïļ Labeling Instances
Placing, editing, selecting, and deleting instances and nodes.
-
ðĶī Skeletons
Templates, drawing a skeleton on the frame, symmetries, editing nodes and edges.
-
ð§ Navigation
Frames, the seekbar, statistic graphs, marks, and multi-video projects.
-
ðĄ Suggestions
Choosing which frames are worth labeling, seven ways.
-
ðĨ Tracks
Identities across frames: assigning, transposing, propagating, cleaning up.
Videos & display¶
-
ðŽ Videos
Adding videos, remote URLs, missing-path resolution, codecs and transcoding.
-
ðïļ View & Display
Zoom, pan, colors, palettes, trails, node sizes, and what gets drawn.
Models¶
-
ð Environment setup
Getting the Python backend in place with
uv, no conda required. -
ð§ Training
Model types, configuration, monitoring, and metrics.
-
⥠Inference
Running predictions and bringing them back into the project.
-
ð Remote Compute
Pairing a GPU worker and sending it training and inference jobs.
Data¶
-
ð Import & Export
NWB, COCO, DeepLabCut, Analysis HDF5/CSV, packages, labeled clips.
-
ð Merging Projects
Combining two projects, with conflict review.
-
ðū Saving & Recovery
How saving differs by runtime, and the crash-recovery draft system.
Analyze¶
-
ð Instance Size Distribution
How big are your animals, really? Pick a crop size from data.
-
ð Label Quality Check
Automated checks for duplicates, left/right swaps, and chain-order errors.