Tensorflow Faster RCNN 目标检测

tf-faster-rcnn

Tensorflow Faster RCNN for Object Detection

Xinlei Chen(Xinleic@cs.cmu.edu)提出了一种 faster RCNN 检测框架的 Tensorflow 实现。这个项目基于 python Caffe 实现faster RCNN 在这里可用。

项目地址:https://github.com/endernewton/tf-faster-rcnn

注意:在重新实现框架时,进行了一些细微的修改,从而提供了潜在的改进。有关修改和分析的详细信息,请参见技术报告“An Implementation of Faster RCNN with Study for Region Sampling”。如果您正在寻求在原始文件中重现结果,请使用官方代码或者是半官方代码。有关 Faster RCNN 架构的详细信息,请参阅文章 Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks https://arxiv.org/pdf/1506.01497.pdf。

检测性能

目前的代码支持VGG16,Resnet V1和Mobilenet V1型号。我们主要测试它在普通VGG16和Resnet101(谢谢@philokey!)架构。作为基线,我们在单个卷积层上使用单个模型报告数字,因此没有多尺度,无多阶段边界框回归,无跳过连接,不使用额外的输入。唯一的数据增强技术是在原始更快的RCNN之后的训练期间左右翻转。所有型号均已发布。

tf-faster-rcnn

A Tensorflow implementation of faster RCNN detection framework by Xinlei Chen (xinleic@cs.cmu.edu). This repository is based on the python Caffe implementation of faster RCNN available here.

Note: Several minor modifications are made when reimplementing the framework, which give potential improvements. For details about the modifications and ablative analysis, please refer to the technical report An Implementation of Faster RCNN with Study for Region Sampling. If you are seeking to reproduce the results in the original paper, please use the official code or maybe the semi-official code. For details about the faster RCNN architecture please refer to the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

Detection Performance

The current code supports VGG16, Resnet V1 and Mobilenet V1 models. We mainly tested it on plain VGG16 and Resnet101 (thank you @philokey!) architecture. As the baseline, we report numbers using a single model on a single convolution layer, so no multi-scale, no multi-stage bounding box regression, no skip-connection, no extra input is used. The only data augmentation technique is left-right flipping during training following the original Faster RCNN. All models are released.

Be the first to comment

Leave a Reply

Your email address will not be published.