Name Last Update
configs Loading commit data...
csrc Loading commit data...
data Loading commit data...
scripts/datasets Loading commit data...
seetadet Loading commit data...
tools Loading commit data...
.flake8 Loading commit data...
.gitignore Loading commit data...
LICENSE Loading commit data...
MODEL_ZOO.md Loading commit data...
README.md Loading commit data...
requirements.txt Loading commit data...
setup.py Loading commit data...
version.txt Loading commit data...

SeetaDet

SeetaDet is a platform implementing popular object detection algorithms.

This platform works with SeetaDragon, and uses the PyTorch style.

Installation

Install from PyPI:

pip install seeta-det

Or, clone this repository to local disk and install:

cd seetadet && pip install .

You can also install from the remote repository:

pip install git+ssh://git@github.com/seetaresearch/seetadet.git

If you prefer to develop locally, build but not install to site-packages:

cd seetadet && python setup.py build

Quick Start

Train a detection model

cd tools
python train.py --cfg <MODEL_YAML>

We have provided the default YAML examples into configs.

Test a detection model

cd tools
python test.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR> --iter <ITERATION>

Export a detection model to ONNX

cd tools
python export.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR> --iter <ITERATION>

Serve a detection model

cd tools
python serve.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR> --iter <ITERATION>

Benchmark and Model Zoo

Results and models are available in the Model Zoo.

License

BSD 2-Clause license