Differentiable architecture search for convolutional and recurrent networks

Overview

Differentiable Architecture Search

Code accompanying the paper

DARTS: Differentiable Architecture Search
Hanxiao Liu, Karen Simonyan, Yiming Yang.
arXiv:1806.09055.

darts

The algorithm is based on continuous relaxation and gradient descent in the architecture space. It is able to efficiently design high-performance convolutional architectures for image classification (on CIFAR-10 and ImageNet) and recurrent architectures for language modeling (on Penn Treebank and WikiText-2). Only a single GPU is required.

Requirements

Python >= 3.5.5, PyTorch == 0.3.1, torchvision == 0.2.0

NOTE: PyTorch 0.4 is not supported at this moment and would lead to OOM.

Datasets

Instructions for acquiring PTB and WT2 can be found here. While CIFAR-10 can be automatically downloaded by torchvision, ImageNet needs to be manually downloaded (preferably to a SSD) following the instructions here.

Pretrained models

The easist way to get started is to evaluate our pretrained DARTS models.

CIFAR-10 (cifar10_model.pt)

cd cnn && python test.py --auxiliary --model_path cifar10_model.pt
  • Expected result: 2.63% test error rate with 3.3M model params.

PTB (ptb_model.pt)

cd rnn && python test.py --model_path ptb_model.pt
  • Expected result: 55.68 test perplexity with 23M model params.

ImageNet (imagenet_model.pt)

cd cnn && python test_imagenet.py --auxiliary --model_path imagenet_model.pt
  • Expected result: 26.7% top-1 error and 8.7% top-5 error with 4.7M model params.

Architecture search (using small proxy models)

To carry out architecture search using 2nd-order approximation, run

cd cnn && python train_search.py --unrolled     # for conv cells on CIFAR-10
cd rnn && python train_search.py --unrolled     # for recurrent cells on PTB

Note the validation performance in this step does not indicate the final performance of the architecture. One must train the obtained genotype/architecture from scratch using full-sized models, as described in the next section.

Also be aware that different runs would end up with different local minimum. To get the best result, it is crucial to repeat the search process with different seeds and select the best cell(s) based on validation performance (obtained by training the derived cell from scratch for a small number of epochs). Please refer to fig. 3 and sect. 3.2 in our arXiv paper.

progress_convolutional_normal progress_convolutional_reduce progress_recurrent

Figure: Snapshots of the most likely normal conv, reduction conv, and recurrent cells over time.

Architecture evaluation (using full-sized models)

To evaluate our best cells by training from scratch, run

cd cnn && python train.py --auxiliary --cutout            # CIFAR-10
cd rnn && python train.py                                 # PTB
cd rnn && python train.py --data ../data/wikitext-2 \     # WT2
            --dropouth 0.15 --emsize 700 --nhidlast 700 --nhid 700 --wdecay 5e-7
cd cnn && python train_imagenet.py --auxiliary            # ImageNet

Customized architectures are supported through the --arch flag once specified in genotypes.py.

The CIFAR-10 result at the end of training is subject to variance due to the non-determinism of cuDNN back-prop kernels. It would be misleading to report the result of only a single run. By training our best cell from scratch, one should expect the average test error of 10 independent runs to fall in the range of 2.76 +/- 0.09% with high probability.

cifar10 ptb ptb

Figure: Expected learning curves on CIFAR-10 (4 runs), ImageNet and PTB.

Visualization

Package graphviz is required to visualize the learned cells

python visualize.py DARTS

where DARTS can be replaced by any customized architectures in genotypes.py.

Citation

If you use any part of this code in your research, please cite our paper:

@article{liu2018darts,
  title={DARTS: Differentiable Architecture Search},
  author={Liu, Hanxiao and Simonyan, Karen and Yang, Yiming},
  journal={arXiv preprint arXiv:1806.09055},
  year={2018}
}
Owner
Hanxiao Liu
Research Scientist @ Google Brain
Hanxiao Liu
Deep Residual Networks with 1K Layers

Deep Residual Networks with 1K Layers By Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Microsoft Research Asia (MSRA). Table of Contents Introduc

Kaiming He 856 Jan 06, 2023
A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

A Light and Fast Face Detector for Edge Devices Big News: LFD, which is a big update of LFFD, now is released (2021.03.09). It is strongly recommended

YonghaoHe 1.3k Dec 25, 2022
URIE: Universal Image Enhancementfor Visual Recognition in the Wild

URIE: Universal Image Enhancementfor Visual Recognition in the Wild This is the implementation of the paper "URIE: Universal Image Enhancement for Vis

Taeyoung Son 43 Sep 12, 2022
ROS-UGV-Control-Interface - Control interface which can be used in any UGV

ROS-UGV-Control-Interface Cam Closed: Cam Opened:

Ahmet Fatih Akcan 1 Nov 04, 2022
classify fashion-mnist dataset with pytorch

Fashion-Mnist Classifier with PyTorch Inference 1- clone this repository: git clone https://github.com/Jhamed7/Fashion-Mnist-Classifier.git 2- Instal

1 Jan 14, 2022
Code for our EMNLP 2021 paper "Learning Kernel-Smoothed Machine Translation with Retrieved Examples"

KSTER Code for our EMNLP 2021 paper "Learning Kernel-Smoothed Machine Translation with Retrieved Examples" [paper]. Usage Download the processed datas

jiangqn 23 Nov 24, 2022
Open & Efficient for Framework for Aspect-based Sentiment Analysis

PyABSA - Open & Efficient for Framework for Aspect-based Sentiment Analysis Fast & Low Memory requirement & Enhanced implementation of Local Context F

YangHeng 567 Jan 07, 2023
A SAT-based sudoku solver

SAT Sudoku solver A SAT-based Sudoku solver made in the context of a small project in the "Logic Problem Solving" class in the first year at the Polyt

Alexandre Malfreyt 5 Apr 15, 2022
Quantized tflite models for ailia TFLite Runtime

ailia-models-tflite Quantized tflite models for ailia TFLite Runtime About ailia TFLite Runtime ailia TF Lite Runtime is a TensorFlow Lite compatible

ax Inc. 13 Dec 23, 2022
Sinkformers: Transformers with Doubly Stochastic Attention

Code for the paper : "Sinkformers: Transformers with Doubly Stochastic Attention" Paper You will find our paper here. Compat This package has been dev

Michael E. Sander 31 Dec 29, 2022
efficient neural audio synthesis in the waveform domain

neural waveshaping synthesis real-time neural audio synthesis in the waveform domain paper • website • colab • audio by Ben Hayes, Charalampos Saitis,

Ben Hayes 169 Dec 23, 2022
Official PyTorch implementation of Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval.

Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval PyTorch This is the PyTorch implementation of Retrieve in Style: Unsupervised Fa

60 Oct 12, 2022
WebUAV-3M: A Benchmark Unveiling the Power of Million-Scale Deep UAV Tracking

WebUAV-3M: A Benchmark Unveiling the Power of Million-Scale Deep UAV Tracking [Paper Link] Abstract In this work, we contribute a new million-scale Un

25 Jan 01, 2023
Implementation of Hire-MLP: Vision MLP via Hierarchical Rearrangement and An Image Patch is a Wave: Phase-Aware Vision MLP.

Hire-Wave-MLP.pytorch Implementation of Hire-MLP: Vision MLP via Hierarchical Rearrangement and An Image Patch is a Wave: Phase-Aware Vision MLP Resul

Nevermore 29 Oct 28, 2022
code for Grapadora research paper experimentation

Road feature embedding selection method Code for research paper experimentation Abstract Traffic forecasting models rely on data that needs to be sens

Eric López Manibardo 0 May 26, 2022
Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

Unofficial pytorch implementation of the paper "Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective"

16 Nov 21, 2022
Code for generating a single image pretraining dataset

Single Image Pretraining of Visual Representations As shown in the paper A critical analysis of self-supervision, or what we can learn from a single i

Yuki M. Asano 12 Dec 19, 2022
Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation

UniFuse (RAL+ICRA2021) Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation, arXiv, Demo Preparation I

Alibaba 47 Dec 26, 2022
Implementation for Panoptic-PolarNet (CVPR 2021)

Panoptic-PolarNet This is the official implementation of Panoptic-PolarNet. [ArXiv paper] Introduction Panoptic-PolarNet is a fast and robust LiDAR po

Zixiang Zhou 126 Jan 01, 2023
Offline Multi-Agent Reinforcement Learning Implementations: Solving Overcooked Game with Data-Driven Method

Overcooked-AI We suppose to apply traditional offline reinforcement learning technique to multi-agent algorithm. In this repository, we implemented be

Baek In-Chang 14 Sep 16, 2022