What's Changed

SLEAP v1.5.1 – Bug fixes & Documentation Improvements

This release focuses on a few bug fixes in the training pipeline, improving installation instructions, and updating documentation for a smoother user experience.

Note: Starting with SLEAP v1.5+, all deep learning functionality is powered by the PyTorch-based sleap-nn backend. TensorFlow models (with UNet backbones) from earlier versions are still supported for inference. Refer Migrating to 1.5+ docs for more details!

How to install?

You can now install SLEAP quickly using uv

Step 1: Install uv - an ultra-fast Python package manager

# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

Step 2: Install sleap

# Windows/ Linux (CUDA)
uv tool install "sleap[nn]" --index https://download.pytorch.org/whl/cu128 --index https://pypi.org/simple

# Windows/ Linux (CPU)
uv tool install "sleap[nn]" --index https://download.pytorch.org/whl/cpu --index https://pypi.org/simple

# macOS
uv tool install "sleap[nn]"

Check the full installation guide for platform-specific instructions and advanced options.

Once you've installed SLEAP, run the below command from anywhere in your terminal

sleap-label

The GUI should open up!

Highlights

• Improved installation:
  • Platform-specific dependency groups for sleap installation with CUDA support.
  • Fixed CUDA installation issues on Windows.
  • Updated installation instructions and options for clarity.
• Documentation updates:
  • Fixed typos and broken links.
  • Improved CLI docs with new options and guidance on legacy CLIs.
  • Fixed MkDocs versioning and improved doc site structure.
• Error handling: sleap-nn import errors are now handled gracefully with clear user guidance.
• Bug fixes: Minor fixes across CLI and docs to improve stability.

Full Changelog: v1.5.0...v1.5.1