https://github.com/guoyongcs/HNAS-SR
공식 코드Hierarchical Neural Architecture Search for Single Image Super-Resolution
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/guoyongcs/NAT
공식 코드NAT: Neural Architecture Transformer for Accurate and Compact Architectures
https://github.com/guoyongcs/NATv2
공식 코드Towards Accurate and Compact Architectures via Neural Architecture Transformer
https://github.com/hadarshavit/nexception
공식 코드From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
https://github.com/haihabi/GeneticNAS
공식 코드https://github.com/halimabouzidi/hadas
공식 코드HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
https://github.com/han-cai/EAS
공식 코드https://github.com/han-cai/PathLevel-EAS
공식 코드Path-Level Network Transformation for Efficient Architecture Search
https://github.com/han-cai/RL4AS_NetTrans
공식 코드https://github.com/hayeonlee/help
공식 코드HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning
https://github.com/hbp-unibi/SNABSuite
공식 코드Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware
https://github.com/he-y/awesome-pruning
공식 코드Structured Pruning for Deep Convolutional Neural Networks: A survey
https://github.com/hkbu-hpml/easnet
공식 코드EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching
https://github.com/hkzhang91/3D-ANAS
공식 코드3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification
https://github.com/hkzhang91/hinas
공식 코드Memory-Efficient Hierarchical Neural Architecture Search for Image Restoration
https://github.com/hpnair/18663_Project_FBNet
공식 코드https://github.com/hsg-aiml/neurips_2021-weight_space_learning
공식 코드Hyper-Representations for Pre-Training and Transfer Learning
https://github.com/hsg-aiml/neurips_2022-generative_hyper_representations
공식 코드Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights
https://github.com/huawei-noah/CARS
공식 코드CARS: Continuous Evolution for Efficient Neural Architecture Search
https://github.com/huawei-noah/Efficient-Computing
공식 코드https://github.com/huawei-noah/Pretrained-Language-Model
공식 코드AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models
https://github.com/huawei-noah/vega
공식 코드https://github.com/huawei-noah/vega/tree/master/examples/nas/nago
공식 코드https://github.com/human-analysis/MUXConv
공식 코드MUXConv: Information Multiplexing in Convolutional Neural Networks
https://github.com/human-analysis/neural-architecture-transfer
공식 코드https://github.com/hust-linyi/LENAS
공식 코드LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction
https://github.com/hustvl/EfficientPose
공식 코드EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search
https://github.com/hy-he/is-darts
공식 코드IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance
https://github.com/hyeonjeongha/croze
공식 코드Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
https://github.com/hzf1174/robot
공식 코드Robustifying and Boosting Training-Free Neural Architecture Search
https://github.com/ianwhale/nsga-net
공식 코드NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
https://github.com/ibm/analog-nas
공식 코드AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing
https://github.com/iboing/ISTA-NAS
공식 코드ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
https://github.com/idstcv/GPU-Efficient-Networks
공식 코드https://github.com/iitm-sysdl/FuSeConv
공식 코드FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrays
https://github.com/indrajeet3333/covid-19-forecasting
공식 코드Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.