Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks

Related tags

Deep LearningCDIL-CNN
Overview

Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks

arXiv preprint: https://arxiv.org/abs/2201.02143.

Architecture

CDIL-CNN is a novel convolutional model for sequence classification. We use symmetric dilated convolutions, a circular mixing protocol, and an average ensemble learning.

Symmetric Dilated Convolutions

Circular Mixing

CDIL-CNN

Experiments

Synthetic Task

To reproduce the synthetic data experiment results, you should:

  1. Run syn_data_generation.py;
  2. Run syn_main.py for one experiment or run syn_all.sh for all experiments.

The generator will create 6 files for each sequence length and store them in the syn_datasets folder in the following format: adding2000_{length}_train.pt adding2000_{length}_train_target.pt adding2000_{length}_test.pt adding2000_{length}_test_target.pt adding2000_{length}_val.pt adding2000_{length}_val_target.pt

By default, it iterates over 8 sequence lengths: [2**7, 2**8, 2**9, 2**10, 2**11, 2**12, 2**13, 2**14].

You can run different models for different lengths. The syn_log folder will save all results.

We provide our used configurations in syn_config.py.

Long Range Arena

Long Range Arena (LRA) is a public benchmark suite. The datasets and the download link can be found in the official GitHub repository.

To reproduce the LRA experiment results, you should:

  1. Download lra_release.gz (~7.7 GB), extract it, move the folder ./lra_release/lra_release into our create_datasets folder, and run all_create_datasets.sh.
  2. Run lra_main.py for one experiment or run lra_all.sh for all experiments.

The dataset creators will create 3 files for each task and store them in the lra_datasets folder in the following format: {task}.train.pickle {task}.test.pickle {task}.dev.pickle

You can run different models on different tasks. The lra_log folder will save all results.

We provide our used configurations in lra_config.py.

Time Series

The UEA & UCR Repository consists of various time series classification datasets. We use three audio datasets: FruitFlies, RightWhaleCalls, and MosquitoSound.

To reproduce the time series results, you should:

  1. Download the datasets, extract them, move the extracted folders into our time_datasets folder, and run time_arff_generation.py.
  2. Run time_main.py for one experiment or run time_all.sh for all experiments.

The generator will create 2 files for each dataset and store them in the time_datasets folder in the following format: {dataset}_train.csv {dataset}_test.csv

You can run different models on different datasets. The time_log folder will save all results.

We provide our used configurations in time_main.py.

Minimal fastai code needed for working with pytorch

fastai_minima A mimal version of fastai with the barebones needed to work with Pytorch #all_slow Install pip install fastai_minima How to use This lib

Zachary Mueller 14 Oct 21, 2022
The Generic Manipulation Driver Package - Implements a ROS Interface over the robotics toolbox for Python

Armer Driver Armer aims to provide an interface layer between the hardware drivers of a robotic arm giving the user control in several ways: Joint vel

QUT Centre for Robotics (QCR) 13 Nov 26, 2022
Demo for the paper "Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation"

Streaming speaker diarization Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation by Juan Manuel Coria, Hervé

Juanma Coria 187 Jan 06, 2023
code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning Overview This code is for paper: Not All Unlabeled Data are Equa

Jason Ren 22 Nov 23, 2022
Parallel and High-Fidelity Text-to-Lip Generation; AAAI 2022 ; Official code

Parallel and High-Fidelity Text-to-Lip Generation This repository is the official PyTorch implementation of our AAAI-2022 paper, in which we propose P

Zhying 77 Dec 21, 2022
Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation. Generally, MAS methods register multiple atlases, i.e., medical images with corresponding labels, to a target i

NanYoMy 13 Oct 09, 2022
A high-performance distributed deep learning system targeting large-scale and automated distributed training.

HETU Documentation | Examples Hetu is a high-performance distributed deep learning system targeting trillions of parameters DL model training, develop

DAIR Lab 150 Dec 21, 2022
An implementation of Geoffrey Hinton's paper "How to represent part-whole hierarchies in a neural network" in Pytorch.

GLOM An implementation of Geoffrey Hinton's paper "How to represent part-whole hierarchies in a neural network" for MNIST Dataset. To understand this

50 Oct 19, 2022
python 93% acc. CNN Dogs Vs Cats ( Pytorch )

English | 简体中文(测试中...敬请期待) Cnn-Classification-Dog-Vs-Cat 猫狗辨别 (pytorch版本) CNN Resnet18 的猫狗分类器,基于ResNet及其变体网路系列,对于一般的图像识别任务表现优异,模型精准度高达93%(小型样本)。 项目制作于

apple ye 1 May 22, 2022
Official source code to CVPR'20 paper, "When2com: Multi-Agent Perception via Communication Graph Grouping"

When2com: Multi-Agent Perception via Communication Graph Grouping This is the PyTorch implementation of our paper: When2com: Multi-Agent Perception vi

34 Nov 09, 2022
NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

5 Nov 03, 2022
Data visualization app for H&M competition in kaggle

handm_data_visualize_app Data visualization app by streamlit for H&M competition in kaggle. competition page: https://www.kaggle.com/competitions/h-an

Kyohei Uto 12 Apr 30, 2022
This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

DropEdge: Towards Deep Graph Convolutional Networks on Node Classification This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Con

401 Dec 16, 2022
Easy to use and customizable SOTA Semantic Segmentation models with abundant datasets in PyTorch

Semantic Segmentation Easy to use and customizable SOTA Semantic Segmentation models with abundant datasets in PyTorch Features Applicable to followin

sithu3 530 Jan 05, 2023
Mmdet benchmark with python

mmdet_benchmark 本项目是为了研究 mmdet 推断性能瓶颈,并且对其进行优化。 配置与环境 机器配置 CPU:Intel(R) Core(TM) i9-10900K CPU @ 3.70GHz GPU:NVIDIA GeForce RTX 3080 10GB 内存:64G 硬盘:1T

杨培文 (Yang Peiwen) 24 May 21, 2022
GNPy: Optical Route Planning and DWDM Network Optimization

GNPy is an open-source, community-developed library for building route planning and optimization tools in real-world mesh optical networks

Telecom Infra Project 140 Dec 19, 2022
🎃 Core identification module of AI powerful point reading system platform.

ppReader-Kernel Intro Core identification module of AI powerful point reading system platform. Usage 硬件: Windows10、GPU:nvdia GTX 1060 、普通RBG相机 软件: con

CrashKing 1 Jan 11, 2022
AI创造营 :Metaverse启动机之重构现世,结合PaddlePaddle 和 Wechaty 创造自己的聊天机器人

paddle-wechaty-Zodiac AI创造营 :Metaverse启动机之重构现世,结合PaddlePaddle 和 Wechaty 创造自己的聊天机器人 12星座若穿越科幻剧,会拥有什么超能力呢?快来迎接你的专属超能力吧! 现在很多年轻人都喜欢看科幻剧,像是复仇者系列,里面有很多英雄、超

105 Dec 22, 2022
We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction

We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction. This repository aims to give easy access to state-of-the-art pre-train

GMUM 90 Jan 08, 2023