Vision Transformer Vision TransformerInductive biasVision Transformer has much less image-specific inductive bias than CNNs. In CNNs, locality, two-dimensional neighborhood structure, and translation equivariance are ba 2026-04-03 Papers #Computer Vision #Deep Learning
BERT:Bidirectional Encoder Representations from Transformers Input/Output Representations Fig.1 Input Represention For handling a variety of down-stream tasks, the input representation of BERT is able to unambiguously represent both a single sen 2026-04-03 Papers #Deep Learning #Natural Language Processing
Flask + Gunicorn + Nginx 搭建 Web 服务 Flask + Gunicorn + Nginx 搭建 Web 服务FlaskFlask 是一个使用 Python 编写的轻量级 Web 框架,被广泛用于构建 Web 应用程序和 API, 开发者可以通过 Flask 在搭建本地 Web 服务。 123456789from flask import Flask, requestapp = Flask(__name__)@app.route( 2026-04-03 Others #Web
cmake Ceres 配置错误:Found Eigen dependency, but the version of Eigen found () does not exactly match the version of Eigen Ceres was compiled with (3.4.0) Ceres 编译错误: Found Eigen dependency, but the version of Eigen found () does not exactly match the version of Eigen Ceres was compiled with (3.4.0)博主在学习高博的《视觉SLAM14讲》时 cmake 配置过程中遇到了以下问题: Fig. 2026-04-03 Others #Cmake
【Berkeley CS184/284A】Computer Graphics and Imaging 学习笔记 Lecture 1: Introduction… Lecture 2: Drawing TrianglesGCL库的使用见使用文档 Primer on Using Vectors and Matrices in the CGL Library 以及 CGL Vectors Library,此处给出一些文档中没提到的 1234567891011121314151617181920Matrix3x3 2026-04-03 Notes #Computer Graphics
【Berkeley CS285】Deep Reinforcement Learning 学习笔记 Lecture 1: Introduction什么是强化学习 基于学习的决策制定的数学形式化方法(Mathematical formalism for learning-based decision making) 从经验中学习决策和控制的方法(Approach for learning decision making and control from experience) 强化学习与监督学习 2026-04-03 Notes #Deep Learning #Reinforcement Learning
Denoising Diffusion Probabilistic Models Basics of ProbabilityConditional Probability \begin{aligned} P(A, B, C) & = P(C|A, B)P(A, B) = P(C|A, B)P(B|A)P(A) \\ P(B, C|A) & = \frac{P(A, B, C)}{P(A)} = P(C|A, B)P(B 2026-04-03 Papers #Deep Learning #Generative Model
DreamFusion Motivation Applying diffusion models to other modalities has been successful, but requires large amounts of modality-specific training data. 3D assetsare currently designed by hand in modeling softwar 2026-04-03 Papers #AIGC #Computer Vision
Einops:Clear and Reliable Tensor Manipulations with Einstein-like Notation Einops:Clear and Reliable Tensor Manipulations with Einstein-like NotationFundamentalsCore Operations1234567from einops import rearrange, reduce, repeat# rearrange elements according to the patternout 2026-04-03 Python #Python
Generative Adverserial Networks Architecture Fig.1 GAN Architecture The GAN architecture is illustrated in Fig.1 . There are two pieces in GAN architecture —— a generator and a discriminator. The generator is used to gene 2026-04-03 Papers #Deep Learning #Generative Model