Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-AutoML-and-Lightweight-Models
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.
https://github.com/guan-yuan/awesome-AutoML-and-Lightweight-Models
Last synced: 4 days ago
JSON representation
-
1.) Neural Architecture Search
-
**[Papers]**
- Designing neural networks through neuroevolution
- When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
- Searching for A Robust Neural Architecture in Four GPU Hours
- D-X-Y/GDAS
- ASAP: Architecture Search, Anneal and Prune
- Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
- Automatic Convolutional Neural Architecture Search for Image Classification Under Different Scenes
- sharpDARTS: Faster and More Accurate Differentiable Architecture Search
- Learning Implicitly Recurrent CNNs Through Parameter Sharing
- Probabilistic Neural Architecture Search
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
- SNAS: Stochastic Neural Architecture Search
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
- Neural Architecture Optimization
- DARTS: Differentiable Architecture Search
- Template-Based Automatic Search of Compact Semantic Segmentation Architectures
- Understanding Neural Architecture Search Techniques
- Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
- Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
- ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
- Transfer Learning with Neural AutoML
- Learning Transferable Architectures for Scalable Image Recognition
- tensorflow/models/research/slim/nets/nasnet
- MnasNet: Platform-Aware Neural Architecture Search for Mobile
- AnjieZheng/MnasNet-PyTorch
- Practical Block-wise Neural Network Architecture Generation
- Efficient Neural Architecture Search via Parameter Sharing
- Efficient Architecture Search by Network Transformation
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- DetNAS: Neural Architecture Search on Object Detection
- The Evolved Transformer
- Designing neural networks through neuroevolution
- EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
- Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
- MFAS: Multimodal Fusion Architecture Search
- DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
- Progressive Neural Architecture Search
- Exploring Randomly Wired Neural Networks for Image Recognition
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- Graph HyperNetworks for Neural Architecture Search
- Inductive Transfer for Neural Architecture Optimization
- Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
- Improving Neural Architecture Search Image Classifiers via Ensemble Learning
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- gmh14/RobNets
- dstamoulis/single-path-nas
- lolemacs/soft-sharing
- Neural Architecture Optimization
- renqianluo/NAO
- quark0/darts
- khanrc/pt.darts
- dragen1860/DARTS-PyTorch
- falsr/FALSR
- moremnas/MoreMNAS
- MIT-HAN-LAB/ProxylessNAS
- Transfer Learning with Neural AutoML
- wandering007/nasnet-pytorch
- AnjieZheng/MnasNet-PyTorch
- melodyguan/enas
- carpedm20/ENAS-pytorch
- Designing neural networks through neuroevolution
- titu1994/progressive-neural-architecture-search
- chenxi116/PNASNet.pytorch
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- lixincn2015/Partial-Order-Pruning
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
- Designing neural networks through neuroevolution
-
**[Projects]**
-
-
2.) Lightweight Structures
-
**[Papers]**
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- tensorflow/tpu/models/official/efficientnet/
- Searching for MobileNetV3
- CGNet: A Light-weight Context Guided Network for Semantic Segmentation
- ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
- BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
- ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation - ITS 2017**]
- ThunderNet: Towards Real-time Generic Object Detection
- Pooling Pyramid Network for Object Detection
- tensorflow/models
- Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
- Pelee: A Real-Time Object Detection System on Mobile Devices
- Receptive Field Block Net for Accurate and Fast Object Detection
- ruinmessi/RFBNet
- FSSD: Feature Fusion Single Shot Multibox Detector
- Feature Pyramid Networks for Object Detection
- lukemelas/EfficientNet-PyTorch
- kuan-wang/pytorch-mobilenet-v3
- leaderj1001/MobileNetV3-Pytorch
- wutianyiRosun/CGNet
- sacmehta/ESPNetv2
- ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
- sacmehta/ESPNet
- ooooverflow/BiSeNet
- Eromera/erfnet_pytorch
- lyxok1/Tiny-DSOD
- Robert-JunWang/Pelee
- Robert-JunWang/PeleeNet
- ShuangXieIrene/ssds.pytorch
- lzx1413/PytorchSSD
- dlyldxwl/fssd.pytorch
-
-
4.) Hyperparameter Optimization
-
**[Projects]**
-
**[Papers]**
- Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
- Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features
- Google vizier: A service for black-box optimization
- On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice
-
**[Tutorials/Blogs]**
-
-
3.) Model Compression & Acceleration
-
**[Papers]**
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Rethinking the Value of Network Pruning
- Slimmable Neural Networks
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- AutoML for Model Compression (AMC): Trials and Tribulations - Trials-and-Tribulations) | [Pytorch]
- Learning Efficient Convolutional Networks through Network Slimming
- Channel Pruning for Accelerating Very Deep Neural Networks
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- Pruning Filters for Efficient ConvNets
- Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
- Quantizing deep convolutional networks for efficient inference: A whitepaper
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Post-training 4-bit quantization of convolution networks for rapid-deployment
- WRPN: Wide Reduced-Precision Networks
- Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy
- Model compression via distillation and quantization
- Fast Algorithms for Convolutional Neural Networks
- google-research/lottery-ticket-hypothesis
- JiahuiYu/slimmable_networks
- foolwood/pytorch-slimming
- yihui-he/channel-pruning
- jacobgil/pytorch-pruning
-
**[Projects]**
-
**[Tutorials/Blogs]**
-
-
Model Analyzer
-
**[Tutorials/Blogs]**
-
-
References
-
**[Tutorials/Blogs]**
-
Programming Languages
Categories
Sub Categories
Keywords
pytorch
15
deep-learning
8
neural-architecture-search
6
semantic-segmentation
5
imagenet
5
automl
4
edge-devices
3
machine-learning
3
convolutional-neural-networks
3
mobilenet
2
real-time
2
mobilenetv2
2
lightweight
2
mobilenetv3
2
object-detection
2
efficient
2
model-compression
2
fssd
2
rfb
2
ssd
2
acceleration
2
cityscapes
2
image-classification
2
hyperparameter-optimization
1
deep-neural-network
1
distributed
1
feature-engineering
1
hyperparameter-tuning
1
machine-learning-algorithms
1
mlops
1
nas
1
neural-network
1
python
1
tensorflow
1
ai
1
ai-agents
1
artificial-intelligence
1
auto-gpt
1
chatbot
1
adversarial-attacks
1
adversarial-examples
1
deep-learning-architectures
1
robustness
1
convolutional-networks
1
language-modeling
1
recurrent-networks
1
efficient-model
1
hardware-aware
1
on-device-ai
1
specialization
1