Python实现基于ClipCap的看图说话Image Caption模型.zip
资源包含文件：设计报告word+源码及数据
Image Caption即我们常说的看图说话：给定一张图片，生成该图片对应的自然语言描述。 该任务涉及到了图像与自然语言两个模态，然而图像空间与自然语言空间本就十分庞大，并且两者之间存在巨大的语义鸿沟。 如何将两个庞大的语义空间进行对齐，这是该任务的重点。本项目对ClipCap: CLIP Prefix for Image Captioning 论文进行介绍，并且对论文在Flickr30k中文数据集上进行实验复现和效果展示。
详细介绍参考：https://biyezuopin.blog.csdn.net/article/details/125617468
文件下载
资源详情
[{"title":"（ 54 个子文件 5.62MB ） Python实现基于ClipCap的看图说话Image Caption模型.zip","children":[{"title":"设计报告.docx <span style='color:#111;'> 1.26MB </span>","children":null,"spread":false},{"title":"models","children":[{"title":"model.py <span style='color:#111;'> 5.06KB </span>","children":null,"spread":false}],"spread":true},{"title":"images","children":[{"title":"mlp.jpg <span style='color:#111;'> 71.81KB </span>","children":null,"spread":false},{"title":"transformer.jpg <span style='color:#111;'> 98.32KB </span>","children":null,"spread":false},{"title":"loss.jpg <span style='color:#111;'> 222.00KB </span>","children":null,"spread":false},{"title":"caption_distribution.jpg <span style='color:#111;'> 28.25KB </span>","children":null,"spread":false},{"title":"overview.jpg <span style='color:#111;'> 147.50KB </span>","children":null,"spread":false}],"spread":true},{"title":"statistics.py <span style='color:#111;'> 1.12KB </span>","children":null,"spread":false},{"title":"pretrain_models","children":[{"title":"gpt2","children":[{"title":"vocab.txt <span style='color:#111;'> 106.97KB </span>","children":null,"spread":false},{"title":"config.json <span style='color:#111;'> 577B </span>","children":null,"spread":false}],"spread":true},{"title":"bert","children":[{"title":"vocab.txt <span style='color:#111;'> 106.97KB </span>","children":null,"spread":false},{"title":"tokenizer.json <span style='color:#111;'> 262.64KB </span>","children":null,"spread":false},{"title":"config.json <span style='color:#111;'> 622B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"train.py <span style='color:#111;'> 6.54KB </span>","children":null,"spread":false},{"title":"predict.py <span style='color:#111;'> 7.69KB </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 3.80KB </span>","children":null,"spread":false},{"title":"output","children":[{"title":"test","children":[{"title":"caption_generate_finetune.txt <span style='color:#111;'> 9.08KB </span>","children":null,"spread":false},{"title":"caption_generate_no_finetune.txt <span style='color:#111;'> 9.11KB </span>","children":null,"spread":false}],"spread":true},{"title":"mlp_finetune_gpt2","children":[{"title":"events.out.tfevents.1647762890.982e5fd2-217a-4002-9edc-eb66e13cb88d.79186.0 <span style='color:#111;'> 13.76KB </span>","children":null,"spread":false}],"spread":true},{"title":"dev","children":[{"title":"caption_generate_finetune.txt <span style='color:#111;'> 2.99KB </span>","children":null,"spread":false},{"title":"caption_generate_no_finetune.txt <span style='color:#111;'> 3.02KB </span>","children":null,"spread":false}],"spread":true},{"title":"bert_no_finetune_gpt2","children":[{"title":"events.out.tfevents.1647763019.982e5fd2-217a-4002-9edc-eb66e13cb88d.79422.0 <span style='color:#111;'> 14.27KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"process_caption.py <span style='color:#111;'> 1019B </span>","children":null,"spread":false},{"title":"process_flickr.py <span style='color:#111;'> 1.80KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 117B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 15.95KB </span>","children":null,"spread":false},{"title":"scripts","children":[{"title":"predict_no_finerune_gpt2.sh <span style='color:#111;'> 495B </span>","children":null,"spread":false},{"title":"train_finetune_gpt2.sh <span style='color:#111;'> 492B </span>","children":null,"spread":false},{"title":"train_no_finetune_gpt2.sh <span style='color:#111;'> 474B </span>","children":null,"spread":false},{"title":"predict_finerune_gpt2.sh <span style='color:#111;'> 511B </span>","children":null,"spread":false}],"spread":false},{"title":"datasets","children":[{"title":"test","children":[{"title":"50292297228_5c260d7dd9_b.jpg <span style='color:#111;'> 34.71KB </span>","children":null,"spread":false},{"title":"global-card-lego.png <span style='color:#111;'> 68.19KB </span>","children":null,"spread":false},{"title":"51249416246_26e7bcee71_b.jpg <span style='color:#111;'> 32.71KB </span>","children":null,"spread":false},{"title":"51324931128_0a4e482944_b.jpg <span style='color:#111;'> 16.77KB </span>","children":null,"spread":false},{"title":"4930864108_cd9fcb7a57_b.jpg <span style='color:#111;'> 26.48KB </span>","children":null,"spread":false},{"title":"51645058861_254767cde0_b.jpg <span style='color:#111;'> 26.31KB </span>","children":null,"spread":false},{"title":"25392547463_615de3cb70_b.jpg <span style='color:#111;'> 26.47KB </span>","children":null,"spread":false},{"title":"25167669554_839ac583a6_b.jpg <span style='color:#111;'> 23.82KB </span>","children":null,"spread":false},{"title":"48690120836_4824a12e6d_b.jpg <span style='color:#111;'> 27.92KB </span>","children":null,"spread":false},{"title":"51259608793_5bdda24605_b.jpg <span style='color:#111;'> 27.89KB </span>","children":null,"spread":false},{"title":"51220776286_cba3991787_b.jpg <span style='color:#111;'> 17.68KB </span>","children":null,"spread":false},{"title":"50825859087_29f3edbd7e_b.jpg <span style='color:#111;'> 30.30KB </span>","children":null,"spread":false},{"title":"50779458317_d4e1fc51a8_b.jpg <span style='color:#111;'> 41.18KB </span>","children":null,"spread":false},{"title":"46442548385_dc00b31170_b.jpg <span style='color:#111;'> 36.36KB </span>","children":null,"spread":false},{"title":"50334773578_d5c84ed71d_b.jpg <span style='color:#111;'> 52.38KB </span>","children":null,"spread":false},{"title":"631407374_db533106dd_b.jpg <span style='color:#111;'> 42.53KB </span>","children":null,"spread":false}],"spread":false},{"title":"dev","children":[{"title":"371902.jpg <span style='color:#111;'> 51.21KB </span>","children":null,"spread":false},{"title":"256063.jpg <span style='color:#111;'> 57.22KB </span>","children":null,"spread":false},{"title":"371897.jpg <span style='color:#111;'> 68.11KB </span>","children":null,"spread":false},{"title":"301246.jpg <span style='color:#111;'> 56.00KB </span>","children":null,"spread":false},{"title":"353913.jpg <span style='color:#111;'> 58.82KB </span>","children":null,"spread":false},{"title":"27860802.jpg <span style='color:#111;'> 136.88KB </span>","children":null,"spread":false}],"spread":false},{"title":"flickr_caption.txt <span style='color:#111;'> 10.09MB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- 修改后的KinectWrapper
- IEEE 802.3标准全文下载
- 半导体材料测试与分析
- 对无线传感器网络(WSN)中参考广播同步算法(RBS)的模拟仿真
- 基于matlab的图形编辑器
- 图像傅里叶变换简单代码实现
- Android 应用完整源码 客户端+服务端+数据库
- EC20_4g模块硬件开发手册
- js生成二维码
- 光学4F系统仿真代码
- wxappUnpacker-master（qwerty472123版）
- VMware-VMRC-11.1.0-15913118
- C#网络应用高级编程（PDF+案例源码+习题解答）
- C#Winform酒店管理系统
- AVR ATMEGA16 SPI双机通信的PROTEUS仿真 （双向）（反馈）
- 答题场景ppt制作.ppt
- Tiny框架图片压缩集成
- net版本Itextsharp根据模板导出pdf报表__0525.rar
- flink-shaded-hadoop-2-uber-2.6.0-cdh5.13.3-7.0.jar
- libjpeg-turbo-1.2.1.tar.gz
- 网龙页编笔试题
- 校园商品交易系统
- pagehelper-3.4.2-fix（jar包完整版）
- 114页5G+AI报告：5G元年，电子行业迎来新时代-2019年01月14日
- Automotive Software Engineering Principles, Processes
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