# sleap-nn
[](https://github.com/talmolab/sleap-nn/actions/workflows/ci.yml)
[](https://codecov.io/gh/talmolab/sleap-nn)
[](https://github.com/talmolab/sleap-nn/releases/)
Neural network backend for training and inference for animal pose estimation.
This is the deep learning engine that powers [SLEAP](https://sleap.ai) (Social LEAP Estimates Animal Poses), providing neural network architectures for multi-instance animal pose estimation and tracking. Built on PyTorch, SLEAP-NN offers an end-to-end training workflow, supporting multiple model types (Single Instance, Top-Down, Bottom-Up, Multi-Class), and seamless integration with SLEAP's GUI and command-line tools.
## Documentation
**📚 [Documentation](https://nn.sleap.ai)** - Comprehensive guides and API reference
## Installation
**Prerequisites: Python 3.11**
### From PyPI
- **Windows/Linux with NVIDIA GPU (CUDA 11.8):**
```bash
pip install sleap-nn[torch-cuda118]
```
- **Windows/Linux with NVIDIA GPU (CUDA 12.8):**
```bash
pip install sleap-nn[torch-cuda128]
```
- **macOS with Apple Silicon (M1, M2, M3, M4) or CPU-only (no GPU or unsupported GPU):**
Note: Even if torch-cpu is used on macOS, the MPS backend will be available.
```bash
pip install sleap-nn[torch-cpu]
```
### For development setup
1. **Clone the sleap-nn repo**
```bash
git clone https://github.com/talmolab/sleap-nn.git
cd sleap-nn
```
2. **Install [`uv`](https://github.com/astral-sh/uv) and development dependencies**
`uv` is a fast and modern package manager for `pyproject.toml`-based projects. Refer [installation docs](https://docs.astral.sh/uv/getting-started/installation/) to install uv.
3. **Install sleap-nn dependencies based on your platform**\
- Sync all dependencies based on your correct wheel using `uv sync`:
- **Windows/Linux with NVIDIA GPU (CUDA 11.8):**
```bash
uv sync --extra dev --extra torch-cuda118
```
- **Windows/Linux with NVIDIA GPU (CUDA 12.8):**
```bash
uv sync --extra dev --extra torch-cuda128
```
- **macOS with Apple Silicon (M1, M2, M3, M4) or CPU-only (no GPU or unsupported GPU):**
Note: Even if torch-cpu is used on macOS, the MPS backend will be available.
```bash
uv sync --extra dev --extra torch-cpu
```
You can find the correct wheel for your system at:\
👉 [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)
4. **Run tests**
```bash
uv run pytest tests
```
5. **(Optional) Lint and format code**
```bash
uv run black --check sleap_nn tests
uv run ruff check sleap_nn/
```
## Quick Start
Let's start SLEAPiNNg !!! 🐭🐭
> For detailed information on setting up config, training/ inference workflows, please refer to our [docs](https://nn.sleap.ai).
#### 1. Set Up Your Configuration
Create a `config.yaml` file for your experiment.
> Use a sample config from [`docs/sample_configs`](https://github.com/talmolab/sleap-nn/tree/main/docs/sample_configs).
#### 2. Train a model
> Download sample training data from [here](https://storage.googleapis.com/sleap-data/datasets/BermanFlies/random_split1/train.pkg.slp) and validation data from [here](https://storage.googleapis.com/sleap-data/datasets/BermanFlies/random_split1/val.pkg.slp) for quick experimentation.
```bash
sleap-nn-train --config-name config.yaml --config-dir configs/ "data_config.train_labels_path=[labels.pkg.slp]"
```
#### 3. Run inference on the trained model
To run inference:
```bash
sleap-nn-track --data-path video.mp4 --model-paths model_ckpt_dir/
```
Raw data
{
"_id": null,
"home_page": null,
"name": "sleap-nn",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "sleap, pose estimation, deep learning, neural networks, computer vision, animal behavior",
"author": null,
"author_email": "Divya Seshadri Murali <dimurali@salk.edu>, Elizabeth Berrigan <eberrigan@salk.edu>, Vincent Tu <vitu@ucsd.edu>, Liezl Maree <lmaree@salk.edu>, David Samy <davidasamy@gmail.com>, Talmo Pereira <talmo@salk.edu>",
"download_url": "https://files.pythonhosted.org/packages/f3/0a/6f79ffe9380c2d64773246f9f59fe5324ddb00decfa9b8f4377a97ff1cfc/sleap_nn-0.0.1.tar.gz",
"platform": null,
"description": "# sleap-nn\n\n[](https://github.com/talmolab/sleap-nn/actions/workflows/ci.yml)\n[](https://codecov.io/gh/talmolab/sleap-nn)\n[](https://github.com/talmolab/sleap-nn/releases/)\n\nNeural network backend for training and inference for animal pose estimation.\n\nThis is the deep learning engine that powers [SLEAP](https://sleap.ai) (Social LEAP Estimates Animal Poses), providing neural network architectures for multi-instance animal pose estimation and tracking. Built on PyTorch, SLEAP-NN offers an end-to-end training workflow, supporting multiple model types (Single Instance, Top-Down, Bottom-Up, Multi-Class), and seamless integration with SLEAP's GUI and command-line tools.\n\n## Documentation\n\n**\ud83d\udcda [Documentation](https://nn.sleap.ai)** - Comprehensive guides and API reference\n\n## Installation\n\n**Prerequisites: Python 3.11**\n\n### From PyPI\n\n- **Windows/Linux with NVIDIA GPU (CUDA 11.8):**\n\n```bash\npip install sleap-nn[torch-cuda118]\n```\n\n- **Windows/Linux with NVIDIA GPU (CUDA 12.8):**\n\n```bash\npip install sleap-nn[torch-cuda128]\n```\n\n- **macOS with Apple Silicon (M1, M2, M3, M4) or CPU-only (no GPU or unsupported GPU):** \nNote: Even if torch-cpu is used on macOS, the MPS backend will be available.\n```bash\npip install sleap-nn[torch-cpu]\n```\n\n\n### For development setup\n\n1. **Clone the sleap-nn repo**\n\n```bash\ngit clone https://github.com/talmolab/sleap-nn.git\ncd sleap-nn\n```\n\n2. **Install [`uv`](https://github.com/astral-sh/uv) and development dependencies** \n `uv` is a fast and modern package manager for `pyproject.toml`-based projects. Refer [installation docs](https://docs.astral.sh/uv/getting-started/installation/) to install uv.\n\n3. **Install sleap-nn dependencies based on your platform**\\\n\n - Sync all dependencies based on your correct wheel using `uv sync`:\n - **Windows/Linux with NVIDIA GPU (CUDA 11.8):**\n\n ```bash\n uv sync --extra dev --extra torch-cuda118\n ```\n\n - **Windows/Linux with NVIDIA GPU (CUDA 12.8):**\n\n ```bash\n uv sync --extra dev --extra torch-cuda128\n ```\n \n - **macOS with Apple Silicon (M1, M2, M3, M4) or CPU-only (no GPU or unsupported GPU):** \n Note: Even if torch-cpu is used on macOS, the MPS backend will be available.\n ```bash\n uv sync --extra dev --extra torch-cpu\n ```\n\n You can find the correct wheel for your system at:\\\n \ud83d\udc49 [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)\n\n4. **Run tests** \n ```bash\n uv run pytest tests\n ```\n\n5. **(Optional) Lint and format code**\n ```bash\n uv run black --check sleap_nn tests\n uv run ruff check sleap_nn/\n ```\n\n## Quick Start\n\nLet's start SLEAPiNNg !!! \ud83d\udc2d\ud83d\udc2d\n\n> For detailed information on setting up config, training/ inference workflows, please refer to our [docs](https://nn.sleap.ai).\n\n#### 1. Set Up Your Configuration\n\nCreate a `config.yaml` file for your experiment.\n\n> Use a sample config from [`docs/sample_configs`](https://github.com/talmolab/sleap-nn/tree/main/docs/sample_configs).\n\n#### 2. Train a model\n\n> Download sample training data from [here](https://storage.googleapis.com/sleap-data/datasets/BermanFlies/random_split1/train.pkg.slp) and validation data from [here](https://storage.googleapis.com/sleap-data/datasets/BermanFlies/random_split1/val.pkg.slp) for quick experimentation.\n\n```bash\nsleap-nn-train --config-name config.yaml --config-dir configs/ \"data_config.train_labels_path=[labels.pkg.slp]\"\n```\n\n#### 3. Run inference on the trained model\n\nTo run inference:\n```bash\nsleap-nn-track --data-path video.mp4 --model-paths model_ckpt_dir/\n```\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "Neural network backend for training and inference for animal pose estimation.",
"version": "0.0.1",
"project_urls": {
"Homepage": "https://sleap.ai",
"Repository": "https://github.com/talmolab/sleap-nn"
},
"split_keywords": [
"sleap",
" pose estimation",
" deep learning",
" neural networks",
" computer vision",
" animal behavior"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "705d00a06cb81af41c40f524fa03aff446366a9dcec247da89684b9da3fbd21c",
"md5": "e85f29aefd14a90e1d81edf5c8d0ed79",
"sha256": "c385aa636a1703a50792e8a20d2f7970fd873cc997401b6a459fb6746b40caba"
},
"downloads": -1,
"filename": "sleap_nn-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e85f29aefd14a90e1d81edf5c8d0ed79",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 216461,
"upload_time": "2025-08-21T01:30:59",
"upload_time_iso_8601": "2025-08-21T01:30:59.645476Z",
"url": "https://files.pythonhosted.org/packages/70/5d/00a06cb81af41c40f524fa03aff446366a9dcec247da89684b9da3fbd21c/sleap_nn-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f30a6f79ffe9380c2d64773246f9f59fe5324ddb00decfa9b8f4377a97ff1cfc",
"md5": "331554124917ff1c283ea31d5218a828",
"sha256": "c3497ac962d3153fc262b0e0b4bf42658728ef8df983b6cc678b6f2ccc0057de"
},
"downloads": -1,
"filename": "sleap_nn-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "331554124917ff1c283ea31d5218a828",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 13833787,
"upload_time": "2025-08-21T01:31:01",
"upload_time_iso_8601": "2025-08-21T01:31:01.600460Z",
"url": "https://files.pythonhosted.org/packages/f3/0a/6f79ffe9380c2d64773246f9f59fe5324ddb00decfa9b8f4377a97ff1cfc/sleap_nn-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-21 01:31:01",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "talmolab",
"github_project": "sleap-nn",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "sleap-nn"
}
JSON
