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

3D Shape RepresentationsExplicit RepresentationThe description of a scene is explicit, and the 3D representation of the scene can be seen directly, such as mesh, point cloud, voxel and volume which ca

networksetup:macOS上的终端网络配置管理工具什么是 networksetupnetworksetup 是macOS自带的，作为 macOS 操作系统的一部分提供给用户的网络配置管理工具, 用户能在终端通过 networksetup 。管理网络设置和配置。 它提供了用于配置网络首选项、接口、代理、DNS 设置等的各种功能。 基本使用1networksetup -help 1234

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

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

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

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

TransformerModel Architecture Fig.1 Transformer Transformer was firsr used for machine translation with an an encoder-decoder structure, see Fig.1. The input (source) and output (target) se

Tokenization And EmbeddingTokenization Fig.1 Tokenization Encode input sequence (usually setence in NLP) with tokenizers to sequence of integers. For example, 1234>>> inputs = &quo

Data Parallel And Distributed Data ParallelData ParallelProcedure Fig.1 Data Parallel 12345678While iterating: 1. Scatter batch to mini-batch and distribute them across given GPUs 2.