torch-ssd 1.2.0

High quality, fast, modular reference implementation of SSD in PyTorch

High quality, fast, modular reference implementation of SSD in PyTorch 1.0

This repository implements SSD (Single Shot MultiBox Detector). The implementation is heavily influenced by the projects ssd.pytorch, pytorch-ssd and maskrcnn-benchmark. This repository aims to be the code base for researches based on SSD.

Example SSD output (ssd300_voc0712).

Losses	Learning rate	Metrics

Highlights

• PyTorch 1.0: Support PyTorch 1.0 or higher.
• Multi-GPU training and inference: We use DistributedDataParallel, you can train or test with arbitrary GPU(s), the training schema will change accordingly.
• Modular: And you own modules without pain. We abstract backbone,Detector, BoxHead, BoxPredictor, etc. You can replace every component with your own code without change the code base. For example, You can add EfficientNet as backbone, just add efficient_net.py (ALREADY ADDED) and register it, specific it in the config file, It's done!
• CPU support for inference: runs on CPU in inference time.
• Smooth and enjoyable training procedure: we save the state of model, optimizer, scheduler, training iter, you can stop your training and resume training exactly from the save point without change your training CMD.
• Batched inference: can perform inference using multiple images per batch per GPU.
• Evaluating during training: eval you model every eval_step to check performance improving or not.
• Metrics Visualization: visualize metrics details in tensorboard, like AP, APl, APm and APs for COCO dataset or mAP and 20 categories' AP for VOC dataset.
• Auto download: load pre-trained weights from URL and cache it.

Installation

Requirements

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

Step-by-step installation

git clone https://github.com/lufficc/SSD.git
cd SSD
#Required packages
pip install torch torchvision yacs tqdm opencv-python vizer

# Optional packages
# If you want visualize loss curve. Default is enabled. Disable by using --use_tensorboard 0 when training.
pip install tensorboardX

# If you train coco dataset, must install cocoapi.
cd ~/github
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
python setup.py build_ext install

Build

NMS build is not necessary, as we provide a python-like nms, but is very slower than build-version.

# For faster inference you need to build nms, this is needed when evaluating. Only training doesn't need this.
cd ext
python build.py build_ext develop

Train

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".

Single GPU training

# for example, train SSD300:
python train.py --config-file configs/vgg_ssd300_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_ssd300_voc0712.yaml SOLVER.WARMUP_FACTOR 0.03333 SOLVER.WARMUP_ITERS 1000

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 according to this paper: Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.

Evaluate

Single GPU evaluating

# for example, evaluate SSD300:
python test.py --config-file configs/vgg_ssd300_voc0712.yaml

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

Demo

Predicting image in a folder is simple:

python demo.py --config-file configs/vgg_ssd300_voc0712.yaml --images_dir demo

Then the predicted images with boxes, scores and label names will saved to demo/result folder.

MODEL ZOO

Origin Paper:

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

COCO:

Backbone	Input Size	box AP	Model Size	Download
VGG16	300	25.2	262MB	model
VGG16	512	xx.x	xxx.xMB
Mobilenet V2	320	xx.x	xxx.xMB

PASCAL VOC:

Backbone	Input Size	mAP	Model Size	Download
VGG16	300	77.6	201MB	model
VGG16	512	xx.x	xxx.xMB
Mobilenet V2	320	68.8	25.5MB	model
EfficientNet-B3	300	73.9	97.1MB	model

Troubleshooting

If you have issues running or compiling this code, we have compiled a list of common issues in TROUBLESHOOTING.md. If your issue is not present there, please feel free to open a new issue.