AI ML - chanandrew96/MyLearning GitHub Wiki
Download Models, Dataset
50 free Machine Learning Datasets: Image Datasets
Orange Data Mining
Kaggle
HuggingFace
OCR related
TrOCR
LayoutLM / LayoutLMV2
LayoutLMV3
CRAFT-pytorch
For text detection
LASER
For tokenizer
CDLA
CDLA: A Chinese document layout analysis (CDLA) dataset
Chinese Labeled text data
PaddleOCR
【OCR入门】一、基于深度学习的OCR技术导论和PaddleOCR
HarvestText
HarvestText : A Toolkit for Text Mining and Preprocessing
GitHub - HarvestText
用HarvestText自动识别实体及别名，用于实体链接分析
NLP
「59页PDF」自然语言处理 NLP 基本概念大全（免费下载）
變形金剛與抱臉怪---NLP 應用開發之實戰 系列
# Day6-初探 Hugging Face Dataset Library
nlpaug
Image Generate
Unconditional Image Generation - HuggingFace
Microsoft DALL‑E
Chatbot / Question Answering Model
Question Answering Model based on SQuAD
NLP on Flask web
手把手教你如何开发一个NLP机器学习模型,并将它部署在Flask的Web平台上(译)
Neural Network
用Python实现神经网络（附完整代码）！
神经网络15分钟入门！足够通俗易懂了吧
史上最详细循环神经网络讲解（RNN/LSTM/GRU）
CNN
Data Annotation / Labeling
Doccano
Label Studio
LabelImg
LabelImg 影像標註工具使用教學，製作深度學習用的資料集
Text Detection
clovaai/deep-text-recognition-benchmark
clovaai/CRAFT-pytorch
Donut
Hugging Face - Donut
GitHub - Donut
Visual NLP + Donut Model
Question Answering in Visual NLP: A Picture is Worth a Thousand Answers
Document Question Answering Model
Data Set
CUDA
SQUAD
DocVQA
LongNet
arxiv - LongNet
arxiv PDF - LongNet
Microsoft’s LongNet Scales Transformer to One Billion Tokens
【骆驼读论文】微软发布1B长度的LongNet;长对话模型测评LongEval;工具模型测评ToolQA等12篇串读
GitHub - LongNet
DocQuery
Hugging Face Space - DocQuery: Document Query Engine
GitHub - DocQuery
CRF Model
PaLM (Deep Learning)
arxiv - PaLM
GitHub - PaLM
PaLM API & MakerSuite: an approachable way to start prototyping and building generative AI applications
LangChain (Question Answering Models)
GitHub - LangChain
4 Ways to Do Question Answering in LangChain
The easiest way to work with large language models?
tutorials-LangChain QA
LangChain 中文入门教程
LangChain - Quickstart
LangChain - Chains
Pipeline
到底什么是Pipeline？
机器学习tips：什么是pipeline？
Sklearn中Pipeline的用法介绍 （使用Pipelines简化Python机器学习代码）
Transformers从零到精通教程——Pipeline
使用HuggingFace的Transformers库的学习笔记(pipeline实战+官方readme文件的解读）
Transformer
QA
Transformers预训练模型使用：抽取式问答 Extractive Question Answering
Transformers库Question Answering任务样例
Question Answering
Qanary
txtai
FiD
BERT
中文文章的抽取式摘要—使用bert-extractive-summarizer
没有模型训练情况下用BERT做文本分类
KeyBERT
SpaCy
Serverless & Text Extraction
Serverless 实战：如何结合 NLP 实现文本摘要和关键词提取?
Text Classification
DataScience_ArtificialIntelligence_Utils
OpenMMLab
Pickle - Python
GraphQL
GraphQL
一文看懂GraphQL 是什么？都有哪些优缺点- 红帽
Vector DB
What is a Vector Database & How Does it Work? Use Cases + Examples
The Top 5 Vector Databases
Vector DB 初探與 Weaviate DB 教學
Gemini
Google Gemini: What We Know So Far
Google新AI模型「Gemini」將推出！曝算力比GPT-4強五倍，能打敗OpenAI？
scikit-learn
What is scikit-learn and use cases of scikit-learn?
Who is using scikit-learn?
SciKit - Examples
Installing scikit-learn
Tensorflow
The Sequential model
The Functional API
TensorFlow Core
TensorFlow 2 quickstart for beginners
基本分类：对服装图像进行分类
Introduction to Tensors
【動手玩系列#2】TensorFlow 帶你無師自通成為植物學家
Keras和Tensorflow（CPU）安装、Pytorch（CPU和GPU）安装以及jupyter使用虚拟环境
The Difference Between The Augmentor Library and TensorFlow’s flow_from_directory
Keras
Introduction to Keras for engineers
Keras Tutorial For Beginners | Keras For Deep Learning | Deep Learning Tutorial | Simplilearn
Gensim (NLP)
Python音頻預處理
使用Python对音频文件进行数据预处理
音频预处理(数据增强方法总结)
Cocos2d-x中使用音频CocosDenshion引擎介绍与音频文件的预处理
Fine-tuning
ChatGPT 應用系統開發(二) -- 微調(Fine-tuning)企業專屬的模型
BART
Multi-Document Summarization with BART
AutoML
Google 機器學習三大服務：AutoML, Cloud ML Engine, ML API 介紹與比較
word2vec
CSDN - word2vec
从Word2Vec到BERT：上下文嵌入 (Contextual Embedding) 最新综述论文.pdf
DALI
NVIDIA DALI从入门到放弃之三：Data Loading
Text-To-Image
Generative AI 新世界 | 走进文生图（Text-to-Image）领域
一分钟跑出 AI 图像的生成平台(StableStudio)
AutoGPT
LLMs
Generative AI 新世界 | 大型语言模型（LLMs）概述
kwprocessor
Feature Engineering
特征工程到底是什么？
特征工程到底是什么？
特征工程到底是什么？
Kaggle
Kaggle入门，看这一篇就够了
[資料分析&機器學習] 第1.3講：Kaggle介紹
PyTorch
Learn PyTorch for deep learning in a day. Literally.
Pytorch 基本介紹與教學
【深度学习理论】一文搞透pytorch中的tensor、autograd、反向传播和计算图
什麼是 PyTorch：完整指南
PyTorch 简介
深度學習新手村：PyTorch入門
手刻 Deep Learning -第壹章-PyTorch入門教學-基礎概念與再探線性迴歸
Deep Learning (DL)
深度学习之 Keras vs Tensorflow vs Pytorch 三种深度学习框架
Deep Learning for Natural Language Processing with Pytorch
手刻 Deep Learning — 第零章 — 線性回歸
手刻 Deep Learning — 第零章 — 微分觀念入門
ImageNet
Download ImageNet
ImageNet Large Scale Visual Recognition Challenge (ILSVRC)
Numpy
NumPy: Get the number of dimensions, shape, and size of ndarray
SIFT特征
SIFT特征点
SIFT特征提取分析
SIFT 特征详解
SIFT - Scale-Invariant Feature Transform
Sift算子特征点提取、描述及匹配全流程解析
PCA-SIFT
SIFT vs SURF
LIME
复杂模型局部可解释方法——LIME
模型无关可解释方法LIME 和SHAP概述
Model Explainability 可解釋模型
A Look Into Global, Cohort and Local Model Explainability
Local Model-Agnostic Methods
Machine Learning (ML) Model
How to Build ML Models in a Local Machine and Google Colab at the Same Time?
Softmax
Learning Materials
🔥Data Science Full Course 2022 | Data Science | Data Science For Beginners | Simplilearn
How Deep Neural Networks Work - Full Course for Beginners
w3school - Machine Learning
w3school CN - AI人工智能 最常见的机器学习算法
巨樹磐石
初學者學演算法｜從時間複雜度認識常見演算法