Coding & Development

awesome-diffusion-models-in-low-level-vision is a comprehensive, open-source GitHub repository dedicated to curating papers related to Diffusion Models (DMs) in the field of low-level vision. It serves as an invaluable resource for researchers, academics, and practitioners looking to stay updated on the latest advancements and foundational works in this rapidly evolving area. The repository is meticulously organized, featuring sections on general-purpose and task-specific image restoration, extended diffusion models, medical image analysis, remote sensing, and video-related tasks. It also includes recommended surveys, large-scale datasets for pre-training, and evaluation metrics, making it a one-stop hub for anyone working with DMs in low-level vision. Contributions are welcomed through issues and pull requests, fostering a collaborative environment for knowledge sharing.

awesome-deepbio is a curated, open-source list of deep learning applications specifically tailored for the field of computational biology. This GitHub repository serves as an invaluable resource for researchers, academics, and practitioners seeking to explore the intersection of deep learning and biological problems. It meticulously compiles research papers, often including links to their implementations, covering a wide array of topics from protein homology detection and contact map prediction to genetic variant annotation and drug discovery. The list is organized chronologically by publication date, making it easy to track the evolution and advancements in the field. It is freely available and constantly updated, providing a dynamic overview of cutting-edge deep learning techniques applied to biological data.

Awesome-Deepfakes-Detection is a curated collection of resources dedicated to deepfake detection, hosted on GitHub. It serves as a valuable hub for researchers and practitioners by compiling an extensive list of datasets, academic papers, and code related to the identification and analysis of deepfakes. The repository is meticulously organized, categorizing resources by various detection methodologies such as spatiotemporal, frequency-based, generalization, and multi-modal approaches. It also includes information on deepfake detection competitions and tools, making it an indispensable reference for anyone working on combating synthetic media. The open-source nature of the repository encourages community contributions, ensuring it remains up-to-date with the latest advancements in the field.

awesome-detection-transformer is a curated collection of research papers focusing on the application of transformer models for object detection and segmentation in computer vision. The repository is organized by research fields, making it easy for researchers and practitioners to navigate and find relevant studies. It includes papers on various aspects such as DETR, open-vocabulary and multi-modal detection, 3D object detection, segmentation, and pose estimation. The project also lists useful toolboxes like detrex and mmdetection, which are dedicated to transformer-based object detectors. This open-source GitHub repository encourages contributions from the community to ensure its comprehensiveness and accuracy.

awesome-open-data-annotation is a comprehensive, curated list of open-source tools designed for data annotation and labeling, crucial for machine learning workflows. The repository categorizes tools by data type, including multi-modal, text, images, audio, and video, making it easy to find specific solutions. Each entry provides a brief description and license information. The list is actively maintained and welcomes contributions, ensuring its relevance and utility for developers and data scientists looking to implement data-centric MLOps practices. It serves as a valuable resource for identifying functional and well-supported open-source options.

awesome-attention-mechanism-in-cv is an open-source GitHub repository providing a curated list of attention mechanisms and plug-and-play modules specifically for computer vision applications. This resource is designed to assist researchers and developers by offering a comprehensive collection of relevant papers, their publication links, and associated GitHub repositories. The list covers various categories including Attention Mechanisms, Dynamic Networks, Plug and Play Modules, and Vision Transformers. It aims to provide a quick reference for understanding and implementing different attention-based techniques, although it acknowledges that not all modules may be included due to the vastness of the field. Users are encouraged to contribute suggestions and improvements to enhance the list's completeness.

awesome-automl-papers is a comprehensive, curated list of resources dedicated to Automated Machine Learning (AutoML). This open-source project compiles a wide array of materials including academic papers, insightful articles, practical tutorials, informative slides, and relevant projects. It serves as an invaluable resource for anyone looking to understand or stay abreast of the rapidly evolving AutoML landscape. The repository covers key areas such as Automated Data Clean, Automated Feature Engineering, Hyperparameter Optimization, Meta-Learning, and Neural Architecture Search. It also provides an overview of various AutoML approaches and their applications, making it a central hub for both newcomers and experienced professionals in the field.

awesome-ChatGPT-repositories is a comprehensive curated list of open-source GitHub repositories, specifically focusing on projects related to ChatGPT, the OpenAI API, and Codex. This resource serves as a valuable hub for developers, researchers, and enthusiasts looking to explore, contribute to, or utilize AI models and tools. It helps users discover various ChatGPT-related projects, fostering collaboration and innovation within the open-source community. The repository is maintained by the community, ensuring a dynamic and up-to-date collection of resources.

CatBoost is a high-performance, open-source Gradient Boosting on Decision Trees library designed for a variety of machine learning tasks, including ranking, classification, and regression. It offers superior quality compared to other GBDT libraries on many datasets and boasts best-in-class prediction speed. CatBoost supports both numerical and categorical features, and provides fast GPU and multi-GPU support for out-of-the-box training. It also includes built-in visualization tools and enables fast, reproducible distributed training with Apache Spark and CLI. The library is compatible with Python, R, Java, and C++, making it a versatile tool for developers and data scientists.

Bag_of_Tricks_for_Image_Classification_with_Convolutional_Neural_Networks is an open-source project that provides a platform for experimenting with and implementing various training tricks to improve the accuracy of image classification using Convolutional Neural Networks (CNNs). Inspired by the paper "Bag of Tricks for Image Classification with Convolutional Neural Networks," this repository tests popular techniques such as Xavier initialization, warmup training, no bias decay, label smoothing, random erasing, linear scaling learning rate, and cosine learning rate decay. It uses the CUB_200_2011 dataset and a VGG16 network for experiments, offering a practical resource for researchers and developers looking to optimize their CNN models.

Can-Ai-Code is an open-source project designed to evaluate the coding capabilities of AI models. Initially created to determine if language models could generate syntactically valid code, it has evolved beyond simple pass/fail metrics. The tool now focuses on measuring AI's reasoning abilities through parametric difficulty scaling, exploring how models handle increasing complexity and working memory stress. It identifies different cognitive fingerprints across model families like OpenAI, Qwen, and Llama, assessing not just accuracy but also efficiency and constrained performance. The benchmark is designed to evolve, becoming harder as models improve, ensuring continuous discrimination power in an advancing field.

shapiq is a Python package designed for machine learning explainability, specifically focusing on Shapley Interactions and Shapley Values. It provides tools for approximating any-order Shapley interactions, benchmarking game-theoretical algorithms, and explaining feature interactions within model predictions. The library extends the functionality of the well-known SHAP package, offering a more comprehensive view of machine learning models by quantifying synergy effects between features, data points, or weak learners. It supports various interaction indices like k-SII, SV, FBII, and FSII, and includes functionalities for visualizing feature interactions through network plots. shapiq is intended for Python 3.12 and above, and can be installed via uv or pip.

cnn-facial-landmark offers training code for facial landmark detection based on deep convolutional neural networks. This open-source project, built with TensorFlow, enables users to train their own models using custom datasets. The repository includes detailed instructions for getting started, installing prerequisites, and training/evaluating models. It supports exporting models for PC/Cloud applications using TensorFlow's SavedModel format. A companion tutorial is available, covering background, dataset preprocessing, model architecture, training, and deployment, making it accessible for beginners. The project also points to more advanced repositories for features like multiple public dataset support, advanced model architectures, data augmentation, and model optimization.

ddpm-segmentation is an official implementation of the paper "Label-Efficient Semantic Segmentation with Diffusion Models" (ICLR'2022). This open-source project investigates representations learned by state-of-the-art Denoising Diffusion Probabilistic Models (DDPMs) and demonstrates their value for downstream vision tasks. The tool offers a simple semantic segmentation approach that leverages these representations, showing superior performance in few-shot operating points compared to other methods. It includes implementations for DDPM, DatasetDDPM, MAE, SwAV, and DatasetGAN, along with pretrained models and scripts for training interpreters and generating synthetic datasets. The project is built upon datasetGAN and guided-diffusion techniques, providing a robust framework for research and application in semantic segmentation.

Crepe offers a robust implementation of character-level convolutional networks for text classification, built on Torch 7. This open-source project allows users to reproduce the experimental results from the "Character-level Convolutional Networks for Text Classification" article published in NIPS 2015. It includes data preprocessing scripts to convert CSV datasets into a Torch 7 binary format and a training program. The tool is designed for technical users and researchers, providing a foundation for advanced text classification tasks. While it requires a specific environment, including Torch 7 and potentially a powerful GPU, it serves as a valuable resource for understanding and applying character-level CNNs.

JarvisIR is an AI-powered image restoration tool designed to enhance and improve the quality of digital images. Users can upload images suffering from common problems such as blur, darkness, or noise. The tool intelligently analyzes the uploaded image, identifies the specific issues, and then recommends and applies the most suitable restoration algorithms to address them. The result is a processed, restored version of the image, aiming to elevate its overall perception and clarity. While the current live website indicates a runtime error, the intended functionality is to provide an intelligent solution for various image restoration needs.

Deep Pink is an open-source chess AI project designed to learn and play chess through deep learning techniques. It offers a foundational pre-trained model, allowing users to immediately explore its capabilities. For those interested in customization and advanced learning, the project provides comprehensive instructions for training a custom model. This process involves downloading PGN files and running specific Python scripts, with a strong recommendation for GPU machines to significantly accelerate the training, which can otherwise take several days. While the code is noted to be somewhat 'hacky' with hardcoded paths, requiring potential modifications, it serves as an excellent resource for AI and game development enthusiasts looking to delve into the practical application of deep learning in game strategy.

Deep-Learning-Project-Template is an open-source PyTorch project template designed to provide a best practice architecture for deep learning projects. It emphasizes simplicity, good object-oriented programming (OOP) design, and a clear folder structure to streamline development. The template helps developers quickly start new PyTorch projects by wrapping common functionalities, allowing them to focus on core aspects like model architecture and training flow. It recommends using high-level libraries like Ignite to reduce repeated code and offers a detailed folder structure for configuration, data handling, model building, and training processes.

detrex is an open-source research platform designed for Transformer-based detection algorithms, built upon Detectron2 and borrowing design principles from MMDetection and DETR. It serves as a comprehensive toolbox for object detection, segmentation, pose estimation, and various visual recognition tasks. The platform emphasizes a modular design, allowing users to easily construct customized models, and offers strong baselines for Transformer-based detection models with optimized hyper-parameters. Key features include a LazyConfig System for flexible configuration and a lightweight training engine. detrex also provides extensive documentation, a model zoo, and supports a wide array of methods like DETR, Deformable-DETR, DINO, and MaskDINO, making it a valuable resource for researchers and developers in the field.

Doubleword AI, formerly TitanML, specializes in delivering optimized high-performance inference solutions for various AI use cases. Their core offerings include the Doubleword API for scalable inference, and the Doubleword Inference Stack for high-performance inference. The platform supports batch inference for large-scale jobs at reduced costs, a control layer for managing models and deployments across teams and clouds with built-in governance, and private infrastructure options for sensitive use cases, allowing deployment in private clouds, on-premise, or hybrid environments. Doubleword AI aims to help businesses deliver value by providing a robust inference layer, reducing the burden of managing complex AI infrastructure.

World Labs is a spatial intelligence company focused on developing advanced AI models capable of perceiving, generating, reasoning, and interacting with the 3D world. Their primary product, Marble, allows users to create spatially consistent, high-fidelity, and persistent 3D environments from multimodal inputs like text, images, videos, or 360 panoramas. Users can precisely control 3D layouts, interactively edit specific elements, and expand or combine worlds to build larger, more immersive experiences. The platform supports versatile outputs, enabling downloads and exports in various 2D and 3D formats for seamless integration into existing workflows in fields such as art, film, gaming, AR/VR, robotics, and architecture.

Equinox is a comprehensive JAX library designed for building neural networks and performing scientific computing. It provides a PyTorch-like syntax for defining models, making it accessible for users familiar with that framework. Beyond neural networks, Equinox offers filtered APIs for transformations, useful PyTree manipulation routines, and advanced features like runtime errors. A key differentiator is that Equinox is not a restrictive framework; everything written within it remains compatible with core JAX and its broader ecosystem. This allows for seamless integration and flexibility in development. It's particularly useful for those coming from Flax or Haiku, offering more advanced features and a simpler model-building approach where models are treated as PyTrees.

FastFormers is an open-source project from Microsoft that provides a collection of methods and recipes for achieving highly efficient inference with Transformer models, specifically for Natural Language Understanding (NLU) tasks. The tool demonstrates impressive speed-ups, including a 233x acceleration on CPU with multi-head self-attentive Transformer architecture. It allows users to replicate results presented in the FastFormers paper and supports various optimization techniques such as model training, distillation, pruning, 8-bit integer quantization for CPU with ONNX Runtime, and 16-bit floating point conversion for GPU. The repository is built on top of several open-source projects including Hugging Face's transformers and ONNX Runtime.

finetune-transformer-lm provides the code and model for the research paper "Improving Language Understanding by Generative Pre-Training." This open-source project is designed for researchers and developers interested in replicating and experimenting with the generative pre-training techniques described in the paper. Specifically, it includes an implementation for the ROCStories Cloze Test, allowing users to run experiments and analyze results. While the code is provided as-is with no expected updates, it serves as a valuable resource for understanding the foundational concepts of generative pre-training and language understanding models. The repository also notes that the code is currently non-deterministic due to various GPU operations, with a median accuracy slightly lower than the paper's reported single run.