SeetaDet

SeetaDet is a platform implementing popular object detection algorithms.

This repository is based on seeta-dragon, while the style of codes is torch.

The torch-style codes help us to simplify the hierarchical pipeline of modern detection.

Requirements

seeta-dragon >= 0.3.0.dev20201024

Installation

Build From Source

If you prefer to develop modules as well as running experiments, following commands will build but not install to site-packages:

cd seetadet && python setup.py build

Install From Source

Clone this repository to local disk and install:

cd seetadet && python setup.py install

Install From Git

You can also install it from remote repository:

pip install git+https://gitlab.seetatech.com/seetaresearch/seetadet.git@master

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>

Or

cd tools
python test_all.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR> --last 1

Export a detection model to ONNX

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

Benchmark and Model Zoo

Results and models are available in the Model Zoo.

Supported Backbones

• ResNet
• VGG
• MobileNet
• AirNet

Supported Algorithms

• Faster R-CNN
• Mask R-CNN
• SSD
• RetinaNet

License

BSD 2-Clause license