Posts

model train feature -> ReconNet_dropout -> drop.feature cat[ drop.feature, init.feature] cat at dim=1 ReconNet_dropout dropout ​ shortcut = self.conv1(x) ​ shortcut.features = self.bn0(shortcut.features) ​ shortcut.features = self.act1(shortcut.features) ​ shortcut.features = self.dropout1(shortcut.features) eval metric ???predict_labels = torch.mean(outputs, dim=0, keepdim=True) uncertainty_scores = torch.var(outputs, dim=0, keepdim=True) uncertainty_scores = torch.mean(uncertainty_scores, dim=1)

# If you come from bash you might have to change your $PATH. # export PATH=$HOME/bin:/usr/local/bin:$PATH export TERM="xterm-256color" #防止中文乱码 export LC_ALL=en_US.UTF-8 export LANG=en_US.UTF-8 # Path to your oh-my-zsh installation. # !!! IMPORTANT to use $HOME instead of normal absolute path in windows !!! ZSH="$HOME/.oh-my-zsh" ZSH_CUSTOM=$HOME/.oh-my-zsh/custom # Set name of the theme to load --- if set to "random", it will # load a random theme each time oh-my-zsh is loaded, in which case, # to know which specific one was loaded, run: echo $RANDOM_THEME # See https://github....

Modern CMake 简体中文版 │ CMakeLists.txt │ triangle.cpp │ ├─include │ │ vmath.h │ │ │ ├─glad │ │ glad.h │ │ │ ├─GLFW │ │ glfw3.h │ │ glfw3native.h │ │ │ └─KHR │ khrplatform.h │ └─lib │ glad.c │ └─GLFW glfw3.dll libglfw3.a libglfw3dll.a 用CMake编译跨shell平台cpp代码 CMake 生成，需要显式指定生成器为*“MinGW Makefiles”，避免Windows平台MSVC优先级使CMakelists指定gcc/g++*失效 cmake -G "MinGW Makefiles" -S . -B buil CMake install cmake --build build run exe ./build/*.exe CMakelists cmake_minimum_required(VERSION 3.10) # 设置C语言编译器 set(CMAKE_C_COMPILER "C:/msys64/ucrt64/bin/gcc....

Whisper based Online-Lectures subtitle universal supply method for speed-up learning. Based on the fact that human can read much more faster than listen while speed-up the videos. whisper ./204-17.mp4 --model large-v2 --language Chinese --initial_prompt "以下是 普通话的句子。" export CUDA_VISIBLE_DEVICES='1' TCP / UDP TCP 关注可靠性 / UDP 关注实时性 网络层 端到端 End to End 链路层 点到点 Point to Point SDN Ch.1 互联网：由 TCP / IP协议构成的一组协议 协议：对等实体遵守的规范xxxxxxx(define) TCP 面向连接可靠服务 UDP 无连接不可靠服务 网络边缘(Edge 方形) / 网络核心(Core 圆形)...

https://kodekloud.com/courses/docker-for-the-absolute-beginner/ https://docs.docker.com/get-started/

https://zhuanlan.zhihu.com/p/627356466 数据集 评价指标：PSNR、SSIM、LPIPS 3. NeRF Mip-NeRF https://jonbarron.info/mipnerf/ PE(Positional Encoding)

A official tutorial here Chinese version of this tutor here

Check oh-my-tuna https://github.com/tuna/oh-my-tuna or https://tuna.moe/oh-my-tuna/ conda mirror setting conda config --set show_channel_urls yes create .condarc file to ~/.condarc and open it fill with channels: - defaults show_channel_urls: true default_channels: - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2 custom_channels: conda-forge: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud msys2: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud bioconda: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud menpo: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud pytorch: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud pytorch-lts: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud simpleitk: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud deepmodeling: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/ run conda clean -i clean index pip mirror setting # tsinghua mirror pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple Alternate conda new created envs default dir...

https://www.bilibili.com/video/BV11N4y1g7Z8/ 1 Intro What is computational Imaging? related with CG / CV / Optics … Applications: 光场相机 Light Field Imaging; Non-line-of-sight Imaging(有什么意义？) color: CRE 标准 建议学完后重看 Intro 2. Color, Human Vision System, and Display Ⅰ SPD(Spectral Power Distribution) S，M，L三种锥状细胞(可以简单理解成分别响应为红绿蓝三色的细胞) 人眼获取颜色：SPD 在视网膜(经过人眼LMS曲线)积分为RGB三色信号 这一过程实际上是 高维 -> 3维 的映射，因此必然导致：同色异谱(Metamerism) 颜色感知： Terms: Prism: 棱镜 3. Color, Human Vision System, and Display Ⅱ CIE，XYZ，亮度？ 色彩空间 HSV 4. Cameras 相差 色散(彩色相差) 畸变 光圈 景深 分辨率的物理限制：衍射极限 sensor: Pixel, Photosite response, color filter array, many kinds of sensors…...

msys2 安装mingw w64 $ pacman -S mingw-w64-x86_64-cc pkg-config 在安装gdb $ pacman -S mingw-w64-x86_64-gdb https://github.com/Insdf/Cpp_OpenGL_Setup

First Name: Siyuan Last Name: Yang My web homepage[blog] and academic homepage My github account: https://github.com/Reed-yang Background & Interests: ​ 3D Reconstruction, Neural Rendering, Computer Graphics, Differentiable Rendering Degree: Major in Computer Science at Huazhong University of Science & Technology(HUST) 2021 - 2025 Minor in Philosophy at Huazhong University of Science & Technology(HUST) 2022 - 2025 Research & Industrial Experience: HUST-EPIC-lab 2022.5-present Under the guidance of Associate Professor Xianzhi Li at HUST EPIC Lab, I had the opportunity to engage in research in point cloud 3D reconstruction....

待填： General description of skills, background knowledge, research interests and experience My primary research interests are computer graphics and artificial intelligence, along with associated subfields: neural rendering, differentiable rendering, NeRF, 3D reconstruction, and photorealistic rendering, etc. I've undertaken independent study in many modern computer graphics courses, and attended a cutting-edge graphics summer camp (USTC 2023). Supervised by Professor Xianzhi Li, I have participated in a research work in the field of point cloud 3D reconstruction, aiming for publication in CVPR 2024(joint author)....