https://github.com/hritikgupta/plantwatcher-ssd

A pytorch implementation of Single Shot Detector trained on plant images [for DESIGN PRACTICUM]
https://github.com/hritikgupta/plantwatcher-ssd

cnn-pytorch plants project ssd

Last synced: 9 days ago
JSON representation

A pytorch implementation of Single Shot Detector trained on plant images [for DESIGN PRACTICUM]

• Host: GitHub
• URL: https://github.com/hritikgupta/plantwatcher-ssd
• Owner: hritikgupta
• Created: 2018-06-01T11:35:50.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2018-10-08T13:45:15.000Z (over 7 years ago)
• Last Synced: 2025-11-21T17:07:12.490Z (7 months ago)
• Topics: cnn-pytorch, plants, project, ssd
• Language: Python
• Homepage:
• Size: 492 KB
• Stars: 1
• Watchers: 0
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# PlantWatcher-SSD

This is an implementation of [Single Shot MultiBox Detector](https://arxiv.org/abs/1512.02325) in PyTorch trained on plant images, done as a part of an academic project, Design Practicum. Below poster represents a gist of the motive behind project.

![Poster entitling the project](res/image.png)

## Use pretrained VGG16 model

I do not recommend training SSD from scratch. Using pretrained VGG model helps a lot to achieve lower losses.

I use the pretrained [pytorch/vision](https://github.com/pytorch/vision#models) VGG16 model from [PyTorch model zoo](https://download.pytorch.org/models/vgg16-397923af.pth).

## Credit

This implementation is initially inspired by:

- [Hakuyume/chainer-ssd](https://github.com/Hakuyume/chainer-ssd)  

- [amdegroot/ssd.pytorch](https://github.com/amdegroot/ssd.pytorch)