资源分类
》 资源 》算法》traffic-sign-faster-rcnn

traffic-sign-faster-rcnn

2020-02-19 | |  56 |   0 |   0

Traffic Sign Detection

Traffic sign detection based on Faster R-CNN, implemented in Keras. The annotated dataset comes from German Traffic Sign Detection Benchmark.

Notes:

  • config.py contains all settings for the train or test run. The anchor box sizes are selected from [8, 16, 32, 64] and anchor ratios from [1:1, 1:2, 2:1].

  • The base network shared by RPN and classifier are implemented in 2-layer FCnet, ZFnet and VGG16.

  • The RPN Stride depends on network structure and should be modified correspondingly if a new model/structure is employed.

Example output:

图片.png

图片.png

上一篇：py_faster_rcnn-ship_detection

下一篇：FasterRCNN_SpringEdition

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...