seavision 1.0.0

Re-usable computer vision tools for research and development

🚀 Quick Start

pip install git+https://github.com/SEA-AI/seavision

Optional installation methods

If you want to install additional dependencies.

pip install "seavision[inference] @ git+https://github.com/SEA-AI/seavision"

If you want to test a specific branch

pip install git+https://github.com/SEA-AI/seavision@branch-name

import seavision as sv

# load image
img = sv.imread("https://raw.githubusercontent.com/SEA-AI/.github/main/assets/example_1_IR.jpg")
# load model trained on mixed IR and RGB images
model = sv.load_model("ahoyv2n-MIX-b1")
# run inference
results = model(img)
# draw results on image
results.draw(img, as_pil=True).show()

💪 Contributing

Contributions are welcome! Please open an issue or submit a pull request.

Install uv if you don't have it yet and run the following command to install the main and development dependencies.

uv sync

If you want to install all dependencies.

uv sync --all-extras

• Pre-commit Hooks: Use pre-commit hooks to maintain code quality.
• Style Guide: Follow guidelines enforced via ruff and run checks before committing.

1. Install pre-commit hooks:

uvx pre-commit install

2. Run Ruff for linting and auto-fixes:

uvx ruff check --fix

3. Add dependencies using UV:

uv add <package-name>
uv add <package-name>@<version>
uv sync  # Syncs dependencies from pyproject.toml