天池大赛医学影像报告检测初赛26名代码分享(脱敏文本多标签分类)

上传者: 54707168 | 上传时间: 2021-07-04 17:03:36 | 文件大小: 5.92MB | 文件类型: ZIP
天池大赛医学影像报告检测初赛26名代码分享(脱敏文本多标签分类) 介绍 数据:标签制作为one-hot形式,例如[3,4,6]就转为[0,0,0,1,1,0,1,…0]模型:采用nezha_large采用n-gram嵌入(具体见代码) 训练:将训练集,测试集放一起,构建独立词表,进行传销无监督训练,属于脱敏文字的预训练模型,然后再在训练集上微调采用对抗训练(FGM)10折交叉验证 运行 Transformers==4.3.2 torch==1.7.1 main_nezha_pretrain.py是传销训练的代码,先运行这个得到预训练模型下载:网盘然后再在预训练模型上有监督训练(微调)运行main_nezha_kfold.py数据中,pretrain.tsv 是训练测试集的合并

文件下载

资源详情

[{"title":"( 53 个子文件 5.92MB ) 天池大赛医学影像报告检测初赛26名代码分享(脱敏文本多标签分类)","children":[{"title":"tainchi_match-main","children":[{"title":"main_nezha_pretrain.py <span style='color:#111;'> 8.75KB </span>","children":null,"spread":false},{"title":"track1_data","children":[{"title":"valid_fold_8.tsv <span style='color:#111;'> 172.72KB </span>","children":null,"spread":false},{"title":"valid_fold_1.tsv <span style='color:#111;'> 173.82KB </span>","children":null,"spread":false},{"title":"valid_fold_5.tsv <span style='color:#111;'> 173.87KB </span>","children":null,"spread":false},{"title":"valid_fold_4.tsv <span style='color:#111;'> 172.96KB </span>","children":null,"spread":false},{"title":"valid_fold_6.tsv <span style='color:#111;'> 171.25KB </span>","children":null,"spread":false},{"title":"train_fold_8.tsv <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"valid_fold_9.tsv <span style='color:#111;'> 167.37KB </span>","children":null,"spread":false},{"title":"valid_fold_3.tsv <span style='color:#111;'> 173.76KB </span>","children":null,"spread":false},{"title":"train_fold_3.tsv <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"track1_round1_train_20210222.csv <span style='color:#111;'> 1.69MB </span>","children":null,"spread":false},{"title":"train_fold_1.tsv <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"train_fold_2.tsv <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"train_fold_5.tsv <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"train_fold_0.tsv <span style='color:#111;'> 1.52MB </span>","children":null,"spread":false},{"title":"train_fold_9.tsv <span style='color:#111;'> 1.52MB </span>","children":null,"spread":false},{"title":"train_fold_7.tsv <span style='color:#111;'> 1.52MB </span>","children":null,"spread":false},{"title":"valid_fold_7.tsv <span style='color:#111;'> 170.39KB </span>","children":null,"spread":false},{"title":"train_fold_6.tsv <span style='color:#111;'> 1.52MB </span>","children":null,"spread":false},{"title":"valid_fold_2.tsv <span style='color:#111;'> 174.89KB </span>","children":null,"spread":false},{"title":"valid_fold_0.tsv <span style='color:#111;'> 171.84KB </span>","children":null,"spread":false},{"title":"track1_round1_testB.csv <span style='color:#111;'> 491.32KB </span>","children":null,"spread":false},{"title":"track1_round1_testA_20210222.csv <span style='color:#111;'> 487.44KB </span>","children":null,"spread":false},{"title":"train_fold_4.tsv <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"pretrain.tsv <span style='color:#111;'> 2.17MB </span>","children":null,"spread":false}],"spread":false},{"title":"pretrain","children":[{"title":"nezha_config.json <span style='color:#111;'> 375B </span>","children":null,"spread":false}],"spread":true},{"title":"Lookahead","children":[{"title":"run.py <span style='color:#111;'> 4.03KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"png","children":[{"title":"valid_acc.png <span style='color:#111;'> 28.12KB </span>","children":null,"spread":false},{"title":"loss.png <span style='color:#111;'> 30.50KB </span>","children":null,"spread":false},{"title":"valid_loss.png <span style='color:#111;'> 27.02KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 1.37KB </span>","children":null,"spread":false},{"title":"trainingmonitor.py <span style='color:#111;'> 2.35KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"optimizer.cpython-38.pyc <span style='color:#111;'> 3.55KB </span>","children":null,"spread":false}],"spread":true},{"title":"nn.py <span style='color:#111;'> 2.31KB </span>","children":null,"spread":false},{"title":"optimizer.py <span style='color:#111;'> 4.13KB </span>","children":null,"spread":false},{"title":"tools.py <span style='color:#111;'> 1.89KB </span>","children":null,"spread":false},{"title":"progressbar.py <span style='color:#111;'> 2.03KB </span>","children":null,"spread":false}],"spread":true},{"title":"main_nezha_kfold.py <span style='color:#111;'> 12.15KB </span>","children":null,"spread":false},{"title":"NeZha","children":[{"title":"convert_nezha_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.39KB </span>","children":null,"spread":false},{"title":"outputs","children":[{"title":"__init__.py <span style='color:#111;'> 2B </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"configuration_nezha.py <span style='color:#111;'> 6.17KB </span>","children":null,"spread":false},{"title":"modeling_nezha.py <span style='color:#111;'> 59.55KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"configuration_nezha.cpython-38.pyc <span style='color:#111;'> 5.77KB </span>","children":null,"spread":false},{"title":"modeling_nezha.cpython-38.pyc <span style='color:#111;'> 43.57KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"dataset","children":[{"title":"__init__.py <span style='color:#111;'> 10B </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"scripts","children":[{"title":"run_task_text_classification_chnsenti.sh <span style='color:#111;'> 748B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 1.60KB </span>","children":null,"spread":false},{"title":"task_text_classification_chnsenti.py <span style='color:#111;'> 4.66KB </span>","children":null,"spread":false},{"title":"pretrained_models","children":[{"title":"__init__.py <span style='color:#111;'> 2B </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 774B </span>","children":null,"spread":false},{"title":"attacks.py <span style='color:#111;'> 2.61KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

  • ZZH123456ZZZ :
    用户下载后在一定时间内未进行评价,系统默认好评。
    2021-11-06

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