Advanced Methods and Deep Learning+in Computer Vision2021

图切RANSAC 论文中提出的图切RANSAC算法：Daniel Barath和Jiri Matas； Graph-Cut RANSAC，计算机视觉和模式识别会议，2018年。可从以下获得： CVPR教程解释了该方法。 有关单应性，基本矩阵，基本矩阵和6D姿态估计的实验，显示在2020年的RANSAC教程的相应中。 安装C ++ 要构建和安装仅C ++的GraphCutRANSAC ，请克隆或下载此存储库，然后通过CMAKE生成项目。 $ git clone https://github.com/danini/graph-cut-ransac $ cd build $ cmake .. $ make 安装Python包并编译C ++ python3 ./setup.py install 或者 pip3 install -e . 示例项目 要构建显示基本矩阵，单应性和基本矩阵

FCOS检测算法在VOC数据集上的训练模型，直接下载可进行inference。配合代码https://github.com/leviome/fcos_pure 使用。具体教程看README.

MIT-6.0001 该库包括课程中我对问题集的解决方案

MIT-6.0001-Python中的计算机科学和程序设计导论 麻省理工学院的课程作业

ABSTRACT In the last few years, power dissipation has become an important design constraint, on par with performance, in the design of new computer systems. Whereas in the past, the primary job of the computer architect was to translate improvements in operating frequency and transistor count into performance, now power efficiency must be taken into account at every step of the design process. While for some time, architects have been successful in delivering 40% to 50% annual improvement in processor performance, costs that were previously brushed aside eventually caught up. The most critical of these costs is the inexorable increase in power dissipation and power density in processors. Power dissipation issues have catalyzed new topic areas in computer architecture, resulting in a substantial body of work on more power-efficient architectures. Power dissipation coupled with diminishing performance gains, was also the main cause for the switch from single-core to multi-core architectures and a slowdown in frequency increase. This book aims to document some of the most important architectural techniques that were invented, proposed, and applied to reduce both dynamic power and static power dissipation in processors and memory hierarchies. A significant number of techniques have been proposed for a wide range of situations and this book synthesizes those techniques by focusing on their common characteristics.

Structure and Interpretation of Computer Programs 经典的编程教程SICP 之 Python 描述，中文版。值得收藏。 译本参照的原版在此 http://www-inst.eecs.berkeley.edu/~cs61a/sp12/book/ 翻译版权归译者。

We have been studying various types of computer-generated holograms for three-dimensional (3D) displays both for a real-time holographic video display and a hard copy, or a printed hologram. For the hard copy output, we have developed a direct fringe printer, which is achieved to print over 100 gigapixels computer-generated hologram with 0.44-\mu m pitch. In this paper, we introduce our recent progresses on the rainbow hologram, the cylindrical holograms, and the disk hologram for 3D display.

pytorch-randaugment RandAugment的非官方PyTorch重新实现。 大部分代码来自 。 介绍 可以使用RandAugment对感兴趣的数据集训练模型，而无需单独的代理任务。 通过仅调整两个超参数（N，M），您可以实现具有竞争优势的AutoAugments性能。 安装 $ pip install git+https://github.com/ildoonet/pytorch-randaugment 用法 from torchvision . transforms import transforms from RandAugment import RandAugment transform_train = transforms . Compose ([ transforms . RandomCrop ( 32 , padding = 4 ), t

PCSS PCSS是百分比更接近的软阴影技术的C ++ / OpenGL实现。 在我的真实感渲染博士课程中开发。 视频：