AutoML library for deep learning
- automl
- neural-architecture-search
- automated-machine-learning
- python
111,085 visible repositories in the index
1–19 of 19 · Most stars
AutoML library for deep learning
A curated list of automated machine learning papers, articles, tutorials, slides and projects
Differentiable architecture search for convolutional and recurrent networks
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
Infrastructure for evolutionary AI systems. GPU-accelerated, PyTorch-based optimization with an ecosystem of algorithm libraries, benchmarks, and tools.
Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)
FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai
AI on the way. An auto deep learning pipe dream. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.
WARNING: Katib project is DEPRECATED, users should migrate to OptimizationJob and Kubeflow Trainer
Automated deep learning algorithms implemented in PyTorch.
A curated list of awesome architecture search resources
An autoML framework & toolkit for machine learning on graphs.
Fast & Simple Resource-Constrained Learning of Deep Network Structure
This is a list of interesting papers and projects about TinyML.
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
Early POC of genetic neural architecture search
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.