https://github.com/rykov8/ssd_keras

Port of Single Shot MultiBox Detector to Keras
https://github.com/rykov8/ssd_keras

computer-vision deep-learning keras-models object-detection

Last synced: about 2 months ago
JSON representation

Port of Single Shot MultiBox Detector to Keras

• Host: GitHub
• URL: https://github.com/rykov8/ssd_keras
• Owner: rykov8
• License: mit
• Archived: true
• Created: 2016-11-04T21:22:49.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2021-06-01T16:00:23.000Z (over 3 years ago)
• Last Synced: 2024-09-21T16:24:01.612Z (about 2 months ago)
• Topics: computer-vision, deep-learning, keras-models, object-detection
• Language: Jupyter Notebook
• Homepage:
• Size: 3.12 MB
• Stars: 1,100
• Watchers: 37
• Forks: 553
• Open Issues: 103
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[![license](https://img.shields.io/github/license/mashape/apistatus.svg)](LICENSE)

# A port of [SSD: Single Shot MultiBox Detector](https://github.com/weiliu89/caffe/tree/ssd) to [Keras](https://keras.io) framework.

For more details, please refer to [arXiv paper](http://arxiv.org/abs/1512.02325).

For forward pass for 300x300 model, please, follow `SSD.ipynb` for examples. For training procedure for 300x300 model, please, follow `SSD_training.ipynb` for examples. Moreover, in `testing_utils` folder there is a useful script to test `SSD` on video or on camera input.

Weights are ported from the original models and are available [here](https://mega.nz/#F!7RowVLCL!q3cEVRK9jyOSB9el3SssIA). You need `weights_SSD300.hdf5`, `weights_300x300_old.hdf5` is for the old version of architecture with 3x3 convolution for `pool6`.

This code was tested with `Keras` v1.2.2, `Tensorflow` v1.0.0, `OpenCV` v3.1.0-dev