Search Results for "learning" - Page 88
Sort By:
Showing 4819 open source projects for "learning"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
The fastai book
The fastai book, published as Jupyter Notebooks
These notebooks cover an introduction to deep learning, fastai, and PyTorch. fastai is a layered API for deep learning; for more information, see the fastai paper. These notebooks are used for a MOOC and form the basis of this book, which is currently available for purchase. It does not have the same GPL restrictions that are on this repository. The code in the notebooks and python .py files is covered by the GPL v3 license; see the LICENSE file for details. -
2
NSFW Data Scraper
Collection of scripts to aggregate image data
...The scripts automate the process of downloading and organizing large volumes of images, significantly reducing the manual effort required to build training datasets. The project was originally created to support research and development of machine learning models capable of identifying explicit or sensitive visual content. -
3
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. Prepare your own dataset with images and labels first. For labeling images, you can use tools like Labelme or CVAT. One more thing worth noting is that you should also implement pull_item and load_anno method... -
4
LayoutParser
A Unified Toolkit for Deep Learning Based Document Image Analysis
With the help of state-of-the-art deep learning models, Layout Parser enables extracting complicated document structures using only several lines of code. This method is also more robust and generalizable as no sophisticated rules are involved in this process. A complete instruction for installing the main Layout Parser library and auxiliary components. Learn how to load DL Layout models and use them for layout detection. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
Faster-Rcnn
This is a pytorch implementation library of faster-rcnn
...The repository includes scripts for training, prediction, evaluation, annotation generation, and model summary inspection. It supports backbone options through pretrained VGG and ResNet weights, making it useful for comparing feature extractors. The project also includes learning rate scheduling through step and cosine methods, optimizer choices between Adam and SGD, adaptive learning rate behavior based on batch size, image cropping, FPS testing, video prediction, and batch prediction. It is a practical reference for users who want a more classical two-stage detector workflow in PyTorch. -
6
PyTorch Handbook
The pytorch handbook is an open source book
...The material is written with a practical focus so that readers can follow along and run the provided examples successfully. Each tutorial is tested to ensure that the code runs correctly, making the repository particularly useful for beginners who want reliable learning materials. The handbook emphasizes hands-on learning through real code examples rather than purely theoretical explanations. -
7
EZStacking
EZStacking is Jupyter notebook generator for machine learning
EZStacking is Jupyter notebook generator for supervised learning problems using Scikit-Learn pipelines and stacked generalization. EZStacking handles classification and regression problems for structured data. It can also be viewed as a development tool, because a notebook generated with EZStacking contains: -an exploratory data analysis (EDA) used to assess data quality - a modelling producing a reduced-size stacked estimator - a server returning a prediction, a measure of the quality of input data and the execution time. -
8
Awesome Conformal Prediction
A professionally curated list of awesome Conformal Prediction videos
...It is not a software library itself but a directory of resources for those wanting to learn or work with conformal prediction and uncertainty quantification. This exceptional resource is the culmination of my PhD journey in Machine Learning, specializing in Conformal Prediction under the supervision of its creator, Prof. Vladimir Vovk. Since 2015, I have painstakingly gathered these invaluable resources, and upon completing my PhD (my thesis, "Machine Learning for Probabilistic Prediction," can be found in the "Theses" section), I am thrilled to share my expertise with the global machine learning community. ... -
9
RLCard
Reinforcement Learning / AI Bots in Card (Poker) Games
RLCard is a toolkit for reinforcement learning research on card games. It includes several popular card games and focuses on learning algorithms for imperfect information games like poker and blackjack. -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
10
30 Days of Elixir
A walk through the Elixir language in 30 exercises
...This incremental learning format allows developers to build confidence and understanding while maintaining consistent progress. As one of the early and influential resources in the Elixir community, 30-days-of-elixir remains a valuable guide for self-learners and newcomers to the functional programming paradigm. -
11
PromptSource
Toolkit for creating, sharing and using natural language prompts
PromptSource is a toolkit for creating, sharing and using natural language prompts. Recent work has shown that large language models exhibit the ability to perform reasonable zero-shot generalization to new tasks. For instance, GPT-3 demonstrated that large language models have strong zero- and few-shot abilities. FLAN and T0 then demonstrated that pre-trained language models fine-tuned in a massively multitask fashion yield even stronger zero-shot performance. A common denominator in these... -
12
RxSwift Chinese Documentation
RxSwift Chinese Documentation
This is an RxSwift Chinese document. Now that reactive programming is becoming more and more popular, we can't stop the craze. This document integrates RxSwift documentation, RxJS documentation, ReactiveX documentation and some of the author's personal opinions. The purpose is to allow everyone to quickly get started with reactive programming. Although this document is mainly about RxSwift , developers using other reactive frameworks can also benefit from it, such as: ReactiveCocoa , RxJava... -
13
SpringBoot Labs
A repository covering six columns
SpringBoot-Labs is a comprehensive learning and reference repository created by yudaocode that explores advanced concepts, features, and best practices in Spring Boot development. The project provides an extensive collection of example modules, each demonstrating a specific framework integration or architectural pattern within the Spring ecosystem. Topics include web development, microservices, security, messaging, distributed systems, DevOps deployment, and cloud-native application design. ... -
14
Fashion-MNIST
A MNIST-like fashion product database
...Each image has a resolution of 28 by 28 pixels and belongs to one of ten clothing classes, making it suitable for evaluating classification models. Because the dataset represents real-world objects rather than handwritten digits, it offers a more challenging benchmark for testing machine learning algorithms. -
15
DeepLabv3 Plus
Encoder-Decoder with Atrous Separable Convolution
...It provides pretrained weight workflows for MobileNetV2 and Xception backbones and notes that the correct backbone should be selected during training and prediction. The project also supports multi-GPU training, multiple backbones, learning rate schedules with step and cosine options, optimizer selection, and adaptive learning rate behavior based on batch size. It is useful for users who want a stronger semantic segmentation baseline than U-Net for scene-level segmentation tasks. -
16
MAE (Masked Autoencoders)
PyTorch implementation of MAE
MAE (Masked Autoencoders) is a self-supervised learning framework for visual representation learning using masked image modeling. It trains a Vision Transformer (ViT) by randomly masking a high percentage of image patches (typically 75%) and reconstructing the missing content from the remaining visible patches. This forces the model to learn semantic structure and global context without supervision. -
17
EasyNLP
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
...It is built with scalable distributed training strategies and supports a comprehensive suite of NLP algorithms for various NLP applications. EasyNLP integrates knowledge distillation and few-shot learning for landing large pre-trained models, together with various popular multi-modality pre-trained models. It provides a unified framework of model training, inference, and deployment for real-world applications. It has powered more than 10 BUs and more than 20 business scenarios within the Alibaba group. It is seamlessly integrated to Platform of AI (PAI) products, including PAI-DSW for development, PAI-DLC for cloud-native training, PAI-EAS for serving, and PAI-Designer for zero-code model training. -
18
MyPoorWebServer
Demonstrates fundamental HTTP server implementation principles
MyPoorWebServer is a C/C++-based web server project that demonstrates fundamental HTTP server implementation principles drawn from classic network programming literature and high-performance server design books. The repository contains source code that implements a basic HTTP server, intended to be compiled and run from the command line, exposing introductory web server functionality such as serving static HTML files and handling simple POST requests. It was originally developed as a resume... -
19
Terminals Are Sexy
A curated list of Terminal frameworks, plugins & resources
This repository is a curated, community-driven collection of tools, tips, themes, and resources that make working in the terminal more productive and enjoyable. It pulls together high-quality links to terminal emulators, shells, prompts, plugins, fonts, color schemes, and command-line utilities, alongside learning materials for sharpening everyday CLI skills. The list favors practical, well-maintained projects and is organized so you can quickly discover alternatives for common tasks (navigation, search, networking, monitoring, text processing, and more). It also points to customization ideas—prompts, themes, and fonts—that help you craft a clear, legible, and pleasant environment. ... -
20
The Lemur Project
Search engine and data mining applications and ClueWeb datasets.
The Lemur Project develops search engines, browser toolbars, text analysis tools, and data resources that support research and development of information retrieval and text mining software, including the Indri search engine in C++, the Galago search engine research framework in Java, the RankLib learning to rank library, ClueWeb09 and ClueWeb12 datasets and the Sifaka data mining application. -
21
Texar-PyTorch
Integrating the Best of TF into PyTorch, for Machine Learning
Texar-PyTorch is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks. Texar provides a library of easy-to-use ML modules and functionalities for composing whatever models and algorithms. The tool is designed for both researchers and practitioners for fast prototyping and experimentation. Texar-PyTorch was originally developed and is actively contributed by Petuum and CMU in collaboration with other institutes. ... -
22
Coding-Guide
Repository of coding guidelines, developer notes, learning resources
The Coding-Guide repository is a personal repository of coding guidelines, developer notes, learning resources, and documentation spanning topics from front-end to full-stack, coding practices, and software development tips. The repository appears to be maintained by “ecmadao” and intended as a reference/knowledge base of best practices, notes, style conventions, and reminders. The content is typically documentation, markdown files, code snippets, and tutorials, rather than a coherent, packaged software tool. ... -
23
LeetCode Python
LeetCode Solutions: A Record of My Problem Solving Journey
This repository is a comprehensive personal journal of LeetCode problem-solving journey. It includes detailed solutions with code, algorithm insights, data structure summaries, Anki flashcards, daily challenge logs, and future planning sections. -
24
MySQL Tutorial
Example-driven guide to MySQL
...The repository also touches on user management, permissions, backups, and common operational tasks that arise in production. Throughout, the emphasis is on clear SQL examples and short explanations that can be tested immediately in a local instance. It serves both as a learning track for newcomers and as a handy reference for developers who need to refresh core MySQL skills. -
25
Stitches
CSS-in-JS with near-zero runtime, SSR, multi-variant support
...Stitches avoids unnecessary prop interpolations at runtime, making it more performant than other styling libraries. Packed full of useful features like theming, smart tokens, css prop, as prop, utils, and a fully-typed API. Stitches has a fully-typed API, to minimize the learning curve, and provide the best possible developer experience. Stitches has a dedicated React lib, but @stitches/core works with any framework including Vue, Svelte, and even vanilla HTML. Variants are first-class citizens of Stitches. With multiple variants, compound variants, and default variants, you can design composable component APIs which are typed automatically. ...