Coding & Development

TensorFlow Federated (TFF) is an open-source framework designed for machine learning and other computations on decentralized data. It specifically supports Federated Learning (FL), an approach where a shared global model is trained across many participating clients while their sensitive training data remains local. This framework enables developers to utilize included federated learning algorithms with their existing TensorFlow models and data, or to experiment with novel algorithms. TFF provides both a high-level Federated Learning (FL) API for applying federated training and evaluation, and a lower-level Federated Core (FC) API for expressing new federated algorithms. It includes a single-machine simulation runtime for experiments, making it suitable for researchers and developers exploring privacy-preserving machine learning.

Veles is a distributed platform designed for rapid deep learning application development, released under the Apache 2.0 license. It comprises several key components, including the core Veles platform, the Znicz Plugin which serves as a neural network engine, and Mastodon, a bridge facilitating integration between Veles and Java-based systems like Hadoop. Additionally, it features a SoundFeatureExtraction library for audio processing. This platform is ideal for developers and researchers looking to build and deploy deep learning applications in a distributed environment, offering tools for both model development and data processing.

transformer-xl-chinese is an open-source project that leverages the Transformer-XL model for advanced Chinese text generation. This tool allows users to generate various forms of Chinese text, including novels, ancient poetry, and general conversational topics. Key functionalities include the ability to perform inference, visualize attention mechanisms within the model, and examine candidate words for generated text. The project builds upon existing Transformer-XL implementations, with specific modifications to support Chinese text generation and enhance usability through added inference capabilities and visualization tools. It provides scripts for data preparation, training, and inference, making it accessible for developers and researchers interested in exploring and applying Transformer-XL to Chinese language tasks.

TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an open-source AutoML library written in Scala, designed to run on Apache Spark. Developed by Salesforce, it focuses on enhancing machine learning developer productivity by automating various stages of the ML workflow, from feature engineering and validation to model selection. The library enforces compile-time type-safety, modularity, and reusability, enabling the creation of robust machine learning applications in a fraction of the time compared to traditional hand-tuned methods. It supports building models with minimal machine learning expertise, making advanced ML accessible to a broader range of developers. TransmogrifAI is particularly useful for structured data and offers flexibility for users who require more control over their ML pipelines.

Bert-Multi-Label-Text-Classification offers a PyTorch implementation of pretrained BERT and XLNET models specifically tailored for multi-label text classification. This open-source repository includes a structured codebase with modules for callbacks, configuration, dataset handling, model architecture, output management, text preprocessing, and training. Developers can fine-tune BERT models, preprocess data, and predict new data using provided scripts. The tool supports various dependencies like PyTorch, transformers, and scikit-learn, making it a robust solution for NLP tasks requiring multi-label classification.

TPVFormer is an academic project offering a Tri-Perspective View (TPV) representation for vision-based 3D semantic occupancy prediction, serving as an alternative to Tesla's Occupancy Network for autonomous driving research. It addresses the limitations of traditional bird's-eye-view (BEV) representations by incorporating two additional perpendicular planes, allowing for a more fine-grained description of 3D scenes. The tool features a transformer-based TPV encoder (TPVFormer) to effectively obtain TPV features by aggregating image features. It demonstrates that camera inputs alone can achieve performance comparable to LiDAR-based methods on LiDAR segmentation tasks. The project also includes resources for semantic scene completion and comparisons with Tesla's Occupancy Network.

Tetris-deep-Q-learning-pytorch is an open-source Python project that demonstrates the application of Deep Q-learning for training an AI agent to play the classic game Tetris. Developed with PyTorch, this tool serves as a foundational example of reinforcement learning in action. Users can leverage the provided source code to train their own Tetris-playing models from scratch or test pre-trained models. The project includes all necessary scripts for training and testing, making it accessible for those interested in understanding and experimenting with AI agents and deep learning techniques in a practical gaming context. It's an excellent resource for students and developers exploring the basics of reinforcement learning.

Nlprule is a fast, low-resource Natural Language Processing and Text Correction library written in Rust. It implements a rule- and lookup-based approach, leveraging resources from LanguageTool for its NLP tasks. Key features include rule-based grammatical error correction with thousands of rules, a comprehensive text processing pipeline covering sentence segmentation, part-of-speech tagging, lemmatization, chunking, and disambiguation. The library supports English, German, and Spanish, with spellchecking currently in progress. Nlprule is designed for speed and efficiency, making it suitable for pre/post-processing in more sophisticated AI approaches, background application tasks with low overhead, or client-side execution via WebAssembly.

VividTalk is an open-source project designed for one-shot audio-driven talking head generation. It leverages a 3D hybrid prior to produce realistic facial animations directly from audio input. This tool is particularly suitable for researchers and developers working in AI-driven video synthesis and deepfake creation, offering a foundation for exploring advanced animation techniques. As a GitHub repository, it provides the code and resources for users to implement and experiment with the technology, making it a valuable asset for those interested in the technical aspects of generating dynamic talking head videos.

VoiceFilter is an unofficial PyTorch implementation of Google AI's VoiceFilter system, designed for targeted voice separation by speaker-conditioned spectrogram masking. This open-source project allows users to filter out specific voices from mixed audio, enhancing speech clarity. While the original author notes some limitations due to its early development, it provides a foundational framework for researchers and developers in audio processing. It includes functionalities for dataset preparation, model training, and inference, utilizing d-vector embeddings for speaker recognition. The project also offers pointers to newer, more reliable VoiceFilter implementations and recommends PyTorch Lightning for deep learning project templates.

WeDLM is an open-source diffusion language model developed by Tencent, designed for high-speed inference. It uniquely reconciles diffusion language models with standard causal attention, enabling native KV cache compatibility with technologies like FlashAttention and PagedAttention. This approach allows for direct initialization from pre-trained autoregressive models such as Qwen2.5 and Qwen3, delivering significant real speedups compared to vLLM-optimized baselines. WeDLM achieves 3-6x speedup on tasks like math reasoning and up to 10x on sequential/counting tasks, while maintaining competitive accuracy. It includes an inference engine, evaluation suite, and a fine-tuning framework, making it a powerful tool for developers and researchers focused on efficient language model deployment.

Watermark-removal is an open-source project that leverages machine learning for image inpainting, effectively removing watermarks from images. The methodology is designed to produce results that are virtually indistinguishable from the original, ground truth images. This project draws inspiration from advanced techniques like Contextual Attention (CVPR 2018) and Gated Convolution (ICCV 2019 Oral), showcasing a sophisticated approach to image manipulation. It provides instructions for running via Docker or Google Colab, making it accessible for developers and researchers interested in image processing and computer vision tasks.

Brevitas is an open-source PyTorch library designed for neural network quantization, offering support for both post-training quantization (PTQ) and quantization-aware training (QAT). This tool enables developers and researchers to optimize and compress neural networks, making them more efficient for deployment on various hardware platforms. It provides quantized implementations of common PyTorch layers, such as QuantConv1d, QuantConv2d, and QuantLSTM, allowing individual tuning of quantization settings for different tensors. Brevitas is a research project from Xilinx, providing examples for ImageNet classification models to demonstrate PTQ under various configurations.

Genie-TTS is an open-source, lightweight inference engine and model converter specifically designed for GPT-SoVITS ONNX models. It excels in providing near-instantaneous speech synthesis on CPUs, making it highly efficient for various applications. The tool integrates essential functionalities such as TTS inference, ONNX model conversion, and an API server, all aimed at delivering ultimate performance and convenience. It supports GPT-SoVITS V2 and V2ProPlus models, with planned support for V3 and V4, and handles Japanese, English, Chinese, and Korean languages. Genie-TTS also offers significant performance advantages over official PyTorch models, particularly in first inference latency and runtime size, making it an ideal solution for developers and content creators seeking high-performance, CPU-based speech synthesis.

evidential-deep-learning is an open-source Python package designed to help neural networks learn their own measures of uncertainty directly from data. It provides the necessary code to reproduce the Deep Evidential Regression paper published in NeurIPS 2020, offering a general framework for evidential learning. The tool allows users to integrate evidential layers and loss functions into existing `tf.keras` model pipelines, supporting both fully connected and convolutional layers. This enables the development of models that can provide fast, scalable, and calibrated measures of uncertainty, enhancing their trustworthiness and utility. The package is compatible with Python (>=3.7) and TensorFlow (>=2.0), with PyTorch support planned.

The NVIDIA Data Loading Library (DALI) is a GPU-accelerated library designed to optimize data loading and pre-processing for deep learning applications. It offers a collection of highly optimized building blocks and an efficient execution engine, specifically tailored for processing image, video, and audio data. DALI addresses the common bottleneck of CPU-bound data pipelines by offloading these tasks to the GPU, significantly enhancing performance and scalability for training and inference. It supports various data formats and is portable across popular deep learning frameworks like TensorFlow, PyTorch, and PaddlePaddle. Key features include prefetching, parallel execution, batch processing, and extensibility for custom operators, making it a versatile solution for accelerating complex deep learning workflows.

deepnet is an open-source project providing GPU-based Python implementations of several deep learning algorithms. It supports a range of models including feed-forward neural networks, Restricted Boltzmann Machines, Deep Belief Nets, Autoencoders, Deep Boltzmann Machines, and Convolutional Neural Nets. Built upon the cudamat library by Vlad Mnih and cuda-convnet library by Alex Krizhevsky, deepnet offers a foundational resource for developers and researchers working with deep learning. Its focus on core algorithm implementations makes it a valuable tool for understanding and experimenting with these fundamental AI architectures.

Katib is a Kubernetes-native project designed for automated machine learning (AutoML), providing robust capabilities for hyperparameter tuning, early stopping, and neural architecture search. It is framework-agnostic, allowing users to tune hyperparameters for applications written in any language and supporting popular ML frameworks like TensorFlow, PyTorch, and XGBoost. Katib can execute training jobs using various Kubernetes Custom Resources, including Kubeflow Training Operator, Argo Workflows, and Tekton Pipelines. It offers a range of search algorithms such as Random Search, Bayesian Optimization, TPE, and CMA-ES, and integrates with frameworks like Goptuna, Hyperopt, and Optuna. A Python SDK is available to simplify the creation of hyperparameter tuning jobs for data scientists.

ResnetGPT is an open-source project built with Resnet101 and GPT, designed to create an AI capable of playing the mobile game Honor of Kings. Developed using the PyTorch framework, it leverages a pre-trained Resnet101 model and a Transformer-based decoder for game actions. The project provides code for training the AI with gameplay data, including scripts for data capture and preprocessing. While the project is no longer actively updated, it serves as a foundational example for developing AI agents for complex game environments, requiring a dedicated NVIDIA graphics card and an Android device for operation.

Real-time-stock-market-prediction is an open-source project that offers a complete server-side architecture for real-time stock market prediction using Machine Learning. It leverages TensorFlow.js for building the ML model architecture and Kafka for efficient real-time data streaming and pipelining. The system integrates MongoDB for updating databases with incoming stock market logs, enabling analysis and model training, and storing model performance. Developed entirely with Node.js, this architecture supports parallel processing for real-time analysis, ML model training, and prediction, making it suitable for those interested in applying machine learning to financial market analysis and developing robust predictive models.

PIRender is an open-source tool for controllable portrait image generation, based on the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering." It allows users to synthesize portrait images by intuitively controlling face motions with fully disentangled 3DMM parameters. This model can be applied to various tasks including intuitive portrait image editing, pose and expression alignment, motion imitation, same and cross-identity reenactment, and audio-driven facial reenactment. The project provides source code for PyTorch, detailed installation instructions, and guidance on dataset preparation using VoxCeleb. It also includes scripts for inference, intuitive control, and training, making it a comprehensive resource for researchers and developers in the field of neural rendering.

rpaframework is a comprehensive, open-source collection of libraries and tools specifically designed for Robotic Process Automation (RPA). It seamlessly integrates with both Robot Framework and Python, providing a robust foundation for automating various tasks and processes. The project is sponsored by Robocorp and optimized for their Control Room and Developer Tools, ensuring a streamlined development experience. It includes a wide array of libraries for browser automation (Selenium, Playwright), desktop automation, email operations (Exchange, IMAP/SMTP), Excel and PDF manipulation, file system interactions, and integrations with cloud services like AWS, Azure, and Google. Additionally, it offers libraries for intelligent document processing, database interactions, and APIs for services like HubSpot, Microsoft Graph, OpenAI, Salesforce, SAP, Slack, and Twitter, making it a versatile solution for complex automation needs.

TextBlob is a Python library designed for simplified text processing, offering a straightforward API for various natural language processing (NLP) tasks. Key functionalities include sentiment analysis, part-of-speech tagging, and noun phrase extraction. It also supports classification, tokenization, word and phrase frequency analysis, parsing, n-grams, word inflection (pluralization and singularization), lemmatization, and spelling correction. Built upon the foundations of NLTK and Pattern, TextBlob allows for the addition of new models or languages through extensions and integrates with WordNet. It's an open-source tool, making it accessible for developers and researchers working with textual data.

Yatai (屋台, food cart) is a Kubernetes deployment operator specifically designed for BentoML, enabling model deployment at scale. It allows DevOps teams to seamlessly integrate BentoML services into their existing GitOps workflows, facilitating the deployment and scaling of machine learning models on any Kubernetes cluster. Yatai is cloud-native and DevOps-friendly, utilizing a Kubernetes-native workflow with its BentoDeployment CRD (Custom Resource Definition). This approach makes it easy to fit BentoML-powered services into existing operational pipelines. The tool provides documentation for installation and offers a quick tour to try it locally in a minikube cluster, along with components for image building and deployment.