faster-rcnn-tf2:这是一个faster-rcnn的tensorflow2实现的库,可以利用voc数据集格式的数据进行训练

上传者: 42133918 | 上传时间: 2021-06-22 11:29:15 | 文件大小: 5.31MB | 文件类型: ZIP
Faster-Rcnn:Two-Stage目标检测模型在Tensorflow2当中的实现 目录 性能情况 训练数据集 权值文件名称 测试数据集 输入图片大小 mAP 0.5:0.95 mAP 0.5 VOC07+12 VOC-Test07 - - 77.5 所需环境 tensorflow-gpu==2.2.0 文件下载 训练所需的voc_weights.h5可以去百度网盘下载 链接: 提取码: 92e8 VOC数据集下载地址如下: VOC2007+2012训练集 链接: 提取码: eiw9 VOC2007测试集 链接: 提取码: dsda 预测步骤 a、使用预训练权重 下载完库后解压,在百度网盘下载voc_weights.h5,放入model_data,运行predict.py,输入 img/street.jpg 利用video.py可进行摄像头检测。 b、使用自己训练的权重 按照训

文件下载

资源详情

[{"title":"( 28 个子文件 5.31MB ) faster-rcnn-tf2:这是一个faster-rcnn的tensorflow2实现的库,可以利用voc数据集格式的数据进行训练","children":[{"title":"faster-rcnn-tf2-main","children":[{"title":"logs","children":[{"title":"README.md <span style='color:#111;'> 36B </span>","children":null,"spread":false}],"spread":true},{"title":"train.py <span style='color:#111;'> 10.38KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"config.py <span style='color:#111;'> 1.45KB </span>","children":null,"spread":false},{"title":"anchors.py <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 13.01KB </span>","children":null,"spread":false},{"title":"roi_helpers.py <span style='color:#111;'> 5.65KB </span>","children":null,"spread":false}],"spread":true},{"title":"model_data","children":[{"title":"simhei.ttf <span style='color:#111;'> 9.30MB </span>","children":null,"spread":false},{"title":"voc_classes.txt <span style='color:#111;'> 153B </span>","children":null,"spread":false}],"spread":true},{"title":"VOCdevkit","children":[{"title":"VOC2007","children":[{"title":"Annotations","children":[{"title":"README.md <span style='color:#111;'> 18B </span>","children":null,"spread":false}],"spread":true},{"title":"ImageSets","children":[{"title":"Main","children":[{"title":"README.md <span style='color:#111;'> 24B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"JPEGImages","children":[{"title":"README.md <span style='color:#111;'> 18B </span>","children":null,"spread":false}],"spread":true},{"title":"voc2faster-rcnn.py <span style='color:#111;'> 2.10KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"voc_annotation.py <span style='color:#111;'> 1.70KB </span>","children":null,"spread":false},{"title":"img","children":[{"title":"street.jpg <span style='color:#111;'> 437.08KB </span>","children":null,"spread":false}],"spread":true},{"title":"predict.py <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"Vision_for_anchor.py <span style='color:#111;'> 2.86KB </span>","children":null,"spread":false},{"title":"get_map.py <span style='color:#111;'> 32.91KB </span>","children":null,"spread":false},{"title":"nets","children":[{"title":"frcnn.py <span style='color:#111;'> 5.25KB </span>","children":null,"spread":false},{"title":"resnet.py <span style='color:#111;'> 7.00KB </span>","children":null,"spread":false},{"title":"RoiPoolingConv.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"frcnn_training.py <span style='color:#111;'> 12.06KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"frcnn.py <span style='color:#111;'> 8.98KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.45KB </span>","children":null,"spread":false},{"title":"get_dr_txt.py <span style='color:#111;'> 5.54KB </span>","children":null,"spread":false},{"title":"常见问题汇总.md <span style='color:#111;'> 19.73KB </span>","children":null,"spread":false},{"title":"video.py <span style='color:#111;'> 1.43KB </span>","children":null,"spread":false},{"title":"get_gt_txt.py <span style='color:#111;'> 1.50KB </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