基于 python+深度学习的视觉问答毕业设计（含源码+答辩 ppt）
【作品名称】：基于 python+深度学习的视觉问答【毕业设计】（含源码+答辩 ppt）
【适用人群】：适用于希望学习不同技术领域的小白或进阶学习者。可作为毕设项目、课程设计、大作业、工程实训或初期项目立项。
【项目介绍】：对于视觉问答（VQA）的研究具有深刻的学术意义和广阔的应用前景。目前，视觉问答模型性能提升的重点在于图像特征的提取，文本特征的提取，attention权重的计算和图像特征与文本特征融合的方式这4个方面。本文主要针对attention权重的计算和图像特征与文本特征融合这两个方面，以及其他细节方面的地方相对于前人的模型做出了改进。本文的主要工作在于本文使用open-ended模式，答案的准确率采用分数累积，而不是一般的多项选择。本文采用CSF模块（包括CSF_A和CSF_B）不仅对spatial-wise进行了权重计算，还对channel-wise进行了权重计算。本文采用MFB模块和ResNet152 FC层之前的tensor来结合LSTM的输出来计算每个区域的权重，而不是直接把image feature和question feature结合本文采用SigMoid来
文件下载
资源详情
[{"title":"（ 70 个子文件 2.73MB ） 基于 python+深度学习的视觉问答毕业设计（含源码+答辩 ppt）","children":[{"title":"Graduation-Design","children":[{"title":"model.png <span style='color:#111;'> 87.30KB </span>","children":null,"spread":false},{"title":"VQA02DataProcess.py <span style='color:#111;'> 10.21KB </span>","children":null,"spread":false},{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":"MFHBaseline.py <span style='color:#111;'> 9.26KB </span>","children":null,"spread":false},{"title":"record","children":[{"title":"current_['m']_freq_0_layer_0_csf_0.log <span style='color:#111;'> 10.21KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_0_csf_0.log <span style='color:#111;'> 10.98KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_2_csf_0.log <span style='color:#111;'> 10.63KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_1_['cs']_1.log <span style='color:#111;'> 10.63KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_0_['csf']_g_0_co_1.log <span style='color:#111;'> 24.61KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_3_['cs']_g_0_co_0.log <span style='color:#111;'> 37.70KB </span>","children":null,"spread":false},{"title":"current_model_['b']_freq_1_layer_1.log <span style='color:#111;'> 6.01KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_3_['csf']_g_0_co_0.log <span style='color:#111;'> 24.61KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_1_csf_0.log <span style='color:#111;'> 10.63KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_2_['cs']_g_0_co_0.log <span style='color:#111;'> 24.62KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_0_['csf']_g_0_co_0.log <span style='color:#111;'> 24.61KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_2_['cs']_0.log <span style='color:#111;'> 10.63KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_3_['cs']_0.log <span style='color:#111;'> 10.98KB </span>","children":null,"spread":false},{"title":"current_model_['b']_freq_1_layer_0.log <span style='color:#111;'> 6.22KB </span>","children":null,"spread":false},{"title":"current_['m']_freq_0_layer_1_['cs']_g_0_co_0.log <span style='color:#111;'> 24.62KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_1_['cs']_0.log <span style='color:#111;'> 10.63KB </span>","children":null,"spread":false},{"title":"current_['b']_freq_0_layer_1_['cs']_g_0_co_0.log <span style='color:#111;'> 24.62KB </span>","children":null,"spread":false}],"spread":false},{"title":"TEST.py <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"VQA02train.py <span style='color:#111;'> 16.71KB </span>","children":null,"spread":false},{"title":"VQA01dataset.py <span style='color:#111;'> 4.70KB </span>","children":null,"spread":false},{"title":"TMP.py <span style='color:#111;'> 10.44KB </span>","children":null,"spread":false},{"title":"VQA02dataset.py <span style='color:#111;'> 5.50KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"COCO_train2014_000000000009.jpg <span style='color:#111;'> 219.04KB </span>","children":null,"spread":false}],"spread":true},{"title":"VQA01ImageProcess.py <span style='color:#111;'> 6.78KB </span>","children":null,"spread":false},{"title":"predict.py <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false},{"title":"modelResNet.py <span style='color:#111;'> 11.89KB </span>","children":null,"spread":false},{"title":"readme <span style='color:#111;'> 751B </span>","children":null,"spread":false},{"title":"VQA01Baseline.py <span style='color:#111;'> 5.55KB </span>","children":null,"spread":false},{"title":"VQAv1Dataloader.py <span style='color:#111;'> 6.03KB </span>","children":null,"spread":false},{"title":"eval_tools.py <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false},{"title":"CSFMODEL.py <span style='color:#111;'> 7.37KB </span>","children":null,"spread":false},{"title":"draft.py <span style='color:#111;'> 6.73KB </span>","children":null,"spread":false},{"title":"VQA02ImageProcess2.py <span style='color:#111;'> 3.62KB </span>","children":null,"spread":false},{"title":"npy_h5py.py <span style='color:#111;'> 1.57KB </span>","children":null,"spread":false},{"title":"modules.py <span style='color:#111;'> 11.21KB </span>","children":null,"spread":false},{"title":"DataLoader.py <span style='color:#111;'> 4.15KB </span>","children":null,"spread":false},{"title":"VQA02getdata.py <span style='color:#111;'> 9.31KB </span>","children":null,"spread":false},{"title":"resnet.py <span style='color:#111;'> 9.82KB </span>","children":null,"spread":false},{"title":"VQA02ImageProcess.py <span style='color:#111;'> 3.78KB </span>","children":null,"spread":false},{"title":"vqa-tools","children":[{"title":"PythonEvaluationTools","children":[{"title":"vqaEvaluation","children":[{"title":"vqaEval.py <span style='color:#111;'> 7.99KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 18B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"vqaEval.cpython-36.pyc <span style='color:#111;'> 7.33KB </span>","children":null,"spread":false},{"title":"__init__.cpython-36.pyc <span style='color:#111;'> 159B </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"vqaEvalDemo.py <span style='color:#111;'> 3.39KB </span>","children":null,"spread":false}],"spread":false},{"title":"PythonHelperTools","children":[{"title":"vqaTools","children":[{"title":"__init__.py <span style='color:#111;'> 24B </span>","children":null,"spread":false},{"title":"vqa.py <span style='color:#111;'> 6.96KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"vqa.cpython-36.pyc <span style='color:#111;'> 6.77KB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"vqaDemo.py <span style='color:#111;'> 2.16KB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"答辩.pptx <span style='color:#111;'> 2.30MB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 15B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"MFHMODEL.cpython-35.pyc <span style='color:#111;'> 5.54KB </span>","children":null,"spread":false},{"title":"CSFMODEL.cpython-35.pyc <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"DataLoader.cpython-35.pyc <span style='color:#111;'> 3.07KB </span>","children":null,"spread":false},{"title":"VQA02DataProcess.cpython-35.pyc <span style='color:#111;'> 133B </span>","children":null,"spread":false},{"title":"config.cpython-35.pyc <span style='color:#111;'> 3.29KB </span>","children":null,"spread":false},{"title":"VQAv1Dataloader.cpython-35.pyc <span style='color:#111;'> 3.83KB </span>","children":null,"spread":false},{"title":"modules.cpython-35.pyc <span style='color:#111;'> 6.83KB </span>","children":null,"spread":false},{"title":"MFHBaseline.cpython-35.pyc <span style='color:#111;'> 5.31KB </span>","children":null,"spread":false},{"title":"resnet.cpython-35.pyc <span style='color:#111;'> 8.76KB </span>","children":null,"spread":false}],"spread":false},{"title":"modelVGG.py <span style='color:#111;'> 10.50KB </span>","children":null,"spread":false},{"title":"VQA01DataProcess.py <span style='color:#111;'> 6.52KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"MFHMODEL.py <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"VQAREesNet.py <span style='color:#111;'> 11.84KB </span>","children":null,"spread":false},{"title":"readme.txt <span style='color:#111;'> 3.96KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 4.25KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- 基于CAN的直流无刷电机速度闭环控制
- 电影数据mysql脚本
- 浙江大学陈越数据结构课件
- 雷达目标特性丛书（pdf扫描版）
- 高通C-V2X方案介绍
- java(swing,awt)图形用户界面编程100多个案例
- 广东工业大学数据结构课程设计-表达式类型的实现
- c++个人理财管理系统
- v4版本的D3js源码和Api已经齐全的demo
- C++围棋游戏
- 新唐mcu（N76E003）全套DEMO，可直接运行
- MATLAB源码集锦-基于格拉布斯准则判断异常数据代码
- 夜间值班-源码
- 网络工程解决方案经典案例合集.zip
- 12_PaintEvent.rar
- 区块链产品文档.docx
- 环境法律法规及其他要求清单
- C++ GUI Qt 4编程（第二版）（书+源代码）
- 网络监控系统 论文
- 基于通信基站的三维室内定位matlab
- 不错的中国象棋单机版
- 数据挖掘在电商领域的应用
- XFire返回自定义实体类实例
- 教材征订系统（毕业设计）
- 地图流向图
- vsftp安装包以及配置说明
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