Official PyTorch Implementation of HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS 2021 Spotlight)

Overview

[NeurIPS 2021 Spotlight] HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning [Paper]

This is Official PyTorch implementation for HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning.

@inproceedings{lee2021help,
    title     = {HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning},
    author    = {Lee, Hayeon and Lee, Sewoong and Chong, Song and Hwang, Sung Ju},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year      = {2021}
} 

Overview

For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on hardware-aware NAS collect a large number of samples (e.g., accuracy and latency) from a target device, either builds a lookup table or a latency estimator. However, such approach is impractical in real-world scenarios as there exist numerous devices with different hardware specifications, and collecting samples from such a large number of devices will require prohibitive computational and monetary cost. To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples. To this end, we introduce novel hardware embeddings to embed any devices considering them as black-box functions that output latencies, and meta-learn the hardware-adaptive latency predictor in a device-dependent manner, using the hardware embeddings. We validate the proposed HELP for its latency estimation performance on unseen platforms, on which it achieves high estimation performance with as few as 10 measurement samples, outperforming all relevant baselines. We also validate end-to-end NAS frameworks using HELP against ones without it, and show that it largely reduces the total time cost of the base NAS method, in latency-constrained settings.

Prerequisites

  • Python 3.8 (Anaconda)
  • PyTorch 1.8.1
  • CUDA 10.2

Hardware spec used for meta-training the proposed HELP model

  • GPU: A single Nvidia GeForce RTX 2080Ti
  • CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz

Installation

$ conda create --name help python=3.8
$ conda activate help
$ conda install pytorch==1.8.1 torchvision cudatoolkit=10.2 -c pytorch
$ pip install nas-bench-201
$ pip install tqdm
$ conda install scipy
$ conda install pyyaml
$ conda install tensorboard

Contents

1. Experiments on NAS-Bench-201 Search Space

2. Experiments on FBNet Search Space

3. Experiments on OFA Search Space

4. Experiments on HAT Search Space

1. Reproduce Main Results on NAS-Bench-201 Search Space

We provide the code to reproduce the main results on NAS-Bench-201 search space as follows:

  • Computing architecture ranking correlation between latencies estimated by HELP and true measured latencies on unseen devices (Table 3).
  • Latency-constrained NAS Results with MetaD2A + HELP on unseen devices (Table 4).
  • Meta-Training HELP model.

1.1. Data Preparation and Model Checkpoint

We include all required datasets and checkpoints in this github repository.

1.2. [Meta-Test] Architecture ranking correlation

You can compute architecture ranking correlation between latencies estimated by HELP and true measured latencies on unseen devices on NAS-Bench-201 search space (Table 3):

$ python main.py --search_space nasbench201 \
		 --mode 'meta-test' \
		 --num_samples 10 \
		 --num_meta_train_sample 900 \
                 --load_path [Path of Checkpoint File] \
		 --meta_train_devices '1080ti_1,1080ti_32,1080ti_256,silver_4114,silver_4210r,samsung_a50,pixel3,essential_ph_1,samsung_s7' \
		 --meta_valid_devices 'titanx_1,titanx_32,titanx_256,gold_6240' \                 
                 --meta_test_devices 'titan_rtx_256,gold_6226,fpga,pixel2,raspi4,eyeriss' 

You can use checkpoint file provided by this git repository ./data/nasbench201/checkpoint/help_max_corr.pt as follows:

$ python main.py --search_space nasbench201 \
		 --mode 'meta-test' \
		 --num_samples 10 \
		 --num_meta_train_sample 900 \
                 --load_path './data/nasbench201/checkpoint/help_max_corr.pt' \
		 --meta_train_devices '1080ti_1,1080ti_32,1080ti_256,silver_4114,silver_4210r,samsung_a50,pixel3,essential_ph_1,samsung_s7' \
		 --meta_valid_devices 'titanx_1,titanx_32,titanx_256,gold_6240' \                 
                 --meta_test_devices 'titan_rtx_256,gold_6226,fpga,pixel2,raspi4,eyeriss' 

or you can use provided script:

$ bash script/run_meta_test_nasbench201.sh [GPU_NUM]

Architecture Ranking Correlation Results (Table 3)

Method # of Training Samples
From Target Device
Desktop GPU
(Titan RTX Batch 256)
Desktop CPU
(Intel Gold 6226)
Mobile
Pixel2
Raspi4 ASIC FPGA Mean
FLOPS - 0.950 0.826 0.765 0.846 0.437 0.900 0.787
Layer-wise Predictor - 0.667 0.866 - - - - 0.767
BRP-NAS 900 0.814 0.796 0.666 0.847 0.811 0.801 0.789
BRP-NAS
(+extra samples)
3200 0.822 0.805 0.693 0.853 0.830 0.828 0.805
HELP (Ours) 10 0.987 0.989 0.802 0.890 0.940 0.985 0.932

1.3. [Meta-Test] Efficient Latency-constrained NAS combined with MetaD2A

You can reproduce latency-constrained NAS results with MetaD2A + HELP on unseen devices on NAS-Bench-201 search space (Table 4):

$ python main.py --search_space nasbench201 --mode 'nas' \
                 --load_path [Path of Checkpoint File] \
                 --sampled_arch_path 'data/nasbench201/arch_generated_by_metad2a.txt' \
                 --nas_target_device [Device] \ 
                 --latency_constraint [Latency Constraint] 

For example, if you use checkpoint file provided by this git repository, then path of checkpoint file is ./data/nasbench201/checkpoint/help_max_corr.pt, if you set target device as CPU Intel Gold 6226 (gold_6226) with batch size 256 and target latency constraint as 11.0 (ms), command is as follows:

$ python main.py --search_space nasbench201 --mode 'nas' \
                 --load_path './data/nasbench201/checkpoint/help_max_corr.pt' \
                 --sampled_arch_path 'data/nasbench201/arch_generated_by_metad2a.txt' \
                 --nas_target_device gold_6226 \ 
                 --latency_constraint 11.0 

or you can use provided script:

$ bash script/run_nas_metad2a.sh [GPU_NUM]

Efficient Latency-constrained NAS Results (Table 4)

Device # of Training Samples
from Target Device
Latency
Constraint (ms)
Latency
(ms)
Accuracy
(%)
Neural Architecture
Config
GPU Titan RTX
(Batch 256)
titan_rtx_256
10 18.0
21.0
25.0
17.8
18.9
24.2
69.7
71.5
71.8
link
link
link
CPU Intel Gold 6226
gold_6226
10 8.0
11.0
14.0
8.0
10.7
14.3
67.3
70.2
72.1
link
link
link
Mobile Pixel2
pixel2
10 14.0
18.0
22.0
13.0
19.0
25.0
69.7
71.8
73.2
link
link
link
ASIC-Eyeriss
eyeriss
10 5.0
7.0
9.0
3.9
5.1
9.1
71.5
71.8
73.5
link
link
link
FPGA
fpga
10 4.0
5.0
6.0
3.8
4.7
7.4
70.2
71.8
73.5
link
link
link

1.4. Meta-Training HELP model

Note that this process is performed only once for all NAS results.

$ python main.py --search_space nasbench201 \
                 --mode 'meta-train' \
                 --num_samples 10 \
                 --num_meta_train_sample 900 \
                 --meta_train_devices '1080ti_1,1080ti_32,1080ti_256,silver_4114,silver_4210r,samsung_a50,pixel3,essential_ph_1,samsung_s7' \
                 --meta_valid_devices 'titanx_1,titanx_32,titanx_256,gold_6240' \           
                 --meta_test_devices 'titan_rtx_256,gold_6226,fpga,pixel2,raspi4,eyeriss' \
                 --exp_name [EXP_NAME] \
                 --seed 3 # e.g.) 1, 2, 3

or you can use provided script:

$ bash script/run_meta_training_nasbench201.sh [GPU_NUM]

The results (checkpoint file, log file etc) are saved in

./results/nasbench201/[EXP_NAME]

2. Reproduce Main Results on FBNet Search Space

We provide the code to reproduce the main results on FBNet search space as follows:

  • Computing architecture ranking correlation between latencies estimated by HELP and true measured latencies on unseen devices (Table 2).
  • Meta-Training HELP model.

2.1. Data Preparation and Model Checkpoint

We include all required datasets and checkpoints in this github repository.

2.2. [Meta-Test] Architecture ranking correlation

You can compute architecture ranking correlation between latencies estimated by HELP and true measured latencies on unseen devices on FBNet search space (Table 2):

$ python main.py --search_space fbnet \
	--mode 'meta-test' \
	--num_samples 10 \
	--num_episodes 4000 \
	--num_meta_train_sample 4000 \
	--load_path './data/fbnet/checkpoint/help_max_corr.pt' \
	--meta_train_devices '1080ti_1,1080ti_32,1080ti_64,silver_4114,silver_4210r,samsung_a50,pixel3,essential_ph_1,samsung_s7' \
	--meta_valid_devices 'titanx_1,titanx_32,titanx_64,gold_6240' \
	--meta_test_devices 'fpga,raspi4,eyeriss'

or you can use provided script:

$ bash script/run_meta_test_fbnet.sh [GPU_NUM]

Architecture Ranking Correlation Results (Table 2)

Method Raspi4 ASIC FPGA Mean
MAML 0.718 0.763 0.727 0.736
Meta-SGD 0.821 0.822 0.776 0.806
HELP (Ours) 0.887 0.943 0.892 0.910

2.3. Meta-Training HELP model

Note that this process is performed only once for all results.

$ python main.py --search_space fbnet \
	--mode 'meta-train' \
	--num_samples 10 \
	--num_episodes 4000 \
	--num_meta_train_sample 4000 \
	--exp_name [EXP_NAME] \
	--meta_train_devices '1080ti_1,1080ti_32,1080ti_64,silver_4114,silver_4210r,samsung_a50,pixel3,essential_ph_1,samsung_s7' \
	--meta_valid_devices 'titanx_1,titanx_32,titanx_64,gold_6240' \
	--meta_test_devices 'fpga,raspi4,eyeriss' \
	--seed 3 # e.g.) 1, 2, 3

or you can use provided script:

$ bash script/run_meta_training_fbnet.sh [GPU_NUM]

The results (checkpoint file, log file etc) are saved in

./results/fbnet/[EXP_NAME]

3. Reproduce Main Results on OFA Search Space

We provide the code to reproduce the main results on OFA search space as follows:

  • Latency-constrained NAS Results with accuracy predictor of OFA + HELP on unseen devices (Table 5).
  • Validating obatined neural architecture on ImageNet-1K.
  • Meta-Training HELP model.

3.1. Data Preparation and Model Checkpoint

We include required datasets except ImageNet-1K, and checkpoints in this github repository. To validate obatined neural architecture on ImageNet-1K, you should download ImageNet-1K (2012 ver.)

3.2. [Meta-Test] Efficient Latency-constrained NAS combined with accuracy predictor of OFA

You can reproduce latency-constrained NAS results with OFA + HELP on unseen devices on OFA search space (Table 5):

python main.py \
	--search_space ofa \
	--mode nas \
	--num_samples 10 \
	--seed 3 \
	--num_meta_train_sample 4000 \
	--load_path './data/ofa/checkpoint/help_max_corr.pt' \
	--nas_target_device [DEVICE_NAME] \
	--latency_constraint [LATENCY_CONSTRAINT] \
	--exp_name 'nas' \
	--meta_train_devices '2080ti_1,2080ti_32,2080ti_64,titan_xp_1,titan_xp_32,titan_xp_64,v100_1,v100_32,v100_64' \
	--meta_valid_devices 'titan_rtx_1,titan_rtx_32' \
	--meta_test_devices 'titan_rtx_64' 

For example,

$ python main.py \
	--search_space ofa \
	--mode nas \
	--num_samples 10 \
	--seed 3 \
	--num_meta_train_sample 4000 \
	--load_path './data/ofa/checkpoint/help_max_corr.pt' \
	--nas_target_device titan_rtx_64 \
	--latency_constraint 20 \
	--exp_name 'nas' \
	--meta_train_devices '2080ti_1,2080ti_32,2080ti_64,titan_xp_1,titan_xp_32,titan_xp_64,v100_1,v100_32,v100_64' \
	--meta_valid_devices 'titan_rtx_1,titan_rtx_32' \
	--meta_test_devices 'titan_rtx_64' 

or you can use provided script:

$ bash script/run_nas_ofa.sh [GPU_NUM]

Efficient Latency-constrained NAS Results (Table 5)

Device Sample from
Target Device
Latency
Constraint (ms)
Latency
(ms)
Accuracy
(%)
Architecture
config
GPU Titan RTX
(Batch 64)
10 20
23
28
20.3
23.1
28.6
76.0
76.8
77.9
link
link
link
CPU Intel Gold 6226 20 170
190
147
171
77.6
78.1
link
link
Jetson AGX Xavier 10 65
70
67.4
76.4
75.9
76.4
link
link

3.3. Validating obtained neural architecture on ImageNet-1K

$ python validate_imagenet.py \
		--config_path [Path of neural architecture config file]
		--imagenet_save_path [Path of ImageNet 1k]

for example,

$ python validate_imagenet.py \
		--config_path 'data/ofa/architecture_config/gpu_titan_rtx_64/latency_28.6ms_accuracy_77.9.json' \
		--imagenet_save_path './ILSVRC2012'

3.4. Meta-training HELP model

Note that this process is performed only once for all results.

$ python main.py --search_space ofa \
		--mode 'meta-train' \
		--num_samples 10 \
		--num_meta_train_sample 4000 \
		--exp_name [EXP_NAME] \
                --meta_train_devices '2080ti_1,2080ti_32,2080ti_64,titan_xp_1,titan_xp_32,titan_xp_64,v100_1,v100_32,v100_64' \
                --meta_valid_devices 'titan_rtx_1,titan_rtx_32' \
                --meta_test_devices 'titan_rtx_64' \
		--seed 3 # e.g.) 1, 2, 3

or you can use provided script:

$ bash script/run_meta_training_ofa.sh [GPU_NUM]

4. Main Results on HAT Search Space

We provide the neural architecture configurations to reproduce the results of machine translation (WMT'14 En-De Task) on HAT search space.

Efficient Latency-constrained NAS Results

Task Device Samples from
Target Device
Latency BLEU score Architecture
Config
WMT'14 En-De GPU NVIDIA Titan RTX 10 74.0ms
106.5ms
27.19
27.44
link
link
WMT'14 En-De CPU Intel Xeon Gold 6240 10 159.6ms
343.2ms
27.20
27.52
link
link

You can test models by BLEU score and Computing Latency.

Reference

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (ICML17)

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

Once-for-All: Train One Network and Specialize it for Efficient Deployment (ICLR20)

NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search (ICLR20)

BRP-NAS: Prediction-based NAS using GCNs (NeurIPS20)

HAT: Hardware Aware Transformers for Efficient Natural Language Processing (ACL20)

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets (ICLR21)

HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark (ICLR21)

Owner
Ph.D. student @ School of Computing, Korea Advanced Institute of Science and Technology (KAIST)
Wordle-solver - Wordle answer generation program in python

🟨 Wordle Solver 🟩 Wordle answer generation program in python ✔️ Requirements U

Dahyun Kang 4 May 28, 2022
SlotRefine: A Fast Non-Autoregressive Model forJoint Intent Detection and Slot Filling

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling Reference Main paper to be cited (Di Wu et al., 2020) @article

Moore 34 Nov 03, 2022
Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch

PyTorch implementation of Continuous Augmented Positional Embeddings (CAPE), by Likhomanenko et al. Enhance your Transformer positional embeddings with easy-to-use augmentations!

Guillermo Cámbara 26 Dec 13, 2022
Efficient 3D Backbone Network for Temporal Modeling

VoV3D is an efficient and effective 3D backbone network for temporal modeling implemented on top of PySlowFast. Diverse Temporal Aggregation and

102 Dec 06, 2022
Sound Event Detection with FilterAugment

Sound Event Detection with FilterAugment Official implementation of Heavily Augmented Sound Event Detection utilizing Weak Predictions (DCASE2021 Chal

43 Aug 28, 2022
Spectral Temporal Graph Neural Network (StemGNN in short) for Multivariate Time-series Forecasting

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting This repository is the official implementation of Spectral Temporal Gr

Microsoft 306 Dec 29, 2022
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
public repo for ESTER dataset and modeling (EMNLP'21)

Project / Paper Introduction This is the project repo for our EMNLP'21 paper: https://arxiv.org/abs/2104.08350 Here, we provide brief descriptions of

PlusLab 19 Oct 27, 2022
RSNA Intracranial Hemorrhage Detection with python

RSNA Intracranial Hemorrhage Detection This is the source code for the first place solution to the RSNA2019 Intracranial Hemorrhage Detection Challeng

24 Nov 30, 2022
University of Rochester 2021 Summer REU focusing on music sentiment transfer using CycleGAN

Music-Sentiment-Transfer University of Rochester 2021 Summer REU focusing on music sentiment transfer using CycleGAN Poster: Music Sentiment Transfer

Miles Sigel 2 Jan 24, 2022
"NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search".

NAS-Bench-301 This repository containts code for the paper: "NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search". The

AutoML-Freiburg-Hannover 57 Nov 30, 2022
A Real-Time-Strategy game for Deep Learning research

Description DeepRTS is a high-performance Real-TIme strategy game for Reinforcement Learning research. It is written in C++ for performance, but provi

Centre for Artificial Intelligence Research (CAIR) 156 Dec 19, 2022
An open source Python package for plasma science that is under development

PlasmaPy PlasmaPy is an open source, community-developed Python 3.7+ package for plasma science. PlasmaPy intends to be for plasma science what Astrop

PlasmaPy 444 Jan 07, 2023
This repository contains all the code and materials distributed in the 2021 Q-Programming Summer of Qode.

Q-Programming Summer of Qode This repository contains all the code and materials distributed in the Q-Programming Summer of Qode. If you want to creat

Sammarth Kumar 11 Jun 11, 2021
HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty

HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty Giorgio Cantarini, Francesca Odone, Nicoletta Noceti, Federi

18 Aug 02, 2022
Python Multi-Agent Reinforcement Learning framework

- Please pay attention to the version of SC2 you are using for your experiments. - Performance is *not* always comparable between versions. - The re

whirl 1.3k Jan 05, 2023
A Python package for generating concise, high-quality summaries of a probability distribution

GoodPoints A Python package for generating concise, high-quality summaries of a probability distribution GoodPoints is a collection of tools for compr

Microsoft 28 Oct 10, 2022
Visualizing lattice vibration information from phonon dispersion to atoms (For GPUMD)

Phonon-Vibration-Viewer (For GPUMD) Visualizing lattice vibration information from phonon dispersion for primitive atoms. In this tutorial, we will in

Liangting 6 Dec 10, 2022
ChatBot-Pytorch - A GPT-2 ChatBot implemented using Pytorch and Huggingface-transformers

ChatBot-Pytorch A GPT-2 ChatBot implemented using Pytorch and Huggingface-transf

ParZival 42 Dec 09, 2022
[3DV 2021] A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks

dispersion-score Official implementation of 3DV 2021 Paper A Dataset-dispersion Perspective on Reconstruction versus Recognition in Single-view 3D Rec

Yefan 7 May 28, 2022