作者:piao lin
链接:https://www.zhihu.com/question/53991536/answer/137494872
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。
《 DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks forLarge-Scale Unconstrained Handwritten Chinese Character Recognition》
《High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps》
《Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification》
《Multi-font printed Chinese character recognition using multi-pooling convolutional neural network》
《Drawing and Recognizing Chinese Characters with Recurrent Neural Network 》(在线手写汉字识别的)
链接:https://www.zhihu.com/question/53991536/answer/137494872
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。
手写体汉字识别
chongyangtao/DeepHCCR
zhongzhuoyao/HCCR-GoogLeNet
打印体汉字识别
JinpengLI/deep_ocr
《 DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks forLarge-Scale Unconstrained Handwritten Chinese Character Recognition》
《High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps》
《Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification》
《Multi-font printed Chinese character recognition using multi-pooling convolutional neural network》
《Drawing and Recognizing Chinese Characters with Recurrent Neural Network 》(在线手写汉字识别的)
谢邀。CS231N之前有一个 course report,地址是:
http://cs231n.stanford.edu/reports/2016/pdfs/428_Report.pdf
我自己也训过一个类似的东西,在这里(是在 机器学习进阶笔记之八 | TensorFlow与中文手写汉字识别 - 知乎专栏 的基础上改的):
soloice/Chinese-Character-Recognition
(不过讲道理,这个训练集上噪声加的有点过了,而且模型没有完全收敛,因为当时我还没有显卡……过段时间可以再调调网络结构重训一个~)
作者:七月
链接:https://www.zhihu.com/question/53991536/answer/158000463
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。