Code Monkey home page Code Monkey logo

tensorflow-yolov1's Introduction

tensorflow YOLO-v1

  • this is a study project, which is not exactly the same as the original paper in the Network structure,we use vgg16 achieve 65.34% map in the voc2007test.

  • The purpose that I write the yolov1 to study,and it achieve a good performance.

Train on voc2007+2012

model map@voc2007test
VGG16 65.34%
VGG19 66.12%
Resnet50 65.23%

1.requirement

  • opencv
  • tensorflow 1.8
  • numpy

2.prepare dataset

  1. download voc2007 and voc2012 dataset

  2. unzip dataset as following

    • VOCdevkit
      • VOC2007
        • Annotations
        • ImageSets
        • JPEGImages
        • SegmentationClass
        • SegmentationObject
      • VOC2012

  3. python proprecess_pasval_voc.py

3.training

python train.py \\  
	--net {Vgg16||Vgg19||resnet50}
	--gpu 0

4.predict and eval

python predict --net {Vgg16||Vgg19||resnet50}
python eval.py

result

tensorflow-yolov1's People

Contributors

yxlijun avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.