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/KunlinY/darts-parallel
https://github.com/LARS-research/DiffMG
DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
https://github.com/LARS-research/SANE
https://github.com/LARS-research/SNAG
https://github.com/Legoons/Melanoma_classification
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/LibrarristShalinward/while_true_involute-Cream_of_the_Crop
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
https://github.com/LuEE-C/PPO-Keras
https://github.com/Luccadoremi/Model-Compression-DAQ
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
https://github.com/MINGUKKANG/ENAS-Tensorflow
https://github.com/MINGUKKANG/PNU_Capstone_Design
https://github.com/MINGUKKANG/PNU_Termproject_ENAS
https://github.com/MS-Mind/MS-Code-02/tree/main/configs/mnasnet
MnasNet: Platform-Aware Neural Architecture Search for Mobile
https://github.com/MS-Mind/MS-Code-06/tree/main/PDarts
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
https://github.com/MS-Mind/MS-Code-06/tree/main/nasnet
https://github.com/MS-Mind/MS-Code-06/tree/main/proxylessnas
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
https://github.com/MS-Mind/MS-Code-08/tree/main/mnasnet
MnasNet: Platform-Aware Neural Architecture Search for Mobile
https://github.com/MS-Mind/MS-Code-08/tree/main/mobilenetV3_small_x1_0
https://github.com/MS-Mind/MS-Code-08/tree/main/mobilenetv3_large
https://github.com/MS-Mind/MS-Code-08/tree/main/nas-fpn
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
https://github.com/MarSaKi/nasnet
Learning Transferable Architectures for Scalable Image Recognition
https://github.com/MarcAntoineAlex/darts
https://github.com/MatteoBrentegani/PPO
https://github.com/MaximIntegratedAI/ai8x-synthesis
Once-for-All: Train One Network and Specialize it for Efficient Deployment
https://github.com/MaximIntegratedAI/ai8x-training
Once-for-All: Train One Network and Specialize it for Efficient Deployment
https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Proximal_Policy_Optimization_Algorithms
https://github.com/Mayurji/Image-Classification-PyTorch
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/MemNAS/MemNAS
https://github.com/MengTianjian/enas-pytorch
https://github.com/MenghaoGuo/AutoDeeplab
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
https://github.com/Michaelrising/Prog-RL
https://github.com/Mind23-2/MindCode-10
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
https://github.com/Mind23-2/MindCode-101/tree/main/HourNAS
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
https://github.com/Mind23-2/MindCode-101/tree/main/ISyNet
ISyNet: Convolutional Neural Networks design for AI accelerator
https://github.com/Mind23-2/MindCode-101/tree/main/mnasnet
MnasNet: Platform-Aware Neural Architecture Search for Mobile
https://github.com/Mind23-2/MindCode-101/tree/main/mobilenetV3_small_x1_0
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.