利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行

上传者: 51986063 | 上传时间: 2023-03-11 16:54:10 | 文件大小: 3.03MB | 文件类型: ZIP
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码。 实现功能: 基础功能利用pytorch实现图像分类 包含带有warmup的cosine学习率调整 warmup的step学习率优调整 多模型融合预测,加权与投票融合 利用flask + redis实现模型云端api部署(tag v1) c++ libtorch的模型部署 使用tta测试时增强进行预测(tag v1) 添加label smooth的pytorch实现(标签平滑)(tag v1) 添加使用cnn提取特征,并使用SVM,RF,MLP,KNN等分类器进行分类(tag v1)。 可视化特征层。 转载:https://github.com/lxztju/pytorch_classification

文件下载

资源详情

[{"title":"( 52 个子文件 3.03MB ) 利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行","children":[{"title":"pytorch_classification-master","children":[{"title":"tools","children":[{"title":"evaluation.py <span style='color:#111;'> 4.62KB </span>","children":null,"spread":false},{"title":"train_val.py <span style='color:#111;'> 5.84KB </span>","children":null,"spread":false},{"title":"predict.py <span style='color:#111;'> 2.45KB </span>","children":null,"spread":false}],"spread":true},{"title":"sample_files","children":[{"title":"imgs","children":[{"title":"dog","children":[{"title":"2.jpg <span style='color:#111;'> 14.95KB </span>","children":null,"spread":false},{"title":"1.jpg <span style='color:#111;'> 26.17KB </span>","children":null,"spread":false},{"title":"5.jpg <span style='color:#111;'> 39.38KB </span>","children":null,"spread":false},{"title":"0.jpg <span style='color:#111;'> 33.64KB </span>","children":null,"spread":false},{"title":"3.jpg <span style='color:#111;'> 30.01KB </span>","children":null,"spread":false},{"title":"4.jpg <span style='color:#111;'> 106.04KB </span>","children":null,"spread":false}],"spread":true},{"title":"cat","children":[{"title":"2.jpg <span style='color:#111;'> 26.36KB </span>","children":null,"spread":false},{"title":"1.jpg <span style='color:#111;'> 16.47KB </span>","children":null,"spread":false},{"title":"5.jpg <span style='color:#111;'> 5.62KB </span>","children":null,"spread":false},{"title":"0.jpg <span style='color:#111;'> 11.93KB </span>","children":null,"spread":false},{"title":"3.jpg <span style='color:#111;'> 37.06KB </span>","children":null,"spread":false},{"title":"4.jpg <span style='color:#111;'> 19.99KB </span>","children":null,"spread":false}],"spread":true},{"title":"listfile.txt <span style='color:#111;'> 804B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"cpp_inference","children":[{"title":"traced_model","children":[{"title":"trace_model.py <span style='color:#111;'> 711B </span>","children":null,"spread":false}],"spread":true},{"title":"compile.sh <span style='color:#111;'> 103B </span>","children":null,"spread":false},{"title":"CMakeLists.txt <span style='color:#111;'> 875B </span>","children":null,"spread":false},{"title":".vscode","children":[{"title":"settings.json <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false}],"spread":true},{"title":"classification","children":[{"title":"include","children":[{"title":"ImgCls.hpp <span style='color:#111;'> 700B </span>","children":null,"spread":false}],"spread":true},{"title":"CMakeLists.txt <span style='color:#111;'> 769B </span>","children":null,"spread":false},{"title":"src","children":[{"title":"ImgCls.cpp <span style='color:#111;'> 2.40KB </span>","children":null,"spread":false}],"spread":true},{"title":"test_ImgCls.cpp <span style='color:#111;'> 511B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"__init__.py <span style='color:#111;'> 155B </span>","children":null,"spread":false},{"title":"util.py <span style='color:#111;'> 2.38KB </span>","children":null,"spread":false},{"title":"loss_kd.py <span style='color:#111;'> 621B </span>","children":null,"spread":false},{"title":"lr_scheduler.py <span style='color:#111;'> 3.25KB </span>","children":null,"spread":false},{"title":"warmup_lr.py <span style='color:#111;'> 3.67KB </span>","children":null,"spread":false},{"title":"label_smoothing_pytorch.py <span style='color:#111;'> 1.00KB </span>","children":null,"spread":false},{"title":"opts.py <span style='color:#111;'> 3.42KB </span>","children":null,"spread":false}],"spread":true},{"title":"dataset","children":[{"title":"__init__.py <span style='color:#111;'> 90B </span>","children":null,"spread":false},{"title":"cls_dataset.py <span style='color:#111;'> 1.24KB </span>","children":null,"spread":false},{"title":"transform.py <span style='color:#111;'> 2.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"visualization","children":[{"title":"test.png <span style='color:#111;'> 143.38KB </span>","children":null,"spread":false},{"title":"f1_conv1.png <span style='color:#111;'> 1.51MB </span>","children":null,"spread":false},{"title":"Feature_Visualization.py <span style='color:#111;'> 2.52KB </span>","children":null,"spread":false},{"title":"Feature_Visualization.ipynb <span style='color:#111;'> 1.73MB </span>","children":null,"spread":false}],"spread":true},{"title":"trt_inference","children":[{"title":"include","children":[{"title":"TrtCls.hpp <span style='color:#111;'> 4.17KB </span>","children":null,"spread":false}],"spread":true},{"title":"CMakeLists.txt <span style='color:#111;'> 1.19KB </span>","children":null,"spread":false},{"title":"src","children":[{"title":"TrtCls.cpp <span style='color:#111;'> 7.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"convert_onnx.py <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false},{"title":"labels.txt <span style='color:#111;'> 12B </span>","children":null,"spread":false}],"spread":true},{"title":"cls_models","children":[{"title":"__init__.py <span style='color:#111;'> 27B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 2.66KB </span>","children":null,"spread":false}],"spread":true},{"title":"ensamble","children":[{"title":"kaggle_vote.py <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"samples","children":[{"title":"method_3.csv <span style='color:#111;'> 83.14KB </span>","children":null,"spread":false},{"title":"method_2.csv <span style='color:#111;'> 83.01KB </span>","children":null,"spread":false},{"title":"method_1.csv <span style='color:#111;'> 83.02KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"run.sh <span style='color:#111;'> 1.26KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 2.33KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

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