Name Last Update
compile Loading commit data...
configs Loading commit data...
lib Loading commit data...
scripts Loading commit data...
tools Loading commit data...
.gitignore Loading commit data...
CHANGES Loading commit data...
README.md Loading commit data...

SeetaDet

WHAT's SeetaDet?

SeetaDet contains many useful object detectors, including R-CNN series, SSD, and the recent RetinaNet.

We have achieved the same or higher performance than the baseline reported by the original paper.

This repository is based on our Dragon, while the style of codes is PyTorch.

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

Installation

1. Install the required python packages

pip install cython pyyaml matplotlib
pip install opencv-python Pillow

2. Compile the C Extensions

cd SeetaDet/compile
bash ./make.sh

Quick Start

Train a detection model

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

We have provided the default YAML examples into SeetaDet/configs.

Test a detection model

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

Or

cd SeetaDet/tools
python test_all.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR>

Export a detection model to ONNX

cd SeetaDet/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.