Skip to content
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
Python Shell
Branch: master
Clone or download
toandaominh1997 Merge pull request #11 from toandaominh1997/demo
Change augbumentation and read dataset
Latest commit 0fc8bd8 Dec 6, 2019

README.md

EfficientDet: Scalable and Efficient Object Detection, in PyTorch

A PyTorch implementation of EfficientDet from the 2019 paper by Mingxing Tan Ruoming Pang Quoc V. Le Google Research, Brain Team. The official and original: comming soon.

Table of Contents

       

Installation

  • Install PyTorch by selecting your environment on the website and running the appropriate command.
  • Clone this repository.
    • Note: We currently only support Python 3.6+.
  • Then download the dataset by following the instructions below.
  • 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 EfficientDet

  • To train EfficientDet using the train script simply specify the parameters listed in train.py as a flag or manually change them.
python train.py
  • Note:
    • For training, an NVIDIA GPU is strongly recommended for speed.
    • For instructions on Visdom usage/installation, see the Installation section.
    • You can pick-up training from a checkpoint by specifying the path as one of the training parameters (again, see train.py for options)

Evaluation

To evaluate a trained network:

Results on the validation set VOC 2012

Models mAP params FLOPs
EfficientDet-D0 training training training
EfficientDet-D1 comming soon comming soon comming soon
EfficientDet-D2 comming soon comming soon comming soon
EfficientDet-D3 comming soon comming soon comming soon
EfficientDet-D4 comming soon comming soon comming soon
EfficientDet-D5+AA comming soon comming soon comming soon
EfficientDet-D6+AA comming soon comming soon comming soon
EfficientDet-D7+AA comming soon comming soon comming soon

Performance

Demo

TODO

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

  • Still to come:
    • EfficientDet
    • GPU-Parallel
    • NMS
    • Soft-NMS
    • Weighted Feature Fusion
    • Pretrained model
    • Demo
    • Model zoo

Authors

Note: Unfortunately, this is just a hobby of ours and not a full-time job, so we'll do our best to keep things up to date, but no guarantees. That being said, thanks to everyone for your continued help and feedback as it is really appreciated. We will try to address everything as soon as possible.

References

You can’t perform that action at this time.