Awesome

A higher performance PyTorch implementation of Single-Shot Refinement Neural Network for Object Detection. The official and original Caffe code can be found here.

Table of Contents

• <a href='#performance'>Performance</a>
• <a href='#installation'>Installation</a>
• <a href='#datasets'>Datasets</a>
• <a href='#training-refinedet'>Train</a>
• <a href='#evaluation'>Evaluate</a>
• <a href='#todo'>Future Work</a>
• <a href='#references'>Reference</a>

Performance

VOC2007 Test

mAP (Single Scale Test)

Installation

• Install PyTorch by selecting your environment on the website and running the appropriate command.
  • Note: You should use at least PyTorch0.4.0
• Clone this repository.
  • Note: We currently only support Python 3+.
• Then download the dataset by following the instructions below.
• We now support Visdom for real-time loss visualization during training!
  • To use Visdom in the browser:

  # First install Python server and client
  pip install visdom
  # Start the server (probably in a screen or tmux)
  python -m visdom.server
  

  • Then (during training) navigate to http://localhost:8097/ (see the Train section below for training details).
• Note: For training, we currently support VOC and COCO, and aim to add ImageNet support soon.

Datasets

To make things easy, we provide bash scripts to handle the dataset downloads and setup for you. We also provide simple dataset loaders that inherit torch.utils.data.Dataset, making them fully compatible with the torchvision.datasets API.

COCO

Microsoft COCO: Common Objects in Context

Download COCO 2014

# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/COCO2014.sh

VOC Dataset

PASCAL VOC: Visual Object Classes

Download VOC2007 trainval & test

# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2007.sh # <directory>

Download VOC2012 trainval

# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2012.sh # <directory>

Training RefineDet

• First download the fc-reduced VGG-16 PyTorch base network weights at: https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth
• By default, we assume you have downloaded the file in the RefineDet.PyTorch/weights dir:

mkdir weights
cd weights
wget https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth

• To train RefineDet320 or RefineDet512 using the train scripts train_refinedet320.sh and train_refinedet512.sh. You can manually change them as you want.

./train_refinedet320.sh  #./train_refinedet512.sh

• Note:
  • For training, an NVIDIA GPU is strongly recommended for speed.
  • For instructions on Visdom usage/installation, see the <a href='#installation'>Installation</a> section.
  • You can pick-up training from a checkpoint by specifying the path as one of the training parameters (again, see train_refinedet.py for options)

Evaluation

To evaluate a trained network:

./eval_refinedet.sh

You can specify the parameters listed in the eval_refinedet.py file by flagging them or manually changing them.

TODO

We have accumulated the following to-do list, which we hope to complete in the near future

• Still to come:
  • Support for multi-scale testing

References

• Original Implementation (CAFFE)
• A list of other great SSD ports that were sources of inspiration:
  • amdegroot/ssd.pytorch
  • lzx1413/PytorchSSD