Giter Club home page Giter Club logo

r-cnn's Introduction

R-CNN

Documentation Status standard-readme compliant Conventional Commits Commitizen friendly

R-CNN算法实现

学习论文Rich feature hierarchies for accurate object detection and semantic segmentation,实现R-CNN算法,完成目标检测器的训练和使用

R-CNN实现由如下3部分组成:

  1. 区域建议算法(SelectiveSearch
  2. 卷积网络模型(AlexNet
  3. 线性分类器(线性SVM

区域建议算法使用OpenCV实现,进一步学习可参考zjZSTU/selectivesearch

内容列表

背景

R-CNN(Region-CNN)是最早实现的深度学习检测算法,其结合了选择性搜索算法和卷积神经网络。复现R-CNN算法,也有利于后续算法的研究和学习

安装

本地编译文档

需要预先安装以下工具:

$ pip install mkdocs

用法

文档浏览

有两种使用方式

  1. 在线浏览文档:R-CNN

  2. 本地浏览文档,实现如下:

    $ git clone https://github.com/zjZSTU/R-CNN.git
    $ cd R-CNN
    $ mkdocs serve
    

    启动本地服务器后即可登录浏览器localhost:8000

python实现

$ cd py/
$ python car_detector.py

主要维护人员

  • zhujian - Initial work - zjZSTU

致谢

引用

@misc{girshick2013rich,
    title={Rich feature hierarchies for accurate object detection and semantic segmentation},
    author={Ross Girshick and Jeff Donahue and Trevor Darrell and Jitendra Malik},
    year={2013},
    eprint={1311.2524},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@misc{pascal-voc-2007,
	author = "Everingham, M. and Van~Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.",
	title = "The {PASCAL} {V}isual {O}bject {C}lasses {C}hallenge 2007 {(VOC2007)} {R}esults",
	howpublished = "http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html"}

参与贡献方式

欢迎任何人的参与!打开issue或提交合并请求。

注意:

许可证

Apache License 2.0 © 2020 zjZSTU

r-cnn's People

Contributors

zjzstu avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

r-cnn's Issues

files miss

sorry,where are the files “data”&“module”?

Confused Selectivesearch

I am so freaking confused with the "selective.py".Now that you import the official selective module,why did you create a new module names "selective.py" which is happened to have the same name with the offiicial one instead of just using it.What you did just cause so many trouble to me and I am so confused.Is there anything I don't figure out?

a small problem in code

image

I think there is something wrong with the code I marked. I don't know whether it is your negligence or my understanding

a problem in linear_svm.py

Epoch 0/9

train - positive_num: 66 - negative_num: 66 - data size: 128
Traceback (most recent call last):
File "linear_svm.py", line 274, in
best_model = train_model(data_loaders, model, criterion, optimizer, lr_schduler, num_epochs=10, device=device)
File "linear_svm.py", line 150, in train_model
for inputs, labels, cache_dicts in data_loaders[phase]:
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 435, in iter
return self._get_iterator()
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 381, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1072, in init
self._reset(loader, first_iter=True)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1105, in _reset
self._try_put_index()
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1339, in _try_put_index
index = self._next_index()
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 618, in _next_index
return next(self._sampler_iter) # may raise StopIteration
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/sampler.py", line 244, in iter
sampler_iter = iter(self.sampler)
File "/content/drive/MyDrive/R-CNN/py/utils/data/custom_batch_sampler.py", line 45, in iter
random.sample(self.idx_list[self.num_positive:], self.batch_negative))
File "/usr/lib/python3.8/random.py", line 363, in sample
raise ValueError("Sample larger than population or is negative")
ValueError: Sample larger than population or is negative

how to solve it ?

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.