Trending Projects

Implementation of SegNet, a deep convolutional encoder-decoder for semantic pixel-wise labeling.

A book focused on guiding the structure of Machine Learning projects and understanding how ML algorithms work.

An open-source OCR engine developed by SYSU DeepDriving Lab, focused on computer vision tasks.

TableBank is a benchmark dataset for table detection and recognition, useful for building computer vision models.

Implementation of the ConvMixer architecture, a novel neural network design for image classification.

A Python library that generates 3D textured meshes from text prompts using 2D text-to-image models.

MSF is a modular framework for multi-sensor fusion based on an Extended Kalman Filter, useful for robotics and computer vision applications.

A collection of chapter summaries for the Deep Learning Book, making it easier to understand.

Lumina-mGPT 2.0 is a stand-alone autoregressive image modeling tool powered by Python.

A reading list and survey paper on hallucination in large language models (LLMs) for AI-focused developers.

A tutorial course for building AI-powered applications using Stable Diffusion and PyTorch.

A curated list of practical natural language processing tools and libraries in Ruby for developers.

A Python-based face editing tool for Stable Diffusion, a popular AI image generation model.

A Python library for sentiment analysis, text classification, and other machine learning tasks on Weibo data.

A curated list of SLAM (Simultaneous Localization and Mapping) resources for developers working in computer vision and robotics.

Unsupervised language modeling and robust sentiment classification for AI/ML developers.

A PyTorch implementation of a neural radiance field model for talking head synthesis driven by audio.

A series of math-focused large language models for AI-powered coding and analysis

Real-time audio analysis in Python, with visualizations and FFT feature extraction from streaming audio.

Efficient GPU kernels for block-sparse matrix multiplication and convolution, useful for AI/ML developers.

A Jupyter Notebook-based library for exploring and analyzing multimedia datasets at scale.

A next-generation recommendation system library for building AI-powered content discovery platforms.

A comprehensive library for few-shot learning in Python with PyTorch, featuring state-of-the-art algorithms.

Dramatron is a Jupyter Notebook tool that uses large language models to generate coherent scripts and screenplays.

A collection of Jupyter Notebooks focused on building tools and agents for large language models (LLMs).

This repository contains machine learning notes, focused on Jupyter Notebooks, for developers interested in learning and exploring the field.

A Chinese named entity recognition (NER) library built using TensorFlow deep learning.

A TypeScript library for training and deploying machine learning models on Node.js using TensorFlow.

A powerful AI-powered image segmentation tool for developers and designers to quickly annotate and label images.

A curated collection of resources and research related to the geometry of representations in the brain, deep networks, and beyond.

A family of lightweight multimodal models for chatGPT, GPT-4, and other large language models.

Customizable implementation of the self-instruct paper for AI-powered coding tools and workflows.

R-FCN with joint training and Python support for object detection and computer vision tasks.

An image-text multimodal deep learning model for object detection and recognition.

Distributed Computing for AI Made Simple - a Python library for building scalable AI workflows.

A C++ tutorial for the TensorRT deep learning inference engine optimized for NVIDIA GPUs.

Official implementation of the ReStyle StyleGAN encoder, a tool for iteratively refining StyleGAN image generation.

A PyTorch implementation of BigGAN with pretrained weights and conversion scripts for generative AI models.

A collection of Reinforcement Learning algorithms implemented in Python for educational and research purposes.

A collection of papers and code related to 3D computer vision, including SLAM, localization, and more.

Simple reference implementation of GraphSAGE, a graph neural network framework for machine learning.

Autonomous GPT-4 agent platform for building AI-powered applications and workflows.

A benchmark to evaluate language models on various tasks, useful for vibe coders building AI-powered apps.

An AI-powered tool to upscale images by 4x while preserving photo-realistic details, built using TensorFlow.

Build agents controlled by large language models (LLMs) using the LangChain framework.

This is a repository of notes for a developer focused on building with AI tools and frameworks.

A TensorFlow-based CRNN model for scene text recognition, useful for vibe coders working on OCR and computer vision AI.

A codebase for Time-series Generative Adversarial Networks (TimeGAN), a deep learning model for time series data generation.

A Python library that extends the Segment Anything Model (SAM) to enable zero-shot video segmentation with point-based tracking.

A PyTorch-based library for unsupervised learning of depth, disparity, and other visual features from monocular video.