登录
首页 » Python » DensePose-master

DensePose-master

于 2019-06-17 发布
0 261
下载积分: 1 下载次数: 4
我要下载

代码说明：

说明：  DensePose用深度学习把2D图像坐标映射到3D人体表面上，再加上以每秒多帧的速度处理密集坐标，最后实现动态人物的精确定位和姿态估计。该技术集目标检测、姿态估计、目标部分/实例分割等多种计算机视觉任务于一身的一个综合问题。(DensePost maps 2D image coordinates to 3D human body surface by in-depth learning, and processes dense coordinates at the speed of multiple frames per second. Finally, it realizes precise positioning and attitude estimation of dynamic characters. This technology integrates many kinds of computer vision tasks, such as target detection, attitude estimation, target part/instance segmentation, etc.)

文件列表：

DensePose-master, 0 , 2018-08-28
DensePose-master\.gitignore, 495 , 2018-08-28
DensePose-master\CMakeLists.txt, 2012 , 2018-08-28
DensePose-master\CODE_OF_CONDUCT.md, 286 , 2018-08-28
DensePose-master\CONTRIBUTING.md, 1250 , 2018-08-28
DensePose-master\DensePoseData, 0 , 2018-08-28
DensePose-master\DensePoseData\demo_data, 0 , 2018-08-28
DensePose-master\DensePoseData\demo_data\demo_dp_single_ann.pkl, 980845 , 2018-08-28
DensePose-master\DensePoseData\demo_data\demo_im.jpg, 149246 , 2018-08-28
DensePose-master\DensePoseData\demo_data\synth_UV_example.png, 25997 , 2018-08-28
DensePose-master\DensePoseData\demo_data\texture_atlas_200.png, 1237384 , 2018-08-28
DensePose-master\DensePoseData\demo_data\texture_from_SURREAL.png, 831242 , 2018-08-28
DensePose-master\DensePoseData\get_DensePose_COCO.sh, 346 , 2018-08-28
DensePose-master\DensePoseData\get_densepose_uv.sh, 163 , 2018-08-28
DensePose-master\DensePoseData\get_eval_data.sh, 173 , 2018-08-28
DensePose-master\DensePoseData\infer_out, 0 , 2018-08-28
DensePose-master\DensePoseData\infer_out\demo_im.jpg.pdf, 1056420 , 2018-08-28
DensePose-master\DensePoseData\infer_out\demo_im_INDS.png, 8801 , 2018-08-28
DensePose-master\DensePoseData\infer_out\demo_im_IUV.png, 77229 , 2018-08-28
DensePose-master\GETTING_STARTED.md, 2815 , 2018-08-28
DensePose-master\INSTALL.md, 6712 , 2018-08-28
DensePose-master\LICENSE, 19333 , 2018-08-28
DensePose-master\MODEL_ZOO.md, 3109 , 2018-08-28
DensePose-master\Makefile, 491 , 2018-08-28
DensePose-master\NOTICE, 1344 , 2018-08-28
DensePose-master\PoseTrack, 0 , 2018-08-28
DensePose-master\PoseTrack\DensePose-PoseTrack-Visualize.ipynb, 792870 , 2018-08-28
DensePose-master\PoseTrack\README.md, 3352 , 2018-08-28
DensePose-master\PoseTrack\configs, 0 , 2018-08-28
DensePose-master\PoseTrack\configs\DensePose_ResNet50_FPN_s1x-e2e.yaml, 1976 , 2018-08-28
DensePose-master\PoseTrack\get_DensePose_PoseTrack.sh, 696 , 2018-08-28
DensePose-master\README.md, 3216 , 2018-08-28
DensePose-master\challenge, 0 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose, 0 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose\data_format.md, 3303 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose\evaluation.md, 4694 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose\example_results.json, 181922 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose\readme.md, 3797 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose\results_format.md, 2153 , 2018-08-28
DensePose-master\challenge\2018_COCO_DensePose\upload.md, 3823 , 2018-08-28
DensePose-master\challenge\2018_PoseTrack_DensePose, 0 , 2018-08-28
DensePose-master\challenge\2018_PoseTrack_DensePose\data_format.md, 4449 , 2018-08-28
DensePose-master\challenge\2018_PoseTrack_DensePose\evaluation.md, 4641 , 2018-08-28
DensePose-master\challenge\2018_PoseTrack_DensePose\readme.md, 3594 , 2018-08-28
DensePose-master\challenge\2018_PoseTrack_DensePose\results_format.md, 2157 , 2018-08-28
DensePose-master\challenge\2018_PoseTrack_DensePose\upload.md, 3873 , 2018-08-28
DensePose-master\challenge\encode_results_for_competition.py, 3508 , 2018-08-28
DensePose-master\cmake, 0 , 2018-08-28
DensePose-master\cmake\Summary.cmake, 1020 , 2018-08-28
DensePose-master\cmake\legacy, 0 , 2018-08-28
DensePose-master\cmake\legacy\Cuda.cmake, 9531 , 2018-08-28
DensePose-master\cmake\legacy\Dependencies.cmake, 1341 , 2018-08-28
DensePose-master\cmake\legacy\Modules, 0 , 2018-08-28
DensePose-master\cmake\legacy\Modules\FindCuDNN.cmake, 2100 , 2018-08-28
DensePose-master\cmake\legacy\Summary.cmake, 940 , 2018-08-28
DensePose-master\cmake\legacy\Utils.cmake, 10724 , 2018-08-28
DensePose-master\cmake\legacy\legacymake.cmake, 1621 , 2018-08-28
DensePose-master\configs, 0 , 2018-08-28
DensePose-master\configs\DensePoseKeyPointsMask_ResNet50_FPN_s1x-e2e.yaml, 2681 , 2018-08-28
DensePose-master\configs\DensePose_ResNet101_FPN.yaml, 1975 , 2018-08-28
DensePose-master\configs\DensePose_ResNet101_FPN_32x8d_s1x-e2e.yaml, 2151 , 2018-08-28
DensePose-master\configs\DensePose_ResNet101_FPN_32x8d_s1x.yaml, 2155 , 2018-08-28
DensePose-master\configs\DensePose_ResNet101_FPN_s1x-e2e.yaml, 1977 , 2018-08-28
DensePose-master\configs\DensePose_ResNet101_FPN_s1x.yaml, 2117 , 2018-08-28
DensePose-master\configs\DensePose_ResNet50_FPN.yaml, 1974 , 2018-08-28
DensePose-master\configs\DensePose_ResNet50_FPN_s1x-e2e.yaml, 1975 , 2018-08-28
DensePose-master\configs\DensePose_ResNet50_FPN_s1x.yaml, 2115 , 2018-08-28
DensePose-master\configs\DensePose_ResNet50_FPN_single_GPU.yaml, 2109 , 2018-08-28
DensePose-master\configs\rpn_densepose_only_R-50-FPN_1x.yaml, 1075 , 2018-08-28
DensePose-master\configs\rpn_densepose_only_X-101-32x8d-FPN_1x.yaml, 1263 , 2018-08-28
DensePose-master\detectron, 0 , 2018-08-28
DensePose-master\detectron\__init__.py, 0 , 2018-08-28
DensePose-master\detectron\core, 0 , 2018-08-28
DensePose-master\detectron\core\__init__.py, 0 , 2018-08-28
DensePose-master\detectron\core\config.py, 47570 , 2018-08-28
DensePose-master\detectron\core\rpn_generator.py, 9280 , 2018-08-28
DensePose-master\detectron\core\test.py, 37386 , 2018-08-28
DensePose-master\detectron\core\test_engine.py, 15303 , 2018-08-28
DensePose-master\detectron\core\test_retinanet.py, 7104 , 2018-08-28
DensePose-master\detectron\datasets, 0 , 2018-08-28
DensePose-master\detectron\datasets\VOCdevkit-matlab-wrapper, 0 , 2018-08-28
DensePose-master\detectron\datasets\VOCdevkit-matlab-wrapper\get_voc_opts.m, 231 , 2018-08-28
DensePose-master\detectron\datasets\VOCdevkit-matlab-wrapper\voc_eval.m, 1332 , 2018-08-28
DensePose-master\detectron\datasets\VOCdevkit-matlab-wrapper\xVOCap.m, 258 , 2018-08-28
DensePose-master\detectron\datasets\__init__.py, 0 , 2018-08-28
DensePose-master\detectron\datasets\cityscapes_json_dataset_evaluator.py, 2960 , 2018-08-28
DensePose-master\detectron\datasets\coco_to_cityscapes_id.py, 2495 , 2018-08-28
DensePose-master\detectron\datasets\data, 0 , 2018-08-28
DensePose-master\detectron\datasets\data\README.md, 3187 , 2018-08-28
DensePose-master\detectron\datasets\dataset_catalog.py, 8164 , 2018-08-28
DensePose-master\detectron\datasets\densepose_cocoeval.py, 39088 , 2018-08-28
DensePose-master\detectron\datasets\dummy_datasets.py, 1899 , 2018-08-28
DensePose-master\detectron\datasets\json_dataset.py, 20722 , 2018-08-28
DensePose-master\detectron\datasets\json_dataset_evaluator.py, 19172 , 2018-08-28
DensePose-master\detectron\datasets\roidb.py, 7497 , 2018-08-28
DensePose-master\detectron\datasets\task_evaluation.py, 14367 , 2018-08-28
DensePose-master\detectron\datasets\voc_dataset_evaluator.py, 6719 , 2018-08-28
DensePose-master\detectron\datasets\voc_eval.py, 7386 , 2018-08-28
DensePose-master\detectron\modeling, 0 , 2018-08-28
DensePose-master\detectron\modeling\FPN.py, 20218 , 2018-08-28

下载说明：请别用迅雷下载，失败请重下，重下不扣分！

发表评论

0 个回复

  • watershed_example
    说明：  分水岭算法是一种图像区域分割法，在分割的过程中，它会把跟临近像素间的相似性作为重要的参考依据，从而将在空间位置上相近并且灰度值相近的像素点互相连接起来构成一个封闭的轮廓，封闭性是分水岭算法的一个重要特征。本示例适用于二维和三维图像，计算分水岭变换并将结果标签矩阵显示为RGB图像。 分水岭算法是一种图像区域分割法，在分割的过程中，它会把跟临近像素间的相似性作为重要的参考依据，从而将在空间位置上相近并且灰度值相近的像素点互相连接起来构成一个封闭的轮廓，封闭性是分水岭算法的一个重要特征。本示例适用于二维和三维图像，计算分水岭变换并将结果标签矩阵显示为RGB图像。(The watershed algorithm is an image region segmentation method. In the segmentation process, it will use the similarity with neighboring pixels as an important reference basis, so as to connect pixels that are close in space and have similar gray values to each other. Forming a closed contour, closedness is an important feature of the watershed algorithm. This example applies to 2D and 3D images, calculates the watershed transformation and displays the resulting label matrix as an RGB image.)
    2020-04-08 21:45:20下载
    积分：1
  • Markov Decision Process matlab程序
    说明：  一个很有用的Markov Decision Process matlab程序(a very useful Markov Decision Process procedures Matlab)
    2005-11-04 16:09:41下载
    积分：1
  • 分割剖面及GRB分量
    主要是对图像的某一部分，做一条线的剖分，然后显示这条线上所有RGB的颜色值(A section of a line is made mainly for a part of the image, and then the color value of all RGB on this line is displayed.)
    2018-01-21 04:16:41下载
    积分：1
  • comperss51
    matlab的图像压缩代码，适合初学者，算法比较简单(Matlab image compression code for beginners, the algorithm is relatively simple)
    2007-04-14 11:51:53下载
    积分：1
  • Medical Image Reader and Viewer
    医疗图像分割，GUI，可视化,能够实现对医疗图像感兴趣区域分割，GUI显示，三维可视化(Medical image segmentation, GUI, visualization)
    2018-06-07 21:49:46下载
    积分：1
  • mmdetection-master
    基于mmdetection框架的深度学习目标检测框架(deep learning object detection based on mmdetection)
    2020-06-19 22:20:02下载
    积分：1
  • MATLABshiyongdaima1
    包括很多实用性的图像处理类源代码 (Including many practical image processing source code。)
    2013-05-10 21:46:25下载
    积分：1
  • jpeg系统实现
    jpeg基本系统编解码实现程序，内附说明文件。(the programs of coding and encoding for then basic system of jpeg.PS:Readme.txt)
    2020-07-03 15:40:01下载
    积分：1
  • segmentation-superpixel
    超像素分割方法，在计算机视觉领域，图像分割（Segmentation）指的是将数字图像细分为多个图像子区域（像素的集合）（也被称作超像素）的过程。超像素有一系列位置相邻且颜色、亮度、纹理等特征相似的像素点组成的小区域。这些小区域大多保留了进一步进行图像分割的有效信息，且一般不会破坏图像中物体的边界信息。(Super pixel Segmentation method, in the field of computer vision, image Segmentation, Segmentation) refers to the digital image Segmentation region for multiple image sequence (the set of pixels) (also known as the pixels) process. Adjacent pixels have a series of position and features such as color, brightness, texture similar to that of small region composed of pixels. Most of these small area retains the further effective information for image segmentation, and generally does not destroy the boundary of the object in the image information.)
    2015-03-31 15:58:59下载
    积分：1
  • artistic-style-transfer-master
    在linux系统中通过卷积神经网络实现图像风格迁移(Image style migration through convolution neural network in linux)
    2021-01-12 23:18:48下载
    积分：1
  • 696516资源总数
  • 106914会员总数
  • 0今日下载

热门标签

Visual C++ matlab C/C++ Java Others Unix_Linux EasyLanguage易语言 Visual Basic C# PDF C++ Delphi VHDL ASP WINDOWS
热门下载

Copyright© 2019-2026 | Powered by Imdn | 浙ICP备16007336号 | IMDN交流 | 联系客服（QQ：3324461878）

本网站资源收集自网络及网站用户上传，若有侵权请邮件至（3324461878@qq.com），核实后我们会在24小时内删除，谢谢！