ml-models.md

ML Models

Tangram, PostgresML, ZenML & Merlin seem neat. Looking into using Cog to package ML models.

Currently use Banana to serve ML models (mostly generative) with their HTTP template.

Links

• Lip Reading - Cross Audio-Visual Recognition using 3D Architectures
• Cortex - API platform for machine learning engineers. (Web)
• BentoML - Model Serving Made Easy. (Docs)
• Lobe - Helps you train machine learning models with a free, easy to use tool. (Tweet) (HN)
• Algorithmia - Deploy Autoscaling ML Models using Serverless Microservices. (GitHub)
• How to Deploy ML models with AWS Lambda (2020)
• Verta - MLOps software supports model development, deployment, operations, monitoring.
• Guild AI - Experiment tracking, ML developer tools. (Code)
• Neuralet - Open-source platform for edge deep learning models on GPU, TPU, and more. (Code)
• InterpretML - Fit interpretable models. Explain blackbox machine learning.
• What-If Tool - Visually probe the behavior of trained machine learning models, with minimal coding. (Code)
• LightAutoML - Automatic model creation framework.
• Evidently - Interactive reports to analyze machine learning models during validation or production monitoring. (Web)
• MLCube - Project that reduces friction for machine learning by ensuring that models are easily portable and reproducible. (Docs)
• Service Streamer - Boosting your Web Services of Deep Learning Applications.
• Shapash - Makes Machine Learning models transparent and understandable by everyone. (Web) (HN)
• BudgetML: Deploy ML models on a budget (HN)
• Introducing Model Search: An Open Source Platform for Finding Optimal ML Models (2021)
• Model Search - Framework that implements AutoML algorithms for model architecture search at scale.
• Embedding stores (2021)
• Running ML models in a game (and in Wasm!) (2020)
• Deep learning model compression (2021)
• ModelDB - Open Source ML Model Versioning, Metadata, and Experiment Management.
• Gradio - Generate an easy-to-use UI for your ML model, function, or API with only a few lines of code. (Code)
• Awesome Model Quantization
• Tracking the Performance of Your Machine Learning Models With MLflow (2021)
• Counterfit - CLI that provides a generic automation layer for assessing the security of ML models.
• Convect - Instant Serverless Deployment of ML Models. (HN)
• Using Argo to Train Predictive Models (2021) (HN)
• Yellowbrick - Visual analysis and diagnostic tools to facilitate machine learning model selection. (Docs)
• Deep Learning Model Convertors
• Tuning Model Performance (2021)
• SHAP - Game theoretic approach to explain the output of any machine learning model.
• Lazy Predict - Helps build a lot of basic models without much code and helps understand which models works better without any parameter tuning.
• How to Monitor Models (2020)
• How to Serve Models (2020)
• StudioML - Python model management framework. (Code)
• MLapp - ML model serving app based on APIs.
• Machine Learning Hyperparameter Optimization with Argo (2021)
• Snakepit - Coqui's machine learning job scheduler.
• MLServer - Inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more. (Docs)
• SpotML - Managed ML Training on Cheap AWS/GCP Spot Instances. (HN)
• Mosaic ML - Making ML Training Efficient. (Tweet) (Intro)
• RecoEdge - Deploy recommendation engines with Edge Computing.
• MLRun - Open-Source MLOps Orchestration Framework.
• PrimeHub - Toil-free multi-tenancy machine learning platform in your Kubernetes cluster. (Docs)
• MLeap - Deploy ML Pipelines to Production. (Docs)
• ServingMLFastCelery - Working example for serving a ML model using FastAPI and Celery.
• Cog - Containers for machine learning. (HN) (Tweet)
• Explaining Machine Learning Models: A Non-Technical Guide to Interpreting SHAP Analyses (2021)
• Improving a Machine Learning System Is Hard (2021)
• Removal-based explanations - Lightweight implementation of removal-based explanations for ML models.
• Gordo - Building thousands of models with timeseries data to monitor systems.
• Mosec - Model Serving made Efficient in the Cloud.
• MLNotify - Add just 1 import line and MLNotify will let you know the second it's done.
• Build models like we build open-source software (2021) (HN)
• Deepchecks - Python package for comprehensively validating your machine learning models and data with minimal effort.
• Auptimizer - Automatic ML model optimization tool.
• runx - Deep Learning Experiment Management.
• ML Console - Web app to train ML models, for free and client-side. (HN)
• MMDeploy - OpenMMLab Model Deployment Framework. (Docs)
• Wonnx - Aimed at being an ONNX Provider for every GPU on all platforms written in 100% Rust.
• How to Build a Machine Learning Demo in 2022
• Zetane Viewer - ML models and internal tensors 3D visualizer.
• ONNX Model Zoo - Collection of pre-trained, state-of-the-art models in the ONNX format.
• Model Zoo for MindSpore
• Seldon - Machine Learning Deployment for Kubernetes. (GitHub)
• ORMB - Docker for Your ML/DL Models Based on OCI Artifacts.
• Spaces - Hugging Face (Tweet)
• Nanit’s AI Development Process (2022)
• ailia SDK ML Models
• BentoML - Simplify Model Deployment. (GitHub)
• bentoctl - Fast model deployment with BentoML on cloud platforms.
• ModelCenter - Efficient, Low-Resource, Distributed transformer implementation based on BMTrain.
• PostgresML - End-to-end machine learning system. It enables you to train models and make online predictions using only SQL, without your data ever leaving your favorite database. (Web) (HN)
• UniLM AI - Pre-trained models across tasks (understanding, generation and translation), languages, and modalities.
• Domino - Discover slices of data on which your models underperform.
• Merlin - Kubernetes-friendly ML model management, deployment, and serving.
• Baseten - Build ML-powered applications. (HN)
• Triton Inference Server - Provides a cloud and edge inferencing solution optimized for both CPUs and GPUs.
• Feature Store - Feature store co-designed with a data platform and MLOps framework. (Announcement)
• Auto-ViML - Automatically Build Variant Interpretable ML models fast.
• Angel - Flexible and Powerful Parameter Server for large-scale machine learning.
• Trainer - General purpose model trainer, as flexible as it gets.
• onnxcustom - Tutorial on how to convert machine learned models into ONNX.
• Vetiver - Version, share, deploy, and monitor models.
• Cloud TPU VMs are generally available (2022) (HN)
• NannyML - Detecting silent model failure.
• Pydra - Pydantic and Hydra for configuration management of model training experiments (2022)
• BlindAI - Confidential AI inference server.
• Vertigo - AI for IoT & The Edge.
• Compair - Model evaluation utilities.
• LightAutoML - Fast and customizable framework for automatic ML model creation (AutoML).
• MLEM - Version and deploy your ML models following GitOps principles. (Web)
• Serving ML at the Speed of Rust (2022) (HN)
• Sematic - Open-source framework to build ML pipelines faster. (Web) (HN)
• ML Platform Workshop - Example code for a basic ML Platform based on Pulumi, FastAPI, DVC, MLFlow and more.
• Mlflow Deployment Controller - Listens MLFlow model registry changes and deploy models based on configurations.
• Truss - Serve any model without boilerplate code. (HN) (Docs)
• Remote Runner - Easy pythonic way to migrate your python training scripts from a local environment to a powerful cloud-backed instance.
• BMList - List of big pre-trained models (GPT-3, DALL-E2...).
• ModelBox - Extensible machine learning model store and model transformation and distribution service.
• Run Stable Diffusion on Your M1 Mac’s GPU (2022) (HN)
• Stable Diffusion Dream Script - Fork of CompVis/stable-diffusion, the wonderful open source text-to-image generator.
• Exporters - Export Hugging Face models to Core ML and TensorFlow Lite.
• SD-explorer - Toy project to explore Stable Diffusion locally through a nodeJS server.
• MultiNeRF: A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
• Prog Rock Stable - Stable Diffusion with some Proggy Enhancements.
• Diffusers-Interpret - Model explainability tool built on top of Diffusers.
• Using GitHub as Artifactory for Machine Learning Model Artifacts (2022)
• Replicate - Run open-source machine learning models with a cloud API. (Go Replicate)
• dfserver - Distributed backend AI pipeline server.
• dstack - Command-line utility to provision infrastructure for ML workflows. (Docs)
• Privacy Meter - Open-source library to audit data privacy in statistical and machine learning algorithms.
• fastDeploy - Deploy DL/ ML inference pipelines with minimal extra code.
• Modelverse - Content-Based Search for Deep Generative Models. (Code)
• FlagAI - Fast, easy-to-use and extensible toolkit for large-scale model.
• Stochastic - AI Acceleration Platform. (GitHub)
• voltaML - Lightweight library to convert and run your ML/DL deep learning models in high performance inference runtimes like TensorRT, TorchScript, ONNX and TVM.
• AWS Deep Learning Containers - Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.
• Spotty - Training deep learning models on AWS and GCP instances.
• FastDeploy - Accessible and efficient deployment Development Toolkit.
• explainerdashboard - Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
• MatxScript - Model pre- and post-processing framework.
• Zoltar - Common library for serving TensorFlow, XGBoost and scikit-learn models in production.
• Robust Intelligence - Machine learning models fail. Prevent bad outcomes with the only end-to-end solution.
• Banana Serverless - Framework to serve ML models in production using simple HTTP servers.
• SkyPilot - Framework for easily running machine learning workloads on any cloud through a unified interface.
• m2cgen (Model 2 Code Generator) - Lightweight library which provides an easy way to transpile trained statistical models into a native code.
• Models - Hugging Face
• Training One Million Machine Learning Models in Record Time with Ray (2022) (Tweet)