mask-rcnn-keras:这是一个mask-rcnn的库,可以用于训练自己的实例分割模型

上传者: 42151305 | 上传时间: 2021-06-22 10:08:44 | 文件大小: 508KB | 文件类型: ZIP
Mask-Rcnn-实例分割模型在Keras当中的实现 目录 所需环境 tensorflow-gpu==1.13.1 keras==2.1.5 文件下载 这个训练好的权重是基于coco数据集的,可以直接运行用于coco数据集的实例分割。 链接: 提取码: 15cj 这个数据集是用于分辨图片中的圆形、正方形、三角形的,格式已经经过了处理,可以让大家明白训练集的格式。 链接: 提取码: 9457 训练步骤 1、准备数据集 a、利用labelme标注数据集,注意标注的时候同一个类要用不同的序号,比如画面中存在两个苹果那么一个苹果的label就是apple1另一个是apple2。 b、标注完成后将jpg文件和json文件放在根目录下的before里面。 c、之后运行json_to_dataset.py就可以生成train_dataset文件夹了。 2、修改训练参数 a、dataset.py内修

文件下载

资源详情

[{"title":"( 29 个子文件 508KB ) mask-rcnn-keras:这是一个mask-rcnn的库,可以用于训练自己的实例分割模型","children":[{"title":"mask-rcnn-keras-master","children":[{"title":"vision_for_anchor.py <span style='color:#111;'> 3.69KB </span>","children":null,"spread":false},{"title":"train_for_coco","children":[{"title":"coco.py <span style='color:#111;'> 14.82KB </span>","children":null,"spread":false}],"spread":true},{"title":"video.py <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":"predict.py <span style='color:#111;'> 399B </span>","children":null,"spread":false},{"title":"before","children":[{"title":"README.md <span style='color:#111;'> 43B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 1.89KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"config.py <span style='color:#111;'> 4.22KB </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 4.26KB </span>","children":null,"spread":false},{"title":"visualize.py <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 27.19KB </span>","children":null,"spread":false},{"title":"anchors.py <span style='color:#111;'> 2.97KB </span>","children":null,"spread":false}],"spread":true},{"title":"json_to_dataset.py <span style='color:#111;'> 3.09KB </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 2.69KB </span>","children":null,"spread":false},{"title":"train_dataset","children":[{"title":"README.md <span style='color:#111;'> 100B </span>","children":null,"spread":false}],"spread":true},{"title":"train.py <span style='color:#111;'> 5.08KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"mask_rcnn.py <span style='color:#111;'> 4.55KB </span>","children":null,"spread":false},{"title":"img","children":[{"title":"2.jpg <span style='color:#111;'> 20.02KB </span>","children":null,"spread":false},{"title":"1.jpg <span style='color:#111;'> 21.40KB </span>","children":null,"spread":false},{"title":"street.jpg <span style='color:#111;'> 437.08KB </span>","children":null,"spread":false},{"title":"0.jpg <span style='color:#111;'> 22.75KB </span>","children":null,"spread":false}],"spread":false},{"title":"常见问题汇总.md <span style='color:#111;'> 19.73KB </span>","children":null,"spread":false},{"title":"nets","children":[{"title":"mrcnn.py <span style='color:#111;'> 20.09KB </span>","children":null,"spread":false},{"title":"mrcnn_training.py <span style='color:#111;'> 16.84KB </span>","children":null,"spread":false},{"title":"resnet.py <span style='color:#111;'> 4.19KB </span>","children":null,"spread":false},{"title":"layers.py <span style='color:#111;'> 23.08KB </span>","children":null,"spread":false}],"spread":false},{"title":"model_data","children":[{"title":"coco_classes.txt <span style='color:#111;'> 705B </span>","children":null,"spread":false},{"title":"shape_classes.txt <span style='color:#111;'> 24B </span>","children":null,"spread":false}],"spread":false},{"title":"logs","children":[{"title":"README.md <span style='color:#111;'> 45B </span>","children":null,"spread":false}],"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