SeetaDet
WHAT's SeetaDet?
SeetaDet is a platform implementing popular object detection algorithms, including R-CNN series, SSD, and RetinaNet.
We have achieved the same or higher performance than the baseline reported by the original paper.
This repository is based on Dragon, while the style of codes is PyTorch.
The torch-style codes help us to simplify the hierarchical pipeline of modern detection.
Requirements
seeta-dragon >= 0.3.0.dev20200723
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 buildInstall From Source
Clone this repository to local disk and install:
cd SeetaDet && python setup.py installInstall From Git
You can also install it from remote repository:
pip install git+https://gitlab.seetatech.com/seetaresearch/seetadet.git@masterQuick Start
Train a detection model
cd tools
python train.py --cfg <MODEL_YAML>We have provided the default YAML examples into seetadet/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>Export a detection model to ONNX
cd tools
python export.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR> --iter <ITERATION>Resources
Pre-trained ImageNet models
| Model | Usage |
|---|---|
| VGG16.SSD | SSD |
| VGG16.RCNN | R-CNN |
| R-18.Affine | R-CNN, RetinaNet, SSD |
| R-34.Affine | R-CNN, RetinaNet, SSD |
| R-50.Affine | R-CNN, RetinaNet, SSD |
| R-101.Affine | R-CNN, RetinaNet, SSD |
| AirNet.Affine | R-CNN, RetinaNet, SSD |
References
[1] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. NIPS, 2015.
[2] Deep Residual Learning for Image Recognition. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. CVPR, 2016.
[3] SSD: Single Shot MultiBox Detector. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. ECCV, 2016.
[4] Feature Pyramid Networks for Object Detection. Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. CVPR, 2017.
[5] Focal Loss for Dense Object Detection. Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. ICCV, 2017.
[6] Mask R-CNN. Kaiming He, Georgia Gkioxari, Piotr Dollár and Ross Girshick. ICCV, 2017.
[7] Detectron. Ross Girshick, Ilija Radosavovic, Georgia Gkioxari, Piotr Dollar and Kaiming He. 2018.