https://github.com/ternaus/nexar2_ssd
https://github.com/ternaus/nexar2_ssd
Last synced: 10 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ternaus/nexar2_ssd
- Owner: ternaus
- License: mit
- Created: 2017-11-11T17:58:55.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-11-14T15:49:08.000Z (over 8 years ago)
- Last Synced: 2025-04-05T13:33:57.905Z (over 1 year ago)
- Language: Python
- Size: 101 MB
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Authors: AUTHORS
Awesome Lists containing this project
README
# SSD: Single Shot MultiBox Object Detector, in PyTorch for [NEXAR CHALLENGE II Vehicle Detection in the Wild using the NEXET Dataset](https://www.getnexar.com/challenge-2/)
A [PyTorch](http://pytorch.org/) implementation of [Single Shot MultiBox Detector](http://arxiv.org/abs/1512.02325) from the 2016 paper by Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang, and Alexander C. Berg. The official and original Caffe code can be found [here](https://github.com/weiliu89/caffe/tree/ssd).
Code is heavily based on (https://github.com/amdegroot/ssd.pytorch)
### Table of Contents
- Installation
- Train
- Evaluate
- Reference
## Installation
- Install [PyTorch](http://pytorch.org/) by selecting your environment on the website and running the appropriate command.
- Clone this repository.
* Note: We currently only support Python 3+.
- Then download the dataset by following the [instructions](#download-voc2007-trainval--test) below.
- We now support [Visdom](https://github.com/facebookresearch/visdom) for real-time loss visualization during training!
* To use Visdom in the browser:
```Shell
# 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).
## Training SSD
- First download the fc-reduced [VGG-16](https://arxiv.org/abs/1409.1556) 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 `ssd.pytorch/weights` dir:
```Shell
mkdir weights
cd weights
wget https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth
```
- To train SSD using the train script simply specify the parameters listed in `train.py` as a flag or manually change them.
```Shell
python -m ssd_pytorch.train
```
- Note:
* For training, an NVIDIA GPU is strongly recommended for speed.
* Currently we only support training on v2 (the newest version).
* 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:
```Shell
python -m ssd_pytorch.eval
```
You can specify the parameters listed in the `eval.py` file by flagging them or manually changing them.
## References
- [PyTorch implementation of SSD](https://github.com/amdegroot/ssd.pytorch)
- Wei Liu, et al. "SSD: Single Shot MultiBox Detector." [ECCV2016]((http://arxiv.org/abs/1512.02325)).
- [Original Implementation (CAFFE)](https://github.com/weiliu89/caffe/tree/ssd)
- A huge thank you to [Alex Koltun](https://github.com/alexkoltun) and his team at [Webyclip](webyclip.com) for their help in finishing the data augmentation portion.
- A list of other great SSD ports that were sources of inspiration (especially the Chainer repo):
* [Chainer](https://github.com/Hakuyume/chainer-ssd), [Keras](https://github.com/rykov8/ssd_keras), [MXNet](https://github.com/zhreshold/mxnet-ssd), [Tensorflow](https://github.com/balancap/SSD-Tensorflow)