Ld NetEfficient Contextualized Representation: Language Model Pruning for Sequence Labeling
Stars: ✭ 148 (+678.95%)
LycorisA lightweight and easy-to-use deep learning framework with neural architecture search.
Stars: ✭ 180 (+847.37%)
Model OptimizationA toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Stars: ✭ 992 (+5121.05%)
Aw nasaw_nas: A Modularized and Extensible NAS Framework
Stars: ✭ 152 (+700%)
JfasttextJava interface for fastText
Stars: ✭ 193 (+915.79%)
Deep architect legacyDeepArchitect: Automatically Designing and Training Deep Architectures
Stars: ✭ 144 (+657.89%)
Channel PruningChannel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
Stars: ✭ 979 (+5052.63%)
SgasSGAS: Sequential Greedy Architecture Search (CVPR'2020) https://www.deepgcns.org/auto/sgas
Stars: ✭ 137 (+621.05%)
Collaborative DistillationPyTorch code for our CVPR'20 paper "Collaborative Distillation for Ultra-Resolution Universal Style Transfer"
Stars: ✭ 138 (+626.32%)
Awesome AutodlA curated list of automated deep learning (including neural architecture search and hyper-parameter optimization) resources.
Stars: ✭ 1,819 (+9473.68%)
rnn darts fastaiImplement Differentiable Architecture Search (DARTS) for RNN with fastai
Stars: ✭ 21 (+10.53%)
PocketflowAn Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Stars: ✭ 2,672 (+13963.16%)
Keras model compressionModel Compression Based on Geoffery Hinton's Logit Regression Method in Keras applied to MNIST 16x compression over 0.95 percent accuracy.An Implementation of "Distilling the Knowledge in a Neural Network - Geoffery Hinton et. al"
Stars: ✭ 59 (+210.53%)
BitPackBitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.
Stars: ✭ 36 (+89.47%)
AmlaAutoML frAmework for Neural Networks
Stars: ✭ 119 (+526.32%)
LightctrLightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.
Stars: ✭ 644 (+3289.47%)
PetridishnnCode for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search
Stars: ✭ 112 (+489.47%)
Pretrained Language ModelPretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Stars: ✭ 2,033 (+10600%)
GraphnasThis directory contains code necessary to run the GraphNAS algorithm.
Stars: ✭ 104 (+447.37%)
Ghostnet.pytorch[CVPR2020] GhostNet: More Features from Cheap Operations
Stars: ✭ 440 (+2215.79%)
Robnets[CVPR 2020] When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
Stars: ✭ 95 (+400%)
Kd libA Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Stars: ✭ 173 (+810.53%)
Autodl ProjectsAutomated deep learning algorithms implemented in PyTorch.
Stars: ✭ 1,187 (+6147.37%)
Mtlnas[CVPR 2020] MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
Stars: ✭ 58 (+205.26%)
Nsganetv2[ECCV2020] NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
Stars: ✭ 52 (+173.68%)
Amc[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Stars: ✭ 298 (+1468.42%)
EfficientnasTowards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906
Stars: ✭ 44 (+131.58%)
DS-Net(CVPR 2021, Oral) Dynamic Slimmable Network
Stars: ✭ 204 (+973.68%)
Morph NetFast & Simple Resource-Constrained Learning of Deep Network Structure
Stars: ✭ 937 (+4831.58%)
Soft Filter PruningSoft Filter Pruning for Accelerating Deep Convolutional Neural Networks
Stars: ✭ 291 (+1431.58%)
Slimmable networksSlimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
Stars: ✭ 708 (+3626.32%)
HawqQuantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
Stars: ✭ 108 (+468.42%)
Fasterseg[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
Stars: ✭ 438 (+2205.26%)
Neural Architecture SearchBasic implementation of [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578).
Stars: ✭ 352 (+1752.63%)
DartsDifferentiable architecture search for convolutional and recurrent networks
Stars: ✭ 3,463 (+18126.32%)
Pnasnet.pytorchPyTorch implementation of PNASNet-5 on ImageNet
Stars: ✭ 309 (+1526.32%)
allie🤖 A machine learning framework for audio, text, image, video, or .CSV files (50+ featurizers and 15+ model trainers).
Stars: ✭ 93 (+389.47%)
Awesome Automl PapersA curated list of automated machine learning papers, articles, tutorials, slides and projects
Stars: ✭ 3,198 (+16731.58%)
Bert Of Theseus⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).
Stars: ✭ 209 (+1000%)
ArchaiReproducible Rapid Research for Neural Architecture Search (NAS)
Stars: ✭ 266 (+1300%)
ZAQ-codeCVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)
Stars: ✭ 59 (+210.53%)
NEATESTNEATEST: Evolving Neural Networks Through Augmenting Topologies with Evolution Strategy Training
Stars: ✭ 13 (-31.58%)
Micronetmicronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Stars: ✭ 1,232 (+6384.21%)
InterstellarInterstellar: Searching Recurrent Architecture for Knowledge Graph Embedding. NeurIPS 2020.
Stars: ✭ 28 (+47.37%)
FastPosepytorch realtime multi person keypoint estimation
Stars: ✭ 36 (+89.47%)
nas-encodingsEncodings for neural architecture search
Stars: ✭ 29 (+52.63%)
awesome-transformer-searchA curated list of awesome resources combining Transformers with Neural Architecture Search
Stars: ✭ 194 (+921.05%)
AutoSpeech[InterSpeech 2020] "AutoSpeech: Neural Architecture Search for Speaker Recognition" by Shaojin Ding*, Tianlong Chen*, Xinyu Gong, Weiwei Zha, Zhangyang Wang
Stars: ✭ 195 (+926.32%)
Torch PruningA pytorch pruning toolkit for structured neural network pruning and layer dependency maintaining.
Stars: ✭ 193 (+915.79%)
Amc Models[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Stars: ✭ 154 (+710.53%)
Enas PytorchPyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
Stars: ✭ 2,506 (+13089.47%)