BERTem：论文实现（ACL2019）：《填补空白：关系学习的分布相似性》
实现说明
主要实现文章前半部分的工作，PyTorch实现，基于的工作，PyTorch才是世界上最屌的框架，逃脱。
实现参考
代码说明
（1）主要修改：
输出表示形式： BertForSequenceClassification
输入表示形式： BertEmbeddings
输入和输出都实现了多种策略，可以结合具体的任务，找到最佳的组合。
（2）非主要实现：examples下的关于classification的文件
（3）服务部署：基于Flask，可以在本地开启一个服务。具体实现在中。
（4）代码正确参考，不提供数据集，不提供预训练模型，不提供训练后的模型（希望理解吧）。
（5）相
文件下载
资源详情
[{"title":"（ 70 个子文件 363KB ） BERTem：论文实现（ACL2019）：《填补空白：关系学习的分布相似性》","children":[{"title":"BERTem-master","children":[{"title":"README.md <span style='color:#111;'> 2.56KB </span>","children":null,"spread":false},{"title":"hubconf.py <span style='color:#111;'> 723B </span>","children":null,"spread":false},{"title":"tests","children":[{"title":"conftest.py <span style='color:#111;'> 511B </span>","children":null,"spread":false},{"title":"modeling_gpt2_test.py <span style='color:#111;'> 16.38KB </span>","children":null,"spread":false},{"title":"modeling_test.py <span style='color:#111;'> 22.79KB </span>","children":null,"spread":false},{"title":"modeling_openai_test.py <span style='color:#111;'> 15.05KB </span>","children":null,"spread":false},{"title":"tokenization_test.py <span style='color:#111;'> 4.97KB </span>","children":null,"spread":false},{"title":"tokenization_gpt2_test.py <span style='color:#111;'> 3.05KB </span>","children":null,"spread":false},{"title":"optimization_test.py <span style='color:#111;'> 3.83KB </span>","children":null,"spread":false},{"title":"tokenization_transfo_xl_test.py <span style='color:#111;'> 2.93KB </span>","children":null,"spread":false},{"title":"modeling_transfo_xl_test.py <span style='color:#111;'> 9.25KB </span>","children":null,"spread":false},{"title":"tokenization_openai_test.py <span style='color:#111;'> 3.15KB </span>","children":null,"spread":false}],"spread":true},{"title":"docs","children":[{"title":"imgs","children":[{"title":"warmup_cosine_warm_restarts_schedule.png <span style='color:#111;'> 21.79KB </span>","children":null,"spread":false},{"title":"warmup_linear_schedule.png <span style='color:#111;'> 16.38KB </span>","children":null,"spread":false},{"title":"warmup_cosine_schedule.png <span style='color:#111;'> 16.93KB </span>","children":null,"spread":false},{"title":"warmup_cosine_hard_restarts_schedule.png <span style='color:#111;'> 21.83KB </span>","children":null,"spread":false},{"title":"warmup_constant_schedule.png <span style='color:#111;'> 9.74KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"examples","children":[{"title":"train.sh <span style='color:#111;'> 461B </span>","children":null,"spread":false},{"title":"tacred_run_infer.py <span style='color:#111;'> 23.18KB </span>","children":null,"spread":false},{"title":"run_swag.py <span style='color:#111;'> 23.75KB </span>","children":null,"spread":false},{"title":"run_transfo_xl.py <span style='color:#111;'> 6.58KB </span>","children":null,"spread":false},{"title":"bertology.py <span style='color:#111;'> 16.75KB </span>","children":null,"spread":false},{"title":"run_squad.py <span style='color:#111;'> 21.29KB </span>","children":null,"spread":false},{"title":"run_gpt2.py <span style='color:#111;'> 5.10KB </span>","children":null,"spread":false},{"title":"run_squad_dataset_utils.py <span style='color:#111;'> 30.25KB </span>","children":null,"spread":false},{"title":"test.sh <span style='color:#111;'> 492B </span>","children":null,"spread":false},{"title":"lm_finetuning","children":[{"title":"simple_lm_finetuning.py <span style='color:#111;'> 27.72KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 6.06KB </span>","children":null,"spread":false},{"title":"pregenerate_training_data.py <span style='color:#111;'> 15.89KB </span>","children":null,"spread":false},{"title":"finetune_on_pregenerated.py <span style='color:#111;'> 16.07KB </span>","children":null,"spread":false}],"spread":false},{"title":"run_classifier_dataset_utils.py <span style='color:#111;'> 19.32KB </span>","children":null,"spread":false},{"title":"tacred_run_classifier.py <span style='color:#111;'> 49.72KB </span>","children":null,"spread":false},{"title":"run_classifier.py <span style='color:#111;'> 49.96KB </span>","children":null,"spread":false},{"title":"run_openai_gpt.py <span style='color:#111;'> 13.33KB </span>","children":null,"spread":false},{"title":"extract_features.py <span style='color:#111;'> 11.92KB </span>","children":null,"spread":false},{"title":"sem_run_classifier.py <span style='color:#111;'> 49.96KB </span>","children":null,"spread":false}],"spread":false},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"docker","children":[{"title":"Dockerfile <span style='color:#111;'> 197B </span>","children":null,"spread":false}],"spread":true},{"title":"pytorch_pretrained_bert","children":[{"title":"convert_openai_checkpoint_to_pytorch.py <span style='color:#111;'> 3.03KB </span>","children":null,"spread":false},{"title":"convert_gpt2_checkpoint_to_pytorch.py <span style='color:#111;'> 2.95KB </span>","children":null,"spread":false},{"title":"tokenization.py <span style='color:#111;'> 17.79KB </span>","children":null,"spread":false},{"title":"convert_pytorch_checkpoint_to_tf.py <span style='color:#111;'> 4.24KB </span>","children":null,"spread":false},{"title":"modeling_gpt2.py <span style='color:#111;'> 44.54KB </span>","children":null,"spread":false},{"title":"convert_transfo_xl_checkpoint_to_pytorch.py <span style='color:#111;'> 5.54KB </span>","children":null,"spread":false},{"title":"optimization.py <span style='color:#111;'> 12.74KB </span>","children":null,"spread":false},{"title":"tokenization_gpt2.py <span style='color:#111;'> 13.85KB </span>","children":null,"spread":false},{"title":"optimization_openai.py <span style='color:#111;'> 5.43KB </span>","children":null,"spread":false},{"title":"modeling_openai.py <span style='color:#111;'> 45.37KB </span>","children":null,"spread":false},{"title":"modeling_transfo_xl.py <span style='color:#111;'> 58.67KB </span>","children":null,"spread":false},{"title":"convert_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.53KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false},{"title":"__main__.py <span style='color:#111;'> 4.29KB </span>","children":null,"spread":false},{"title":"tokenization_transfo_xl.py <span style='color:#111;'> 21.82KB </span>","children":null,"spread":false},{"title":"file_utils.py <span style='color:#111;'> 9.13KB </span>","children":null,"spread":false},{"title":"tokenization_openai.py <span style='color:#111;'> 13.87KB </span>","children":null,"spread":false},{"title":"modeling.py <span style='color:#111;'> 64.98KB </span>","children":null,"spread":false},{"title":"modeling_transfo_xl_utilities.py <span style='color:#111;'> 15.73KB </span>","children":null,"spread":false}],"spread":false},{"title":"requirements.txt <span style='color:#111;'> 196B </span>","children":null,"spread":false},{"title":"MANIFEST.in <span style='color:#111;'> 16B </span>","children":null,"spread":false},{"title":"notebooks","children":[{"title":"Comparing-TF-and-PT-models-MLM-NSP.ipynb <span style='color:#111;'> 169.10KB </span>","children":null,"spread":false},{"title":"Comparing-TF-and-PT-models-SQuAD.ipynb <span style='color:#111;'> 202.69KB </span>","children":null,"spread":false},{"title":"Comparing-PT-and-TF-models.ipynb <span style='color:#111;'> 90.12KB </span>","children":null,"spread":false},{"title":"Comparing-TF-and-PT-models.ipynb <span style='color:#111;'> 61.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"setup.py <span style='color:#111;'> 2.73KB </span>","children":null,"spread":false},{"title":"samples","children":[{"title":"input.txt <span style='color:#111;'> 52B </span>","children":null,"spread":false},{"title":"sample_text.txt <span style='color:#111;'> 4.29KB </span>","children":null,"spread":false}],"spread":true},{"title":"hubconfs","children":[{"title":"gpt_hubconf.py <span style='color:#111;'> 8.09KB </span>","children":null,"spread":false},{"title":"bert_hubconf.py <span style='color:#111;'> 16.90KB </span>","children":null,"spread":false},{"title":"gpt2_hubconf.py <span style='color:#111;'> 6.89KB </span>","children":null,"spread":false},{"title":"transformer_xl_hubconf.py <span style='color:#111;'> 5.72KB </span>","children":null,"spread":false}],"spread":true}],"spread":false}],"spread":true}]
评论信息
其他资源
- java点餐系统
- 光线追踪OBJ模型VC源代码
- 1688分类ID，类目列表，详情准确，类目大全 2018年数据
- verilog 实现串口通信 含fifo,很好用！
- 线性调频信号的matlab代码
- 中国地标山峰
- 用labview基于pc声卡进行采集音频型号，之后进行相应的处理
- multisim字发生器
- network information theory讲义
- 数学建模艾滋病的分析MATHEMATICA编程
- 基于arm cortex M3 的LED控制源代码
- 基于FPGA的单周期处理器设计MIPS指令集
- NPOI 1.2.5
- web常用组件+后台管理系统框架模板+大屏数据可视化+智慧社区管理系统大屏+图表组件+表单组合+智慧数据看板+通用大屏图表+后台管理常用组件.zip
- 鸿言人脉管理 v6.2.zip
- ECSHOP商品页按地区显示运费插件 仿淘宝运费带自动获取访客位置
- PsAndroidAdaptiveIcon：对Android的自适应图标支持。 要求的API级别26-源码
- httpclient需要的jar包，合订版（httclient.jar,commons-codec,commons-logging）
- 微软百科全书 DVD 一共4个包 L09AXLRD1.part1.rar
- TGS2600Datasheet
- 最新搜狗输入法词库大全2015
- US无线充电专利US7863861B2
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
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