TensorFlow-HandWritten-

上传者: 42131541 | 上传时间: 2022-07-18 20:32:31 | 文件大小: 18.17MB | 文件类型: ZIP
使用TensorFlow进行手写文本识别 使用TensorFlow(TF)实现并在IAM离线HTR数据集上接受训练的手写文本识别(HTR)系统。 这种神经网络(NN)模型可以识别分段词图像中包含的文本,如下图所示。 由于这些单词图像小于完整文本行的图像,因此可以将NN保持较小,并且在CPU上进行训练是可行的。 正确识别了验证集中的3/4个单词,字符错误率约为10%。 如果您需要更大的输入图像(例如,识别文本行)或想要更好的识别精度,我将给出一些提示,以扩展模型。 运行演示 转到model/目录并解压缩model.zip文件(已在IAM数据集上进行了预训练)。 请注意,将解压缩的文件直接放置在model/目录中,而不要放置在解压缩程序创建的某些子目录中。 然后,转到src/目录并运行python main.py 输入图像和预期输出如下所示。 > python main.py Validat

文件下载

资源详情

[{"title":"( 26 个子文件 18.17MB ) TensorFlow-HandWritten-","children":[{"title":"TensorFlow-HandWritten--master","children":[{"title":"data","children":[{"title":"checkDirs.py <span style='color:#111;'> 325B </span>","children":null,"spread":false},{"title":"translationInvarianceTexts.pickle <span style='color:#111;'> 294B </span>","children":null,"spread":false},{"title":"translationInvariance.npy <span style='color:#111;'> 192B </span>","children":null,"spread":false},{"title":"corpus.txt <span style='color:#111;'> 577.12KB </span>","children":null,"spread":false},{"title":"analyze.png <span style='color:#111;'> 4.27KB </span>","children":null,"spread":false},{"title":"Get IAM training data.txt <span style='color:#111;'> 488B </span>","children":null,"spread":false},{"title":"test.png <span style='color:#111;'> 8.87KB </span>","children":null,"spread":false},{"title":"pixelRelevance.npy <span style='color:#111;'> 12.70KB </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"accuracy.txt <span style='color:#111;'> 58B </span>","children":null,"spread":false},{"title":"model.zip <span style='color:#111;'> 17.67MB </span>","children":null,"spread":false},{"title":"wordCharList.txt <span style='color:#111;'> 54B </span>","children":null,"spread":false},{"title":"charList.txt <span style='color:#111;'> 79B </span>","children":null,"spread":false}],"spread":true},{"title":"src","children":[{"title":"main.py <span style='color:#111;'> 4.70KB </span>","children":null,"spread":false},{"title":"Model.py <span style='color:#111;'> 9.85KB </span>","children":null,"spread":false},{"title":"analyze.py <span style='color:#111;'> 4.68KB </span>","children":null,"spread":false},{"title":"DataLoader.py <span style='color:#111;'> 4.17KB </span>","children":null,"spread":false},{"title":"SamplePreprocessor.py <span style='color:#111;'> 1.25KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 295B </span>","children":null,"spread":false},{"title":"doc","children":[{"title":"nn_overview.png <span style='color:#111;'> 63.48KB </span>","children":null,"spread":false},{"title":"decoder_comparison.png <span style='color:#111;'> 30.76KB </span>","children":null,"spread":false},{"title":"analyze.png <span style='color:#111;'> 61.47KB </span>","children":null,"spread":false},{"title":"graphics.svg <span style='color:#111;'> 179.72KB </span>","children":null,"spread":false},{"title":"htr.png <span style='color:#111;'> 11.64KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE.md <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 108B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 12.49KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明