颜色分类leetcode-traffic-light-classification:交通灯图像分类

上传者: 38743391 | 上传时间: 2022-10-09 15:08:15 | 文件大小: 81.13MB | 文件类型: ZIP
颜色分类leetcode 交通灯图像分类 Udacity 自动驾驶汽车纳米学位顶点项目。 系统集成 概述 感知子系统对车辆前方的交通灯颜色进行动态分类。 在给定的模拟器和测试站点环境中,汽车面对单个交通灯或一组 3 个处于相同状态(绿色、黄色、红色)的交通灯。 我们假设不可能同时在不同的州有多个交通灯。 我们考虑了不同的方法来解决交通灯分类任务: 使用CNN对整个图像进行分类; 物体(红绿灯状态)检测; 使用单独模型的物体(交通灯)检测和分类。 考虑到红绿灯始终处于相同状态,并专注于创建轻量级和快速模型,我们选择了对整个图像进行分类的方向。 这种方法使用卷积神经网络,它将前置摄像头的整个图像作为输入,并预测交通灯状态(我们决定使用红色/无预测类)作为输出。 我们在 MobileNet 架构上使用了迁移学习技术和 Tensorflow Image Retraining Example(教程:,代码:)。 数据集 有多个数据集可用于模型训练: 来自 Udacity 模拟器的图像(图像以及来自前置摄像头的地面实况可作为 ROS 主题提供); rosbag,在 Udacity 的测试站点上捕获

文件下载

资源详情

[{"title":"( 29 个子文件 81.13MB ) 颜色分类leetcode-traffic-light-classification:交通灯图像分类","children":[{"title":"traffic-light-classification-master","children":[{"title":"bosch_preprocessing.py <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"udacity_graph.pb <span style='color:#111;'> 16.34MB </span>","children":null,"spread":false},{"title":"mobilenets.png <span style='color:#111;'> 109.69KB </span>","children":null,"spread":false},{"title":"output_graph.pb <span style='color:#111;'> 16.34MB </span>","children":null,"spread":false},{"title":"sim_accuracy.png <span style='color:#111;'> 67.51KB </span>","children":null,"spread":false},{"title":"udacity_labels.txt <span style='color:#111;'> 22B </span>","children":null,"spread":false},{"title":"sim_labels.txt <span style='color:#111;'> 22B </span>","children":null,"spread":false},{"title":"summaries_sim","children":[{"title":"train","children":[{"title":"events.out.tfevents.1507556172.ip-172-31-28-95 <span style='color:#111;'> 83.39MB </span>","children":null,"spread":false}],"spread":true},{"title":"validation","children":[{"title":"events.out.tfevents.1507556174.ip-172-31-28-95 <span style='color:#111;'> 5.26MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"sim_graph.pb <span style='color:#111;'> 16.34MB </span>","children":null,"spread":false},{"title":"udacity_accuracy.png <span style='color:#111;'> 94.93KB </span>","children":null,"spread":false},{"title":"output_labels.txt <span style='color:#111;'> 22B </span>","children":null,"spread":false}],"spread":true},{"title":"src","children":[{"title":"retrain.py <span style='color:#111;'> 54.24KB </span>","children":null,"spread":false},{"title":"bosch_classif.py <span style='color:#111;'> 4.56KB </span>","children":null,"spread":false},{"title":"retrain_sim.py <span style='color:#111;'> 55.14KB </span>","children":null,"spread":false},{"title":"label_image.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false}],"spread":true},{"title":"sim_preprocessing.py <span style='color:#111;'> 1.59KB </span>","children":null,"spread":false},{"title":"scripts","children":[{"title":"train_model.py <span style='color:#111;'> 61.37KB </span>","children":null,"spread":false},{"title":"yellow2red.py <span style='color:#111;'> 434B </span>","children":null,"spread":false},{"title":"train_mobilenets.sh <span style='color:#111;'> 486B </span>","children":null,"spread":false},{"title":"bosch_transf_to_classif.py <span style='color:#111;'> 4.56KB </span>","children":null,"spread":false},{"title":"train_inception.sh <span style='color:#111;'> 293B </span>","children":null,"spread":false},{"title":"bosch_classif.py <span style='color:#111;'> 4.21KB </span>","children":null,"spread":false},{"title":"png2jpg.py <span style='color:#111;'> 564B </span>","children":null,"spread":false},{"title":"scripts.sh <span style='color:#111;'> 2.34KB </span>","children":null,"spread":false},{"title":"retrain_mobilenets.sh <span style='color:#111;'> 494B </span>","children":null,"spread":false},{"title":"prepare-ami.sh <span style='color:#111;'> 1.66KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 4.52KB </span>","children":null,"spread":false}],"spread":true}],"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