Open source implementation of AceNAS: Learning to Rank Ace Neural Architectures with Weak Supervision of Weight Sharing

Related tags

Deep Learningnasautoml
Overview

AceNAS

This repo is the experiment code of AceNAS, and is not considered as an official release. We are working on integrating AceNAS as a built-in strategy provided in NNI.

Data Preparation

  1. Download our prepared data from Google Drive. The directory should look like this:
data
├── checkpoints
│   ├── acenas-m1.pth.tar
│   ├── acenas-m2.pth.tar
│   └── acenas-m3.pth.tar
├── gcn
│   ├── nasbench101_gt_all.pkl
│   ├── nasbench201cifar10_gt_all.pkl
│   ├── nasbench201_gt_all.pkl
│   ├── nasbench201imagenet_gt_all.pkl
│   ├── nds_amoeba_gt_all.pkl
│   ├── nds_amoebaim_gt_all.pkl
│   ├── nds_dartsfixwd_gt_all.pkl
│   ├── nds_darts_gt_all.pkl
│   ├── nds_dartsim_gt_all.pkl
│   ├── nds_enasfixwd_gt_all.pkl
│   ├── nds_enas_gt_all.pkl
│   ├── nds_enasim_gt_all.pkl
│   ├── nds_nasnet_gt_all.pkl
│   ├── nds_nasnetim_gt_all.pkl
│   ├── nds_pnasfixwd_gt_all.pkl
│   ├── nds_pnas_gt_all.pkl
│   ├── nds_pnasim_gt_all.pkl
│   ├── nds_supernet_evaluate_all_test1_amoeba.json
│   ├── nds_supernet_evaluate_all_test1_dartsfixwd.json
│   ├── nds_supernet_evaluate_all_test1_darts.json
│   ├── nds_supernet_evaluate_all_test1_enasfixwd.json
│   ├── nds_supernet_evaluate_all_test1_enas.json
│   ├── nds_supernet_evaluate_all_test1_nasnet.json
│   ├── nds_supernet_evaluate_all_test1_pnasfixwd.json
│   ├── nds_supernet_evaluate_all_test1_pnas.json
│   ├── supernet_evaluate_all_test1_nasbench101.json
│   ├── supernet_evaluate_all_test1_nasbench201cifar10.json
│   ├── supernet_evaluate_all_test1_nasbench201imagenet.json
│   └── supernet_evaluate_all_test1_nasbench201.json
├── nb201
│   ├── split-cifar100.txt
│   ├── split-cifar10-valid.txt
│   └── split-imagenet-16-120.txt
├── proxyless
│   ├── imagenet
│   │   ├── augment_files.txt
│   │   ├── test_files.txt
│   │   ├── train_files.txt
│   │   └── val_files.txt
│   ├── proxyless-84ms-train.csv
│   ├── proxyless-ws-results.csv
│   └── tunas-proxylessnas-search.csv
└── tunas
    ├── imagenet_valid_split_filenames.txt
    ├── random_architectures.csv
    └── searched_architectures.csv
  1. (Required for benchmark experiments) Download CIFAR-10, CIFAR-100, ImageNet-16-120 dataset and also put them under data.
data
├── cifar10
│   └── cifar-10-batches-py
│       ├── batches.meta
│       ├── data_batch_1
│       ├── data_batch_2
│       ├── data_batch_3
│       ├── data_batch_4
│       ├── data_batch_5
│       ├── readme.html
│       └── test_batch
├── cifar100
│   └── cifar-100-python
│       ├── meta
│       ├── test
│       └── train
└── imagenet16
    ├── train_data_batch_1
    ├── train_data_batch_10
    ├── train_data_batch_2
    ├── train_data_batch_3
    ├── train_data_batch_4
    ├── train_data_batch_5
    ├── train_data_batch_6
    ├── train_data_batch_7
    ├── train_data_batch_8
    ├── train_data_batch_9
    └── val_data

  1. (Required for ImageNet experiments) Prepare ImageNet. You can put it anywhere.

  2. (Optional) Copy tunas (https://github.com/google-research/google-research/tree/master/tunas) to a folder named tunas.

Evaluate pre-trained models.

We provide 3 checkpoints obtained from 3 different runs in data/checkpoints. Please evaluate them via the following command.

python -m tools.standalone.imagenet_eval acenas-m1 /path/to/your/imagenet
python -m tools.standalone.imagenet_eval acenas-m2 /path/to/your/imagenet
python -m tools.standalone.imagenet_eval acenas-m3 /path/to/your/imagenet

Train supernet

python -m tools.supernet.nasbench101 experiments/supernet/nasbench101.yml
python -m tools.supernet.nasbench201 experiments/supernet/nasbench201.yml
python -m tools.supernet.nds experiments/supernet/darts.yml
python -m tools.supernet.proxylessnas experiments/supernet/proxylessnas.yml

Please refer to experiments/supernet folder for more configurations.

Benchmark experiments

We've already provided weight-sharing results from supernet so that you do not have to train you own. The provided files can be found in json files located under data/gcn.

# pretrain
python -m gcn.benchmarks.pretrain data/gcn/supernet_evaluate_all_test1_${SEARCHSPACE}.json data/gcn/${SEARCHSPACE}_gt_all.pkl --metric_keys top1 flops params
# finetune
python -m gcn.benchmarks.train --use_train_samples --budget {budget} --test_dataset data/gcn/${SEARCHSPACE}_gt_all.pkl --iteration 5 \
    --loss lambdarank --gnn_type gcn --early_stop_patience 50 --learning_rate 0.005 --opt_type adam --wd 5e-4 --epochs 300 --bs 20 \
    --resume /path/to/previous/output.pt

Running baselines

BRP-NAS:

# pretrain
python -m gcn.benchmarks.pretrain data/gcn/supernet_evaluate_all_test1_${SEARCHSPACE}.json data/gcn/${SEARCHSPACE}_gt_all.pkl --metric_keys flops
# finetune
python -m gcn.benchmarks.train --use_train_samples --budget ${BUDGET} --test_dataset data/gcn/${SEARCHSPACE}_gt_all.pkl --iteration 5 \
    --loss brp --gnn_type brp --early_stop_patience 35 --learning_rate 0.00035 \
    --opt_type adamw --wd 5e-4 --epochs 250 --bs 64 --resume /path/to/previous/output.pt

Vanilla:

python -m gcn.benchmarks.train --use_train_samples --budget ${BUDGET} --test_dataset data/gcn/${SEARCHSPACE}_gt_all.pkl --iteration 1 \
    --loss mse --gnn_type vanilla --n_hidden 144 --learning_rate 2e-4 --opt_type adam --wd 1e-3 --epochs 300 --bs 10

ProxylessNAS search space

Train GCN

python -m gcn.proxyless.pretrain --metric_keys ws_accuracy simulated_pixel1_time_ms flops params
python -m gcn.proxyless.train --loss lambdarank --early_stop_patience 50 --learning_rate 0.002 --opt_type adam --wd 5e-4 --epochs 300 --bs 20 \
    --resume /path/to/previous/output.pth

Train final model

Validation set:

python -m torch.distributed.launch --nproc_per_node=16 \
    --use_env --module \
    tools.standalone.imagenet_train \
    --output "$OUTPUT_DIR" "$ARCH" "$IMAGENET_DIR" \
    -b 256 --lr 2.64 --warmup-lr 0.1 \
    --warmup-epochs 5 --epochs 90 --sched cosine --num-classes 1000 \
    --opt rmsproptf --opt-eps 1. --weight-decay 4e-5 -j 8 --dist-bn reduce \
    --bn-momentum 0.01 --bn-eps 0.001 --drop 0. --no-held-out-val

Test set:

python -m torch.distributed.launch --nproc_per_node=16 \
    --use_env --module \
    tools.standalone.imagenet_train \
    --output "$OUTPUT_DIR" "$ARCH" "$IMAGENET_DIR" \
    -b 256 --lr 2.64 --warmup-lr 0.1 \
    --warmup-epochs 9 --epochs 360 --sched cosine --num-classes 1000 \
    --opt rmsproptf --opt-eps 1. --weight-decay 4e-5 -j 8 --dist-bn reduce \
    --bn-momentum 0.01 --bn-eps 0.001 --drop 0.15
Owner
Yuge Zhang
Yuge Zhang
GitHub Repository
KinectFusion implemented in Python with PyTorch

KinectFusion implemented in Python with PyTorch This is a lightweight Python implementation of KinectFusion. All the core functions (TSDF volume, fram

Jingwen Wang 80 Jan 03, 2023
Tools for computational pathology

A toolkit for computational pathology and machine learning. View documentation Please cite our paper Installation There are several ways to install Pa

254 Dec 12, 2022
Source Code for DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (https://arxiv.org/pdf/2012.01775.pdf)

DialogBERT This is a PyTorch implementation of the DialogBERT model described in DialogBERT: Neural Response Generation via Hierarchical BERT with Dis

Xiaodong Gu 67 Jan 06, 2023
FANet - Real-time Semantic Segmentation with Fast Attention

FANet Real-time Semantic Segmentation with Fast Attention Ping Hu, Federico Perazzi, Fabian Caba Heilbron, Oliver Wang, Zhe Lin, Kate Saenko , Stan Sc

Ping Hu 42 Nov 30, 2022
Code for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing CVPR 2021. Project page: https://kai-46.github.io/

Kai Zhang 141 Dec 14, 2022
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

Antoine Caillon 589 Jan 02, 2023
This is an official implementation for "Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation".

Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation This repo is the official implementation of Exploiting Temporal Con

Vegetabird 241 Jan 07, 2023
CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

CLIP2Video: Mastering Video-Text Retrieval via Image CLIP The implementation of paper CLIP2Video: Mastering Video-Text Retrieval via Image CLIP. CLIP2

168 Dec 29, 2022
Official PyTorch code for the paper: "Point-Based Modeling of Human Clothing" (ICCV 2021)

Point-Based Modeling of Human Clothing Paper | Project page | Video This is an official PyTorch code repository of the paper "Point-Based Modeling of

Visual Understanding Lab @ Samsung AI Center Moscow 64 Nov 22, 2022
Implementation for the IJCAI2021 work "Beyond the Spectrum: Detecting Deepfakes via Re-synthesis"

Beyond the Spectrum Implementation for the IJCAI2021 work "Beyond the Spectrum: Detecting Deepfakes via Re-synthesis" by Yang He, Ning Yu, Margret Keu

Yang He 27 Jan 07, 2023
DexterRedTool - Dexter's Red Team Tool that creates cronjob/task scheduler to consistently creates users

DexterRedTool Author: Dexter Delandro CSEC 473 - Spring 2022 This tool persisten

2 Feb 16, 2022
The Pytorch implementation for "Video-Text Pre-training with Learned Regions"

Region_Learner The Pytorch implementation for "Video-Text Pre-training with Learned Regions" (arxiv) We are still cleaning up the code further and pre

Rui Yan 0 Mar 20, 2022
a reimplementation of Holistically-Nested Edge Detection in PyTorch

pytorch-hed This is a personal reimplementation of Holistically-Nested Edge Detection [1] using PyTorch. Should you be making use of this work, please

Simon Niklaus 375 Dec 06, 2022
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators [Project Website] [Replicate.ai Project] StyleGAN-NADA: CLIP-Guided Domain Adaptation

992 Dec 30, 2022
Differential fuzzing for the masses!

NEZHA NEZHA is an efficient and domain-independent differential fuzzer developed at Columbia University. NEZHA exploits the behavioral asymmetries bet

147 Dec 05, 2022
A clean and robust Pytorch implementation of PPO on continuous action space.

PPO-Continuous-Pytorch I found the current implementation of PPO on continuous action space is whether somewhat complicated or not stable. And this is

XinJingHao 56 Dec 16, 2022
使用深度学习框架提取视频硬字幕；docker容器免安装深度学习库，使用本地api接口使得界面和后端识别分离；

extract-video-subtittle 使用深度学习框架提取视频硬字幕； 本地识别无需联网； CPU识别速度可观； 容器提供API接口； 运行环境 本项目运行环境非常好搭建，我做好了docker容器免安装各种深度学习包； 提供windows界面操作； 容器为CPU版本； 视频演示 https

歌者 16 Aug 06, 2022
Implementation of ReSeg using PyTorch

Implementation of ReSeg using PyTorch ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation Pascal-Part Annotations Pascal VOC 2010

Onur Kaplan 46 Nov 23, 2022
Train the HRNet model on ImageNet

High-resolution networks (HRNets) for Image classification News [2021/01/20] Add some stronger ImageNet pretrained models, e.g., the HRNet_W48_C_ssld_

HRNet 866 Jan 04, 2023
Anderson Acceleration for Deep Learning

Anderson Accelerated Deep Learning (AADL) AADL is a Python package that implements the Anderson acceleration to speed-up the training of deep learning

Oak Ridge National Laboratory 7 Nov 24, 2022