proxylessnas
Hardware-aware NAS
Direct neural architecture search on target task and hardware for efficient model deployment
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1k stars
70 watching
285 forks
Language: C++
last commit: 6 months ago
Linked from 1 awesome list
accelerationautomlefficient-modelhardware-awareon-device-aispecialization
weiaicunzai/awesome-image-classificationRelated projects:
| Repository | Description | Stars |
|---|---|---|
 microsoft/archai | Automates the search for optimal neural network configurations in deep learning applications | 468 |
 datacanvasio/hyperkeras | An autoML tool that searches and optimizes neural network architectures using tensorflow and keras. | 30 |
 doonny/pipecnn | A tool for accelerating convolutional neural networks on Field-Programmable Gate Arrays (FPGAs) using OpenCL-based hardware design | 1,264 |
 alrevuelta/connxr | An embedded device-friendly C ONNX runtime with zero dependencies | 196 |
 nvdla/hw | The NVDLA project provides hardware designs and tools for building deep learning inference accelerators. | 1,763 |
 titu1994/neural-architecture-search | An implementation of Neural Architecture Search using Reinforcement Learning with a Controller RNN. | 433 |
 100/cranium | A lightweight, portable C implementation of a feedforward artificial neural network library | 593 |
 xilinx/finn | Fast and scalable neural network inference framework for FPGAs. | 770 |
 apache/tvm-vta | A comprehensive hardware design stack for accelerating deep learning models | 258 |
 huawei-noah/efficient-computing | A collection of research methods and techniques developed by Huawei to improve the efficiency of neural networks in computer vision and other applications. | 1,218 |
| mit-han-lab/data-efficient-gans | Improves GAN training efficiency by incorporating data augmentation | 1,286 |
 ibm/aihwkit | An open source toolkit for developing and training neural networks on analog computing devices | 365 |
 alibaba-miil/tresnet | A high-performance deep learning architecture designed to balance accuracy and efficiency on GPUs. | 471 |
 forresti/squeezenet | Provides pre-trained models and training configurations for a deep neural network architecture optimized for image classification tasks | 2,181 |
 kirthevasank/nasbot | An implementation of Neural Architecture Search with Bayesian Optimization and Optimal Transport | 133 |