Supports software work with AI-assisted coding, testing or application development.
Directory
Search the directory
Search published websites, apps and repositories.
A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.
A fast Clojure Tensor & Deep Learning library.
Official PyTorch implementation of the CVPR 2019 paper on deep high-resolution representation learning for human pose estimation. The network maintains high-resolution representations through the whole process and connects multi-resolution subnetworks in parallel with repeated multi-scale fusions. Results are reported on the COCO keypoint detection dataset and the MPII Human Pose dataset.
deep-floyd/IF is a GitHub repository for the IF image generation model developed by DeepFloyd Lab at StabilityAI. It provides documentation for minimum model requirements, quick start guides, local notebook support, and integration with the Hugging Face Diffusers library for model use.
DeepAlpha is an AI-powered cryptocurrency trading bot that uses a deep neural network combining BiLSTM and attention mechanisms, trained on GPU. It supports 25 coins with a reported 84.9% accuracy rate, integrates with Bybit, Binance, OKX, and Gate.io exchanges, and is available as a free cloud or self-hosted service.
An agentic LLM for autonomous data science that performs data preparation, analysis, modeling, visualization, and report generation without human intervention. It supports open-ended research on structured, semi-structured, and unstructured data sources, and the model, code, training data, and demo are open-sourced.
Deepchecks is an open-source project for validating machine learning models and data from research to production. It includes built-in and custom checks and suites for tabular, NLP and CV validation, CI and testing management, and monitoring of deployed models. Installation is via pip.
DeepDetect is a deep learning runtime, command-line tool and REST server for training and inference. It provides Python wheel variants for CPU and GPU environments and a command-line interface with profiles such as object detection and semantic segmentation. YAML configuration files make runs repeatable. It handles images, text, tabular data, time series, object-detection boxes and segmentation masks through a single API surface.
deepface is a lightweight Python library for face recognition and facial attribute analysis. It supports analysis of age, gender, emotion, and race attributes from facial data. The project is hosted as an open source repository on GitHub.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
deeplearn-rs is a Rust library for neural networks and deep learning, described by its author as mostly a proof of concept with a changing API. Implemented models include MNIST handwritten digit recognition and a char-rnn using LSTM, alongside layers such as fully connected, LSTM, softmax, and loss functions, with SGD and RMSProp optimizers. The repository was archived by its owner on Mar 8, 2024, and is read-only.
Deeplearning4j is an open-source suite of tools for deploying and training deep learning models using the Java Virtual Machine (JVM). It supports model import from Keras, TensorFlow, and ONNX/PyTorch, includes a modular C++ math library with a corresponding Java library built on top, and offers SameDiff, a library for deep learning operations similar to PyTorch and TensorFlow.
Deepnote is a drop-in replacement for Jupyter with an AI-first design. It uses the Deepnote kernel, adds block types, native data integrations and an AI agent, and supports Python, R and SQL locally in an IDE before scaling to Deepnote Cloud for collaboration and deployable data apps.
DeepPavlov is an open-source library for deep learning end-to-end dialog systems and chatbots. Version 1.0 is described as an NLP framework built on PyTorch and transformers for modular, configuration-driven development of NLP models, intended for practitioners with limited NLP/ML knowledge. It supports Linux, Windows 10+ through WSL/WSL2, and MacOS Big Sur+ on Python 3.6 to 3.10.
DeepSeek Coder is a series of open code language models trained from scratch on 2T tokens, composed of 87% code and 13% natural language in English and Chinese. Models are offered in 1B, 5.7B, 6.7B and 33B sizes, pre-trained on project-level code corpora with a 16K window size and a fill-in-the-blank task for completion and infilling.
DeepSeek-R1 is the first-generation reasoning model family from DeepSeek, including DeepSeek-R1-Zero and DeepSeek-R1. The repository describes training via large-scale reinforcement learning and cold-start data, and open-sources the models plus six distilled dense models based on Llama and Qwen.
DeepSeek-V3 is a Mixture-of-Experts language model with 671B total parameters and 37B activated per token. It uses Multi-head Latent Attention and DeepSeekMoE architectures, was pre-trained on 14.8 trillion tokens, and then underwent supervised fine-tuning and reinforcement learning. The repository provides the model weights and inference code.
DeepSeek-VL2 is a mixture-of-experts vision-language model designed for advanced multimodal understanding. Its public GitHub repository provides documentation including an introduction, release information, model download resources, and a quick start guide.
Deep learning optimization library that makes distributed training easy, efficient, and effective.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
This GitHub repository hosts the official Deforum extension for AUTOMATIC1111's Stable Diffusion web user interface. The extension integrates Deforum functionality into the Stable Diffusion webui, and the repository includes resources such as a FAQ, getting started guide, and known issues list for users.
A listener that streams your spark events logs to delight, a free and improved spark UI.