Learning Versatile Neural Architectures by Propagating Network Codes

Related tags

Deep LearningNCP
Overview

Learning Versatile Neural Architectures by Propagating Network Codes

Mingyu Ding, Yuqi Huo, Haoyu Lu, Linjie Yang, Zhe Wang, Zhiwu Lu, Jingdong Wang, Ping Luo

diagram

Introduction

This work includes:
(1) NAS-Bench-MR, a NAS benchmark built on four challenging datasets under practical training settings for learning task-transferable architectures.
(2) An efficient predictor-based algorithm Network Coding Propagation (NCP), which back-propagates the gradients of neural predictors to directly update architecture codes along desired gradient directions for various objectives.

This framework is implemented and tested with Ubuntu/Mac OS, CUDA 9.0/10.0, Python 3, Pytorch 1.3-1.6, NVIDIA Tesla V100/CPU.

Dataset

We build our benchmark on four computer vision tasks, i.e., image classification (ImageNet), semantic segmentation (CityScapes), 3D detection (KITTI), and video recognition (HMDB51). Totally 9 different settings are included, as shown in the data/*/trainval.pkl folders.

Note that each .pkl file contains more than 2500 architectures, and their corresponding evaluation results under multiple metrics. The original training logs and checkpoints (including model weights and optimizer data) will be uploaded to Google drive (more than 4T). We will share the download link once the upload is complete.

Quick start

First, train the predictor

python3 tools/train_predictor.py  # --cfg configs/seg.yaml

Then, edit architecture based on desired gradients

python3 tools/ncp.py  # --cfg configs/seg.yaml

Examples

  • An example in NAS-Bench-MR (Seg):
{'mIoU': 70.57,
 'mAcc': 80.07,
 'aAcc': 95.29,
 'input_channel': [16, 64],
 # [num_branches, [num_convs], [num_channels]]
 'network_setting': [[1, [3], [128]],
  [2, [3, 3], [32, 48]],
  [2, [3, 3], [32, 48]],
  [2, [3, 3], [32, 48]],
  [3, [2, 3, 2], [16, 32, 16]],
  [3, [2, 3, 2], [16, 32, 16]],
  [4, [2, 4, 1, 1], [96, 112, 48, 80]]],
 'last_channel': 112,
 # [num_branches, num_block1, num_convs1, num_channels1, ..., num_block4, num_convs4, num_channels4, last_channel]
 'embedding': [16, 64, 1, 3, 128, 3, 3, 3, 32, 48, 2, 2, 3, 2, 16, 32, 16, 1, 2, 4, 1, 1, 96, 112, 48, 80]
}
  • Load Datasets:
import pickle
exps = pickle.load(open('data/seg/trainval.pkl', 'rb'))
# Then process each item in exps
  • Load Model / Get Params and Flops (based on the thop library):
import torch
from thop import profile
from models.supernet import MultiResolutionNet

# Get model using input_channel & network_setting & last_channel
model = MultiResolutionNet(input_channel=[16, 64],
                           network_setting=[[1, [3], [128]],
                            [2, [3, 3], [32, 48]],
                            [2, [3, 3], [32, 48]],
                            [2, [3, 3], [32, 48]],
                            [3, [2, 3, 2], [16, 32, 16]],
                            [3, [2, 3, 2], [16, 32, 16]],
                            [4, [2, 4, 1, 1], [96, 112, 48, 80]]],
                          last_channel=112)

# Get Flops and Parameters
input = torch.randn(1, 3, 224, 224)
macs, params = profile(model, inputs=(input, ))  

structure

Data Format

Each code in data/search_list.txt denotes an architecture. It can be load in our supernet as follows:

  • Code2Setting
params = '96_128-1_1_1_48-1_2_1_1_128_8-1_3_1_1_1_128_128_120-4_4_4_4_4_4_128_128_128_128-64'
embedding = [int(item) for item in params.replace('-', '_').split('_')]

embedding = [ 96, 128,   1,   1,  48,   1,   1,   1, 128,   8,   1,   1,
           1,   1, 128, 128, 120,   4,   4,   4,   4,   4, 128, 128,
         128, 128, 64]
input_channels = embedding[0:2]
block_1 = embedding[2:3] + [1] + embedding[3:5]
block_2 = embedding[5:6] + [2] + embedding[6:10]
block_3 = embedding[10:11] + [3] + embedding[11:17]
block_4 = embedding[17:18] + [4] + embedding[18:26]
last_channels = embedding[26:27]
network_setting = []
for item in [block_1, block_2, block_3, block_4]:
    for _ in range(item[0]):
        network_setting.append([item[1], item[2:-int(len(item) / 2 - 1)], item[-int(len(item) / 2 - 1):]])

# network_setting = [[1, [1], [48]], 
#  [2, [1, 1], [128, 8]],
#  [3, [1, 1, 1], [128, 128, 120]], 
#  [4, [4, 4, 4, 4], [128, 128, 128, 128]], 
#  [4, [4, 4, 4, 4], [128, 128, 128, 128]], 
#  [4, [4, 4, 4, 4], [128, 128, 128, 128]], 
#  [4, [4, 4, 4, 4], [128, 128, 128, 128]]]
# input_channels = [96, 128]
# last_channels = [64]
  • Setting2Code
input_channels = [str(item) for item in input_channels]
block_1 = [str(item) for item in block_1]
block_2 = [str(item) for item in block_2]
block_3 = [str(item) for item in block_3]
block_4 = [str(item) for item in block_4]
last_channels = [str(item) for item in last_channels]

params = [input_channels, block_1, block_2, block_3, block_4, last_channels]
params = ['_'.join(item) for item in params]
params = '-'.join(params)
# params
# 96_128-1_1_1_48-1_2_1_1_128_8-1_3_1_1_1_128_128_120-4_4_4_4_4_4_128_128_128_128-64'

License

For academic use, this project is licensed under the 2-clause BSD License. For commercial use, please contact the author.

Owner
Mingyu Ding
Mingyu Ding
Synthetic structured data generators

Join us on What is Synthetic Data? Synthetic data is artificially generated data that is not collected from real world events. It replicates the stati

YData 850 Jan 07, 2023
Deep learning algorithms for muon momentum estimation in the CMS Trigger System

Deep learning algorithms for muon momentum estimation in the CMS Trigger System The Compact Muon Solenoid (CMS) is a general-purpose detector at the L

anuragB 2 Oct 06, 2021
A robust pointcloud registration pipeline based on correlation.

PHASER: A Robust and Correspondence-Free Global Pointcloud Registration Ubuntu 18.04+ROS Melodic: Overview Pointcloud registration using correspondenc

ETHZ ASL 101 Dec 01, 2022
Pyeventbus: a publish/subscribe event bus

pyeventbus pyeventbus is a publish/subscribe event bus for Python 2.7. simplifies the communication between python classes decouples event senders and

15 Apr 21, 2022
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Python library with Neural Networks for Image Segmentation based on Keras and TensorFlow. The main features of this library are: High level API (just

Pavel Yakubovskiy 4.2k Jan 09, 2023
face2comics by Sxela (Alex Spirin) - face2comics datasets

This is a paired face to comics dataset, which can be used to train pix2pix or similar networks.

Alex 164 Nov 13, 2022
Python calculations for the position of the sun and moon.

Astral This is 'astral' a Python module which calculates Times for various positions of the sun: dawn, sunrise, solar noon, sunset, dusk, solar elevat

Simon Kennedy 169 Dec 20, 2022
Agile SVG maker for python

Agile SVG Maker Need to draw hundreds of frames for a GIF? Need to change the style of all pictures in a PPT? Need to draw similar images with differe

SemiWaker 4 Sep 25, 2022
Neighborhood Reconstructing Autoencoders

Neighborhood Reconstructing Autoencoders The official repository for Neighborhood Reconstructing Autoencoders (Lee, Kwon, and Park, NeurIPS 2021). T

Yonghyeon Lee 24 Dec 14, 2022
GUI for a Vocal Remover that uses Deep Neural Networks.

GUI for a Vocal Remover that uses Deep Neural Networks.

4.4k Jan 07, 2023
LETR: Line Segment Detection Using Transformers without Edges

LETR: Line Segment Detection Using Transformers without Edges Introduction This repository contains the official code and pretrained models for Line S

mlpc-ucsd 157 Jan 06, 2023
Measures input lag without dedicated hardware, performing motion detection on recorded or live video

What is InputLagTimer? This tool can measure input lag by analyzing a video where both the game controller and the game screen can be seen on a webcam

Bruno Gonzalez 4 Aug 18, 2022
MohammadReza Sharifi 27 Dec 13, 2022
This is the official PyTorch implementation of our paper: "Artistic Style Transfer with Internal-external Learning and Contrastive Learning".

Artistic Style Transfer with Internal-external Learning and Contrastive Learning This is the official PyTorch implementation of our paper: "Artistic S

51 Dec 20, 2022
A deep learning CNN model to identify and classify and check if a person is wearing a mask or not.

Face Mask Detection The Model is designed to check if any human is wearing a mask or not. Dataset Description The Dataset contains a total of 11,792 i

1 Mar 01, 2022
TensorFlow (Python) implementation of DeepTCN model for multivariate time series forecasting.

DeepTCN TensorFlow TensorFlow (Python) implementation of multivariate time series forecasting model introduced in Chen, Y., Kang, Y., Chen, Y., & Wang

Flavia Giammarino 21 Dec 19, 2022
Supplementary code for the AISTATS 2021 paper "Matern Gaussian Processes on Graphs".

Matern Gaussian Processes on Graphs This repo provides an extension for gpflow with Matérn kernels, inducing variables and trainable models implemente

41 Dec 17, 2022
Code corresponding to The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents This is the code corresponding to The Introspective

0 Jan 10, 2022
Differentiable Abundance Matching With Python

shamnet Differentiable Stellar Population Synthesis Installation You can install shamnet with pip. Installation dependencies are numpy, jax, corrfunc,

5 Dec 17, 2021
AAAI 2022 paper - Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction

AT-BMC Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction (AAAI 2022) Paper Prerequisites Install pac

16 Nov 26, 2022