sestars666/ma-ssd

MA SSD for small and fast object detection

The pytorch implement of MA-SSD

This repository implements MA-SSD (Multi Attention SSD for Fast Detection of Small Objects). The implementation is based on the projects lufficc/SSD.

MA-SSD	SSD

New Features in This Implementation

• Fast Small Object Detection MA-SSD outperforms SSD on detection especially in small object detection task. MA-SSD runs over 100 FPS on single RTX 2080 Ti GPU. In Quadro P2000 GPU, it also runs over 23 FPS(SSD is 28 FPS).
• Neck Structure In ssd/modeling/neck/, you can add or modifiy neck module. Neck module always be employed between backbone and head.
• Inference Speed Calculation While you running demo.py, it is not only detect objects in specify image folder but also calculate FPS for each image and avgerage FPS for all image.
• Multi Attention Module
• Feature Fusion Module

Installation

Requirements

1. Python3
2. PyTorch 1.0 or higher
3. yacs
4. Vizer
5. GCC >= 4.9
6. OpenCV

Installation Steps

git clone https://github.com/kevinchan04/MA-SSD.git
cd MA-SSD
# Required packages: torch torchvision yacs tqdm opencv-python vizer
pip install -r requirements.txt

# It's recommended to install the latest release of torch and torchvision.

Setting Up Datasets

Pascal VOC

For Pascal VOC dataset, make the folder structure like this:

VOC_ROOT
|__ VOC2007
    |_ JPEGImages
    |_ Annotations
    |_ ImageSets
    |_ SegmentationClass
|__ VOC2012
    |_ JPEGImages
    |_ Annotations
    |_ ImageSets
    |_ SegmentationClass
|__ ...

Where VOC_ROOT default is datasets folder in current project, you can create symlinks to datasets or export VOC_ROOT="/path/to/voc_root".

COCO

For COCO dataset, make the folder structure like this:

COCO_ROOT
|__ annotations
    |_ instances_valminusminival2014.json
    |_ instances_minival2014.json
    |_ instances_train2014.json
    |_ instances_val2014.json
    |_ ...
|__ train2014
    |_ <im-1-name>.jpg
    |_ ...
    |_ <im-N-name>.jpg
|__ val2014
    |_ <im-1-name>.jpg
    |_ ...
    |_ <im-N-name>.jpg
|__ ...

Where COCO_ROOT default is datasets folder in current project, you can create symlinks to datasets or export COCO_ROOT="/path/to/coco_root".

Evaluate

Single GPU evaluating

# for example, evaluate SSD300:
python test.py --config-file configs/vgg_att_ssd300_neckthreemed_voc0712.yaml --ckpt https://github.com/kevinchan04/MA-SSD/releases/download/1.0/vgg_att_ssd300_voc0712_neckthreemed.pth

Multi-GPU evaluating

# for example, evaluate SSD300 with 4 GPUs:
export NGPUS=4
python -m torch.distributed.launch --nproc_per_node=$NGPUS test.py --config-file configs/vgg_ssd300_voc0712.yaml --ckpt https://github.com/kevinchan04/MA-SSD/releases/download/1.0/vgg_att_ssd300_voc0712_neckthreemed.pth

Demo

Predicting image in a folder is simple, it will calculate avgerage speed of inference(FPS):

python demo.py --config-file configs/vgg_ssd300_voc0712.yaml --images_dir demo --ckpt https://github.com/kevinchan04/MA-SSD/releases/download/1.0/vgg_att_ssd300_voc0712_neckthreemed.pth

Then it will download and cache vgg_att_ssd300_voc0712_neckthreemed.pth automatically and predicted images with boxes, scores and label names will saved to demo/result folder by default.

Train

Single GPU training

# for example, train SSD300:
python train.py --config-file configs/vgg_att_ssd300_neckthreemed_voc0712.yaml

Multi-GPU training

# for example, train SSD300 with 4 GPUs:
export NGPUS=4
python -m torch.distributed.launch --nproc_per_node=$NGPUS train.py --config-file configs/vgg_att_ssd300_neckthreemed_voc0712.yaml 

The configuration files that I provide assume that we are running on single GPU. When changing number of GPUs, hyper-parameter (lr, max_iter, ...) will also changed. The learning rate is the sum of all GPUs, which means if you are training on 4 GPUs, lr should be set as 1e-3. According to our experiments, larger lr always requires more warm-up iterations. The max_iter also is the sum on all GPUs.

MODEL ZOO

Origin Paper:

	VOC2007 test	coco test-dev2015
SSD300*	77.2	25.1
SSD512*	79.8	28.8

COCO:

Backbone	Neck	Input Size	box AP	Model Size	Download
VGG16	neckthreemed	300	26.5	372MB	model

PASCAL VOC:

Backbone	Neck	Input Size	mAP	Model Size	Download
VGG16	neckthreemed	300	79.9	307MB	model

neckthreemed is multi attention with feature fusion neck. Please refer to paper with more details about comparsion with other methods.