ML Models
Tangram, PostgresML & ZenML seem neat. Using Cog to package ML models.
Tangram ↗, PostgresML ↗ & ZenML ↗ seem neat. Using Cog ↗ to package ML models.
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 ↗)
- 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 ML pipeline development toolkit.
- ML Platform Workshop ↗ - Example code for a basic ML Platform based on Pulumi, FastAPI, DVC, MLFlow and more.