flownet2-pytorch:FlowNet 2.0的Pytorch实施-源码

上传者: 42112658 | 上传时间: 2021-09-05 22:11:03 | 文件大小: 222KB | 文件类型: ZIP
flownet2-pytorch FlowNet Pytorch实现。 支持多种GPU训练,并且代码提供了有关干净数据集和最终数据集的训练或推理示例。 相同的命令可用于训练或推断其他数据集。 有关更多详细信息,请参见下文。 还支持使用fp16(半精度)进行推理。 如需更多帮助,请键入 python main.py --help 网络架构 以下是提供的不同Flownet神经网络架构。 每个网络的batchnorm版本也可用。 FlowNet2S FlowNet2C FlowNet2CS FlowNet2CSS FlowNet2SD FlowNet2 自定义图层 FlowNet2或FlowNet2C*结构依赖于自定义层Resample2d或Correlation 。 这些层与CUDA内核的pytorch实现可在 。 注意:当前,半精度内核不适用于这些层。 数据加载器 dat

文件下载

资源详情

[{"title":"( 45 个子文件 222KB ) flownet2-pytorch:FlowNet 2.0的Pytorch实施-源码","children":[{"title":"flownet2-pytorch-master","children":[{"title":"run-caffe2pytorch.sh <span style='color:#111;'> 1.49KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"frame_utils.py <span style='color:#111;'> 534B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"tools.py <span style='color:#111;'> 5.26KB </span>","children":null,"spread":false},{"title":"flow_utils.py <span style='color:#111;'> 4.99KB </span>","children":null,"spread":false},{"title":"param_utils.py <span style='color:#111;'> 6.72KB </span>","children":null,"spread":false}],"spread":true},{"title":"install.sh <span style='color:#111;'> 340B </span>","children":null,"spread":false},{"title":"Dockerfile <span style='color:#111;'> 1.25KB </span>","children":null,"spread":false},{"title":"download_caffe_models.sh <span style='color:#111;'> 413B </span>","children":null,"spread":false},{"title":"datasets.py <span style='color:#111;'> 12.99KB </span>","children":null,"spread":false},{"title":"main.py <span style='color:#111;'> 23.49KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"models.py <span style='color:#111;'> 19.45KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 558B </span>","children":null,"spread":false},{"title":"convert.py <span style='color:#111;'> 4.59KB </span>","children":null,"spread":false},{"title":"losses.py <span style='color:#111;'> 2.76KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false},{"title":"run_a_pair.py <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false},{"title":"launch_docker.sh <span style='color:#111;'> 205B </span>","children":null,"spread":false},{"title":"networks","children":[{"title":"resample2d_package","children":[{"title":"resample2d.py <span style='color:#111;'> 1.56KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"resample2d_kernel.cuh <span style='color:#111;'> 391B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 767B </span>","children":null,"spread":false},{"title":"resample2d_cuda.cc <span style='color:#111;'> 852B </span>","children":null,"spread":false},{"title":"resample2d_kernel.cu <span style='color:#111;'> 12.73KB </span>","children":null,"spread":false}],"spread":false},{"title":"submodules.py <span style='color:#111;'> 2.75KB </span>","children":null,"spread":false},{"title":"FlowNetFusion.py <span style='color:#111;'> 2.27KB </span>","children":null,"spread":false},{"title":"channelnorm_package","children":[{"title":"channelnorm_kernel.cuh <span style='color:#111;'> 298B </span>","children":null,"spread":false},{"title":"channelnorm_kernel.cu <span style='color:#111;'> 5.92KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 725B </span>","children":null,"spread":false},{"title":"channelnorm.py <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"channelnorm_cuda.cc <span style='color:#111;'> 722B </span>","children":null,"spread":false}],"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"FlowNetSD.py <span style='color:#111;'> 4.09KB </span>","children":null,"spread":false},{"title":"FlowNetC.py <span style='color:#111;'> 4.65KB </span>","children":null,"spread":false},{"title":"FlowNetS.py <span style='color:#111;'> 3.57KB </span>","children":null,"spread":false},{"title":"correlation_package","children":[{"title":"correlation.py <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 791B </span>","children":null,"spread":false},{"title":"correlation_cuda_kernel.cu <span style='color:#111;'> 19.45KB </span>","children":null,"spread":false},{"title":"correlation_cuda_kernel.cuh <span style='color:#111;'> 1.38KB </span>","children":null,"spread":false},{"title":"correlation_cuda.cc <span style='color:#111;'> 6.46KB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":".gitignore <span style='color:#111;'> 39B </span>","children":null,"spread":false},{"title":"image.png <span style='color:#111;'> 175.93KB </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