CLIP_inChinese-源码
多语言CLIP
适用于任何语言的OpenAI CLIP文本编码器
··
概述
最近发布了一篇论文，《中 ，其中介绍了CLIP（对比语言-图像预训练）模型。 使用对比学习目标，通过匹配文本和图像的相应矢量表示，训练该模型以使其连接文本和图像。 CLIP由两个单独的模型组成，一个视觉编码器和一个文本编码器。 这些内容接受了高达4亿张的图像和相应的字幕的培训。 此后，OpenAI发布了一组较小的CLIP模型，可以在上找到它们。
我们建议进行微调，以使用任何语言的预训练文本模型替换原始英语文本编码器。 这种方法可以使强大的CLIP模型在大约24个GPU小时内适应任何语言。
该存储库包含
pytorch推断代码
Tensorflow培训代码
预训练的CLIP-Text编码器可支持多种语言
训练数据和预先计算的CLIP文本编码，用于 + MSCOCO + VizWiz图像标题的很大一部分
要求
文件下载
资源详情
[{"title":"（ 58 个子文件 81.95MB ） CLIP_inChinese-源码","children":[{"title":"CLIP_inChinese-master","children":[{"title":"inference.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"CLIP","children":[{"title":"matched_train2014.txt <span style='color:#111;'> 380.35KB </span>","children":null,"spread":false},{"title":"database.json <span style='color:#111;'> 96.61MB </span>","children":null,"spread":false},{"title":"prepare.py <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 148B </span>","children":null,"spread":false},{"title":"database.txt <span style='color:#111;'> 96.36MB </span>","children":null,"spread":false},{"title":"zero_shot_prediction.py <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 1.26KB </span>","children":null,"spread":false},{"title":"aa.txt <span style='color:#111;'> 2.76MB </span>","children":null,"spread":false},{"title":"main.py <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":".database.json.swp <span style='color:#111;'> 8.00KB </span>","children":null,"spread":false},{"title":"matched_total.txt <span style='color:#111;'> 1.13MB </span>","children":null,"spread":false}],"spread":false},{"title":"Multilingual_CLIP.ipynb <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"src","children":[{"title":"multilingual_clip.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"TeacherLearning","children":[{"title":"Training.py <span style='color:#111;'> 5.89KB </span>","children":null,"spread":false},{"title":"Utils.py <span style='color:#111;'> 298B </span>","children":null,"spread":false},{"title":"extracted_data.pkl <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"TrainingModel.cpython-36.pyc <span style='color:#111;'> 2.25KB </span>","children":null,"spread":false}],"spread":true},{"title":"evaluate.py <span style='color:#111;'> 174B </span>","children":null,"spread":false},{"title":"TrainingModel.py <span style='color:#111;'> 1.58KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"multilingual_clip.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"extracted_data.pkl <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"weights","children":[{"title":"cp.ckpt.data-00000-of-00001 <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"cp.ckpt.index <span style='color:#111;'> 22.18KB </span>","children":null,"spread":false},{"title":"checkpoint <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"CLIP-Text-Encoder-200-Weights.data-00000-of-00001 <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"Model Cards","children":[{"title":"M-BERT Distil 40","children":[{"title":"Images","children":[{"title":"French-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"M-Swedish-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Spanish-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Kannada-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"German-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Russian-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Greek-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Fine-Tune-Languages.md <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"Swe-CLIP 500k","children":[{"title":"README.md <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"M-BERT Base 69","children":[{"title":"Images","children":[{"title":"French-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"M-Swedish-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Spanish-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Kannada-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"German-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Russian-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Greek-Both.png <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"Fine-Tune-Languages.md <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"Swe-CLIP 2M","children":[{"title":"README.md <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"practice.py <span style='color:#111;'> 20B </span>","children":null,"spread":false},{"title":"test","children":[{"title":"test.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"femalasadzzl1.jpg <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 8.75KB </span>","children":null,"spread":false},{"title":"CLIP.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"evaluate.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"data.pkl <span style='color:#111;'> 156B </span>","children":null,"spread":false},{"title":"get-weights.sh <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"checkpoint <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- 一个PSCAD配网故障仿真
- ISAR雷达成像，采用距离－多普勒处理得到目标的图像
- 眼球跟踪定位算法，eyelike
- IDRAC8注册码
- RSA算法C++实现
- 大数据开发岗位面试大礼包
- 汽车客运公司售票系统
- 好用的SqlServerHelper.cs工具类
- TCP连接测试工具_强烈推荐！
- js实现页面加loading提示效果
- 无网格法及其应用（西北工业大学出版社）
- 2020云计算技术期末作业.zip
- VC++ MFC 如何用 CZip CUnzip类压缩解压缩文件
- 单片机 89c51 八个数码管显示0到f c程序及仿真图
- c#调用相机拍照.rar
- 技嘉B85MD2VPLUSSI.F1
- Ma 等。 - 2021 - Image Matching from Handcrafted to Deep Features .pdf
- Telerik UI for ASP.NET Core 2020.3.915
- echarts中词云图js
- 语音识别HTK代码学习手册
- c语言编程实现聊天程序设计
- Confluent.Kafka源代码+Test
- Java简易聊天程序
- 动态分区分配存储管理-操作系统课程设计
- Silverlight SharpDraw 在线绘图Demo
- 剑儿百度文库下载器最新更新
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