张博208-CSDN博客

转载 Distinguish between Beam Search, Random Sampling, Top-K, and Nucleus

省层策略

2024-07-11 16:38:07 43

原创 Stable Diffusion LoRA模型

stable diffusion lora

2024-07-10 13:31:32 122

标题：Adding Conditional Control to Text-to-Image Diffusion Models作者：Lvmin Zhang, Maneesh Agrawala原文链接：https://arxiv.org/pdf/2302.05543.pdf代码链接：https://github.com/lllyasviel/ControlNet大型文本到图像模型的存在让人们意识到人工智能的巨大潜力，这些模型可以通过用户输入简短的描述性提示来生成视觉上吸引人的图像。

2024-07-10 11:46:17 778

原创 RAG（检索增强生成）

retrieval augmented generation

2024-07-09 11:24:07 76

转载 MAE -Masked Autoencoders Are Scalable Vision Learners

本文表明，掩码自编码器 (MAE) 是用于计算机视觉的可扩展自监督学习器。本文的 MAE 方法很简单：屏蔽输入图像的随机patch 并重建丢失的像素。它基于两个核心设计。首先，本文开发了一个非对称的编码器-解码器架构，其中一个编码器只对可见的patches子集（没有掩码tokens）进行操作，以及一个轻量级解码器，它从隐表示和掩码tokens 重建原始图像。其次，本文发现屏蔽输入图像的高比例，例如 75%，会产生一个重要且有意义的自监督任务。结合这两种设计使本文能够有效地训练大型模型：本文

2024-07-08 17:11:08 49

转载 NT-Xent (Normalized Temperature-Scaled Cross-Entropy) Loss Explained and Implemented in PyTorch

loss

2024-07-08 16:47:08 114

原创计算机视觉自监督学习资料

https://zhuanlan.zhihu.com/p/258958247https://zhuanlan.zhihu.com/p/682212621

2024-07-08 16:45:25 119

原创 LLM 资料

从 FlashAttention 到 PagedAttention, 如何进一步优化 Attention 性能 Transformer综述！100多种不同的视觉Transformer

2024-07-08 15:27:59 108

原创 Bert 变种， T5模型

NLP-预训练模型-2019-NLU：DistilBERT【 BERT模型压缩】【模型大小减小了40%（66M），推断速度提升了60%，但性能只降低了约3%】_distillbert-CSDN博客https://zhuanlan.zhihu.com/p/673535548

2024-07-08 14:23:15 339

原创 EINSUM IS ALL YOU NEED

Tim Rocktäschelhttps://medium.com/ibm-data-ai/einsum-an-easy-intuitive-way-to-write-tensor-operation-9e12b8a80570Understanding einsum for Deep learning: implement a transformer with multi-head self-attention from scratch | AI Summer

2024-07-07 19:07:06 125

原创大模型思维链（Chain-of-Thought）技术原理

推理链

2024-07-04 18:11:13 260

原创 DINO DINO2

【大模型系列】根据文本检索目标(DINO/DINOv2/GroundingDINO)_dino目标检测-CSDN博客

2024-07-02 14:32:13 132

原创全模态自监督算法—data2vec

https://zhuanlan.zhihu.com/p/471494010Data2Vec：视觉、语音和语言的语境化目标表征的高效自监督学习_data2vec模型-CSDN博客

2024-07-02 11:43:21 107

转载 Vision Transformers, Explained

Vision Transform details

2024-06-14 17:08:12 32

原创 Multiclass Classification vs Multi-label Classification

多分类和多标签

2024-06-11 14:40:34 763

原创 How does vmap() function work?

According to JAX docsfile on vmap, jax.vmap(function, in_axes=0, out_axes=0) returns a function which maps the function one specified over using in_axes and stack them together using out_axes

2024-06-04 11:44:32 644

转载 JAX VMAP Simplified: An Easy Introduction for Beginners

WMAP

2024-06-04 10:03:36 70

原创 Automatic Differentiation Part 2

自动微分

2024-06-01 16:59:57 901

原创 Automatic Differentiation Part 1

自动微分

2024-06-01 16:53:18 833

转载 CUDA Programming: An Introduction to GPU Architecture

gpu 架构

2024-06-01 09:22:52 34

原创 AutoGraph

graph details

2024-05-22 10:32:49 970

转载将python函数转化为tensorflow图函数

tensorflow 基础

2024-05-22 10:30:22 40

原创 Multiprocessing Event Object In Python

Event

2024-04-17 10:55:13 839

原创 Multiprocessing Freeze Support in Python

You can add support for multiprocessing when freezing your code via the multiprocessing.freeze_support() function.In this tutorial you will discover how to add freeze support for multiprocessing in your Python program.You can package your code with a Pytho

2024-04-17 10:38:29 1258

原创 Understand torch.scatter

scatter 理解

2024-04-10 16:16:03 652

转载 NVIDIA MPS总结

MPS多进程服务（Multi-Process Scheduling）是CUDA应用程序编程接口（API）的替代二进制兼容实现。从Kepler的GP10架构开始，NVIDIA就引入了MPS（基于软件的多进程服务），这种技术在当时实际上是称为HyperQ ，允许多个流（stream）或者CPU的进程同时向GPU发射Kernel函数，结合为一个单一应用程序的上下文在GPU上运行，从而实现更好的GPU利用率。在单个进程的任务处理，对GPU利用率不高的情况下是非常有用的。

2024-02-06 10:02:34 409

原创 CUDA Thread Indexing

CUDA Thread Indexing。

2023-07-10 16:45:58 410

转载 Facebook如何训练超大模型系列

我们在前文介绍过，微软 ZeRO 可以对一个万亿参数模型可以使用 8 路模型并行、64 路管道并行和 8 路数据并行在 4,096 个 NVIDIA A100 GPU 上进行扩展。而FSDP（Fully Sharded Data Parallel）是Facebook 深度借鉴微软ZeRO之后提出的PyTorch DDP升级版本，可以认为是对标微软 ZeRO，其本质是 parameter sharding。Parameter sharding 就是把模型参数等切分到各个GPU之上。

2023-06-21 15:31:24 396

原创大模型训练技术论文

大模型训练框架论文

2023-06-21 11:23:43 1155

转载大模型训练框架Megatron原理系列转载

NVIDIA Megatron 是一个基于 PyTorch 的分布式训练框架，用来训练超大Transformer语言模型，其通过综合应用了数据并行，Tensor并行和Pipeline并行来复现 GPT3，值得我们深入分析其背后机理。本系列大概有6～7篇文章，通过论文和源码和大家一起学习研究。本文把 Megatron 的两篇论文/一篇官方PPT 选取部分内容，糅合在一起进行翻译分析，希望大家可以通过本文对 Megatron 思路有一个基本了解。

2023-06-20 11:34:03 3962

转载人脸识别损失函数(Center-Loss、A-Softmax、AM-Softmax、ArcFace)

引用

2023-05-30 18:22:10 407

原创 linkname, soname and realname

As you may already know, the linker1 option should be used to specify the name of the library which is needed by your application when it was compiled. For example, if we write a program which utilize libjpeg, we should specify explicitly when we compile

2023-05-22 13:26:11 596

原创 Linux资料

学习

2023-05-06 15:32:29 71

原创通过例子深入了解c++/c的构建系统

C/C++ is the mother of many popular programming languages out there today, all the fancy programming languages we use today like Python, JavaScript are built using C/C++. For example, the standard python interpreter is built using C and the most popular J

2023-04-25 13:37:04 1743 4

原创 PixelShuffle上采样原理

PixelShuffle是目前通用上采样upsample技术中性能最好的。PixelShuffle现已广泛应用在如图像分割等计算机视觉问题上，和。一起成为了神经网络中最常用的两种上采样技术。

2023-04-12 11:36:45 162

原创 @contextmanager 和yield 的结合使用法

上面这个例子，我们可以把print('1') 和 print('3')看成是try和except，要执行代码的部分就是他们中间的部分,进行以下更改。先执行commit(),遇到yield后，跳出来执行sql1,sql2，然后再进入commit()执行上一次跳出来的位置。所以要引用装饰器@contextmanager，它需要与with语法结合使用。但是每次都这样try...except...就会显得很重复。

2023-04-06 17:45:34 297

原创 Understanding Diffusion Probabilistic Models (DPMs) 扩散模型，最好资料

diffusion model step by step

2023-03-28 17:59:32 960 1

原创扩散模型学习

diffusion model 学习资料呢

2023-03-27 16:24:50 80

llama3 study

2024-07-25

tensorrt ppt资料

tensorrt的教程，和相关的资料，案例，供大家学习

2024-07-09

GPU-知识点资料合集

bank_conflicts coalescing

2023-08-03

Pro Go The Complete Guide -go语言学习最新书籍

Best-selling author Adam Freeman explains how to get the most from Go, starting from the basics and building up to the most advanced and sophisticated features. You will learn how Go builds on a simple and consistent type system to create a comprehensive and productive development experience that produces fast and robust applications that run across platforms 参见：https://www.amazon.com/Pro-Go-Complete-Programming-Efficient/dp/1484273540/ref=sr_1_1?crid=1K22H21ZB1EIZ&keywords=Pro+Go+The+Complete+G

2023-06-19

扩散模型讲义美国大学之一

2023-03-28

Advanced_Programming_in_the_UNIX_Environment，_3rd

Advanced_Programming_in_the_UNIX_Environment，_3rd_Edition very good book for unix user

2018-11-30

Pattern_Recognition_and_Big_Data

Pattern_Recognition_and_Big_Data 很好的资源，对于学习大数据的朋友来说

2018-09-07

图论引导中文

中文版本图论引导

2018-09-05

现代图论--------------

现代图论研究生教材适合大家学习与总结了

2018-09-05

Deep_Learning_Quick_Reference

Deep_Learning_Quick_Reference, a cookbook for deep learning

2018-09-01

Convex Optimization Algorithms

Convex Optimization Algorithms, understand convex optimization algorithms, this is good chances

2018-09-01

Guide.to.Medical.Image.Analysis.Methods.and.Algorithms

Guide.to.Medical.Image.Analysis.Methods.and.Algorithms very good book for computer vision

2018-09-01

machine learning algorithm

machine learning algorithm 想学习的可以好好学学了

2018-04-02

Python Machine Learning Machine Learning and Deep Learning

Python Machine Learning Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition 很受推荐

2018-03-27

Data Structures and Algorithms Using Python and C++

Data Structures and Algorithms Using Python and C++ 数据结构与算法方面的书籍

2018-03-27

R_for_Data_Science

R_for_Data_Science_－_Import，_Tidy，_Transform，_Visualize_and_Model_Data.rar

2018-03-27

深度学习之Pytorch

国内少有的学习 pytorch的资料,适合初学者, 希望对大家有帮助,清晰版本

2018-03-27

Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow

Table of Contents Giving Computers the Ability to Learn from Data Training Simple Machine Learning Algorithms for Classification A Tour of Machine Learning Classifiers Using Scikit-Learn Building Good Training Sets - Data Preprocessing Compressing Data via Dimensionality Reduction Learning Best Practices for Model Evaluation and Hyperparameter Tuning Combining Different Models for Ensemble Learning Applying Machine Learning to Sentiment Analysis Embedding a Machine Learning Model into a Web Application Predicting Continuous Target Variables with Regression Analysis Working with Unlabeled Data - Clustering Analysis Implementing a Multilayer Artificial Neural Network from Scratch Parallelizing Neural Network Training with TensorFlow Going Deeper - The Mechanics of TensorFlow Classifying Images with Deep Convolutional Neural Networks Modeling Sequential Data using Recurrent Neural Networks

2018-03-17

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

llama3 study

tensorrt ppt资料

GPU-知识点资料合集

Pro Go The Complete Guide -go语言学习最新书籍

扩散模型讲义 美国大学之一

Advanced_Programming_in_the_UNIX_Environment，_3rd

Pattern_Recognition_and_Big_Data

图论引导 中文

现代图论--------------

Deep_Learning_Quick_Reference

Convex Optimization Algorithms

Guide.to.Medical.Image.Analysis.Methods.and.Algorithms

machine learning algorithm

Python Machine Learning Machine Learning and Deep Learning

Data Structures and Algorithms Using Python and C++

R_for_Data_Science

深度学习之Pytorch

Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow

Approximate.Dynamic.Programming.2011

计算群体智能基础

Swarm Intelligence Principles Advances and Applications

Reinforcement Learning With Open A TensorFlow and Keras Using Python.pdf

Fundamentals of Deep Learning完整非扫描版本2017

Data Wrangling with R

NLTK基础教程-用NLTK和Python库构建机器学习应用2017-06

Text Mining in Practice with R 2017.12

Text_Mining－From_Ontology_Learning_to_Automated_Text_Processing_Applications

Python Natural Language Processing最新版本

Mastering Scipy

Elegant SciPy

Tensorflow 机器学习参考手册2007

reinforcement learning An Introduction 第二版

Spark大数据处理技术 带标签 完整版

TensorFlow技术解析与实战 高清晰完整版- 2017新书

TENSORFLOW深度学习

模式分类11

集体编程智慧

敏捷软件开发：原则、模式与实践

面向对象方法原理与实践

ollydbg 教程

空空如也

扩散模型讲义美国大学之一

图论引导中文

Spark大数据处理技术带标签完整版

TensorFlow技术解析与实战高清晰完整版- 2017新书