NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search[slides][arXiv]

@inproceedings{  lu2020nsganetv2,title={{NSGANetV2}: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search},author={Zhichao Lu and Kalyanmoy Deb and Erik Goodman and Wolfgang Banzhaf and Vishnu Naresh Boddeti},booktitle={European Conference on Computer Vision (ECCV)},year={2020}}

Overview

Datasets

How to evalute NSGANetV2 models

""" NSGANetV2 pretrained modelsSyntax: python validation.py\    --dataset [imagenet/cifar10/...] --data /path/to/data\    --model /path/to/model/config/file --pretrained /path/to/model/weights"""

How to use MSuNAS to search

""" Bi-objective searchSyntax: python msunas.py\    --dataset [imagenet/cifar10/...] --data /path/to/dataset/images\    --save search-xxx \ # dir to save search results    --sec_obj [params/flops/cpu] \ # objective (in addition to top-1 acc)    --n_gpus 8 \ # number of available gpus    --supernet_path /path/to/supernet/weights\    --vld_size [10000/5000/...] \ # number of subset images from training set to guide search    --n_epochs [0/5]"""

How to choose architectures

""" Find architectures with objectives close to your preferencesSyntax: python post_search.py\    -n 3 \ # number of desired architectures you want, the most accurate archecture will always be selected    --save search-imagenet/final \ # path to the dir to store the selected architectures    --expr search-imagenet/iter_30.stats \ # path to last iteration stats file in experiment dir    --prefer top1#80+flops#150 \ # your preferences, i.e. you want an architecture with 80% top-1 acc. and 150M FLOPs    --supernet_path /path/to/imagenet/supernet/weights\"""

How to validate architectures

""" Fine-tune on ImageNet from inherited weightsSyntax: sh scripts/distributed_train.sh 8 \ # of available gpus    /path/to/imagenet/data/\    --model [nsganetv2_s/nsganetv2_m/...] \ # just for naming the output dir    --model-config /path/to/model/.config/file\    --initial-checkpoint /path/to/model/.inherited/file\    --img-size [192, ..., 224, ..., 256] \ # image resolution, check "r" in net.subnet    -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97\    --opt rmsproptf --opt-eps .001 -j 6 --warmup-lr 1e-6\    --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999\    --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .024\    --teacher /path/to/supernet/weights\"""

""" Fine-tune on CIFAR-10 from inherited weightsSyntax: python train_cifar.py\    --data /path/to/CIFAR-10/data/\    --model [nsganetv2_s/nsganetv2_m/...] \ # just for naming the output dir    --model-config /path/to/model/.config/file\    --img-size [192, ..., 224, ..., 256] \ # image resolution, check "r" in net.subnet    --drop 0.2 --drop-path 0.2\    --cutout --autoaugment --save"""

More Use Cases (coming soon)

Requirements