https://github.com/VascoLopes/EPE-NAS
공식 코드EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search
Papers with Code 아카이브
Neural Architecture Search
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 26
- 보존된 평가 기록
- 424
Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.
Image Credit : NAS with Reinforcement Learning
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/VascoLopes/EPENAS
공식 코드EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search
https://github.com/VascoLopes/GEA
공식 코드https://github.com/VisualTrackingVLL/CHASE
공식 코드CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search
https://github.com/Waasem/RobDanns
공식 코드Exploring Robust Architectures for Deep Artificial Neural Networks
https://github.com/WenjinW/LLSEU
공식 코드https://github.com/Xiaobin-Rong/ul-unas
공식 코드UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search
https://github.com/XuelianCheng/LEAStereo
공식 코드Hierarchical Neural Architecture Search for Deep Stereo Matching
https://github.com/YaoYao1995/i-Razor
공식 코드https://github.com/Yuantian013/E2GAN
공식 코드Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search
https://github.com/YunChunChen/NAS-DIP-pytorch
공식 코드NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
https://github.com/ZhangYuanhan-AI/NOAH
공식 코드https://github.com/ZitongYu/3DCDC-NAS
공식 코드Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
https://github.com/ZitongYu/CDCN
공식 코드Searching Central Difference Convolutional Networks for Face Anti-Spoofing
https://github.com/Ziwei-Zheng/OSen-NAS
공식 코드OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength
https://github.com/a-elsaid/cants_public
공식 코드Backpropagation-Free 4D Continuous Ant-Based Neural Topology Search
https://github.com/aaronserianni/training-free-nas
공식 코드Training-free Neural Architecture Search for RNNs and Transformers
https://github.com/abdelfattah-lab/flan_nas
공식 코드https://github.com/abdelfattah-lab/nasflat_latency
공식 코드https://github.com/abduallahmohamed/inner_ensemble_nets
공식 코드Inner Ensemble Networks: Average Ensemble as an Effective Regularizer
https://github.com/acamero/dlopt
공식 코드Bayesian Neural Architecture Search using A Training-Free Performance Metric
https://github.com/afzalxo/accel-nasbench
공식 코드Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAS
https://github.com/aheuillet/D-DARTS
공식 코드https://github.com/aheuillet/nasiam
공식 코드NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks
https://github.com/ahundt/costar_dataset
공식 코드The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints
https://github.com/ahundt/enas
공식 코드The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints
https://github.com/ahundt/sharpDARTS
공식 코드sharpDARTS: Faster and More Accurate Differentiable Architecture Search
https://github.com/ai-tech-research-lab/asquaredm
공식 코드Architecture-Aware Minimization (A$^2$M): How to Find Flat Minima in Neural Architecture Search
https://github.com/ai-tech-research-lab/cnas
공식 코드FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness
https://github.com/ai-tech-research-lab/nas
공식 코드NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
https://github.com/ain-soph/autovul
공식 코드https://github.com/ajbrock/SMASH
공식 코드SMASH: One-Shot Model Architecture Search through HyperNetworks
https://github.com/albertipot/nar
공식 코드Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search
https://github.com/alexa/bort
공식 코드https://github.com/alexadlu/after
공식 코드https://github.com/alexandrewang915/autost
공식 코드AutoST: Training-free Neural Architecture Search for Spiking Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.