Sequencer: Deep LSTM for Image Classification

Related tags

Audio sequencer
Overview

Sequencer: Deep LSTM for Image Classification

arXiv Support Ukraine

Created by

This repository contains implementation for Sequencer.

Abstract

In recent computer vision research, the advent of the Vision Transformer (ViT) has rapidly revolutionized various architectural design efforts: ViT achieved state-of-the-art image classification performance using self-attention found in natural language processing, and MLP-Mixer achieved competitive performance using simple multi-layer perceptrons. In contrast, several studies have also suggested that carefully redesigned convolutional neural networks (CNNs) can achieve advanced performance comparable to ViT without resorting to these new ideas. Against this background, there is growing interest in what inductive bias is suitable for computer vision. Here we propose Sequencer, a novel and competitive architecture alternative to ViT that provides a new perspective on these issues. Unlike ViTs, Sequencer models long-range dependencies using LSTMs rather than self-attention layers. We also propose a two-dimensional version of Sequencer module, where an LSTM is decomposed into vertical and horizontal LSTMs to enhance performance. Despite its simplicity, several experiments demonstrate that Sequencer performs impressively well: Sequencer2D-L, with 54M parameters, realizes 84.6% top-1 accuracy on only ImageNet-1K. Not only that, we show that it has good transferability and the robust resolution adaptability on double resolution-band.

Schematic diagrams

The overall architecture of Sequencer2D is similar to the typical hierarchical ViT and Visual MLP. It uses Sequencer2D blocks instead of Transformer blocks:

Sequencer

Sequencer2D block replaces the Transformer's self-attention layer with an LSTM-based layer like BiLSTM2D layer:

Sequencer2D

BiLSTM2D includes a vertical LSTM and a horizontal LSTM:

BiLSTM2D

Model Zoo

We provide our Sequencer models pretrained on ImageNet-1K:

name arch Params FLOPs [email protected] download
Sequencer2D-S sequencer2d_s 28M 8.4G 82.3 here
Sequencer2D-M sequencer2d_m 38M 11.1G 82.8 here
Sequencer2D-L sequencer2d_l 54M 16.6G 83.4 here

Usage

Requirements

  • torch>=1.10.0
  • torchvision
  • timm==0.5.4
  • Pillow
  • matplotlib
  • scipy
  • etc., see requirements.txt

Data preparation

Download and extract ImageNet images. The directory structure should be as follows.

│imagenet/
├──train/
│  ├── n01440764
│  │   ├── n01440764_10026.JPEG
│  │   ├── n01440764_10027.JPEG
│  │   ├── ......
│  ├── ......
├──val/
│  ├── n01440764
│  │   ├── ILSVRC2012_val_00000293.JPEG
│  │   ├── ILSVRC2012_val_00002138.JPEG
│  │   ├── ......
│  ├── ......

Traning

Command line for training Sequencer models on ImageNet from scratch.

./distributed_train.sh 8 /path/to/imagenet --model sequencer2d_s -b 256 -j 8 --opt adamw --epochs 300 --sched cosine --native-amp --img-size 224 --drop-path 0.1 --lr 2e-3 --weight-decay 0.05 --remode pixel --reprob 0.25 --aa rand-m9-mstd0.5-inc1 --smoothing 0.1 --mixup 0.8 --cutmix 1.0 --warmup-lr 1e-6 --warmup-epochs 20

Command line for fine-tuning a pre-trained model at higher resolution.

./distributed_train.sh 8 /path/to/imagenet --model sequencer2d_l --pretrained -b 64 -j 8 --opt adamw --epochs 30 --sched cosine --native-amp --input-size 3 392 392 --img-size 392 --crop-pct 1.0 --drop-path 0.4 --lr 5e-5 --weight-decay 1e-8 --remode pixel --reprob 0.25 --aa rand-m9-mstd0.5-inc1 --smoothing 0.1 --mixup 0.8 --cutmix 1.0 --warmup-epochs 0 --cooldown-epochs 0

Command line for fine-tuning a pre-trained model on a transfer learning dataset.

./distributed_train.sh 4 /path/to/cifar10 --model sequencer2d_s -b 128 -j 4 --num-classes 10 --dataset torch/cifar10 --pretrained --opt adamw --epochs 200 --sched cosine --native-amp --img-size 224 --clip-grad 1 --drop-path 0.1 --lr 0.0001 --weight-decay 1e-4 --remode pixel --aa rand-m9-mstd0.5-inc1 --smoothing 0.1 --mixup 0.8 --cutmix 1.0 --warmup-lr 1e-6 --warmup-epochs 5

Validation

To evaluate our Sequencer models, run:

python validate.py /path/to/imagenet --model sequencer2d_s -b 16 --input-size 3 224 224 --amp

Reference

You may want to cite:

@article{tatsunami2022sequencer,
  title={Sequencer: Deep LSTM for Image Classification},
  author={Tatsunami, Yuki and Taki, Masato},
  journal={arXiv preprint arXiv:2205.01972},
  year={2022}
}

Acknowledgment

This implementation is based on pytorch-image-models by Ross Wightman. We thank for his brilliant work.

We thank Graduate School of Artificial Intelligence and Science, Rikkyo University (Rikkyo AI) which supports us with computational resources, facilities, and others. logo-rikkyo-ai
AnyTech Co. Ltd. provided valuable comments on the early versions and encouragement. We thank them for their cooperation. In particular, We thank Atsushi Fukuda for organizing discussion opportunities. logo-anytech
Issues
Releases(weights)
Owner
Yuki Tatsunami
Yuki Tatsunami
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

A Python library for audio feature extraction, classification, segmentation and applications This doc contains general info. Click here for the comple

Theodoros Giannakopoulos 3.8k Feb 17, 2021
praudio provides audio preprocessing framework for Deep Learning audio applications

praudio provides objects and a script for performing complex preprocessing operations on entire audio datasets with one command.

Valerio Velardo 98 May 14, 2022
Deep learning transformer model that generates unique music sequences.

music-ai Deep learning transformer model that generates unique music sequences. Abstract In 2017, a new state-of-the-art was published for natural lan

xacer 8 Jun 14, 2022
Codes for "Efficient Long-Range Attention Network for Image Super-resolution"

ELAN Codes for "Efficient Long-Range Attention Network for Image Super-resolution", arxiv link. Dependencies & Installation Please refer to the follow

xindong zhang 75 Jun 26, 2022
A modular sequencer based on Pi Pico & EuroPi

PicoSequencer A modular sequencer based on Pi Pico & EuroPi by Zeno Van Moerkerke / Keurslager Kurt For now it is 'only' a trigger sequencer, but I si

null 3 Apr 9, 2022
Time-series-deep-learning - Developing Deep learning LSTM, BiLSTM models, and NeuralProphet for multi-step time-series forecasting of stock price.

Stock Price Prediction Using Deep Learning Univariate Time Series Predicting stock price using historical data of a company using Neural networks for

Abdultawwab Safarji 3 Jun 11, 2022
Text Classification Using LSTM

Text classification is the task of assigning a set of predefined categories to free text. Text classifiers can be used to organize, structure, and categorize pretty much anything. For example, new articles can be organized by topics, support tickets can be organized by urgency, chat conversations can be organized by language, brand mentions can be organized by sentiment, and so on.

KrishArul26 1 Feb 23, 2022
A Simple LSTM-Based Solution for "Heartbeat Signal Classification and Prediction" in Tianchi

LSTM-Time-Series-Prediction A Simple LSTM-Based Solution for "Heartbeat Signal Classification and Prediction" in Tianchi Contest. The Link of the Cont

KevinCHEN 1 Jun 13, 2022
Binary LSTM model for text classification

Text Classification The purpose of this repository is to create a neural network model of NLP with deep learning for binary classification of texts re

Nikita Elenberger 1 Mar 11, 2022
Text classification on IMDB dataset using Keras and Bi-LSTM network

Text classification on IMDB dataset using Keras and Bi-LSTM Text classification on IMDB dataset using Keras and Bi-LSTM network. Usage python3 main.py

Hamza Rashid 1 Jan 10, 2022
Simple-Image-Classification - Simple Image Classification Code (PyTorch)

Simple-Image-Classification Simple Image Classification Code (PyTorch) Yechan Kim This repository contains: Python3 / Pytorch code for multi-class ima

Yechan Kim 6 Jun 2, 2022
Image Classification - A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

null 0 Jan 23, 2022
A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

A tour through tensorflow with financial data I present several models ranging in complexity from simple regression to LSTM and policy networks. The s

null 192 Jun 2, 2022
Deep learning based hand gesture recognition using LSTM and MediaPipie.

Hand Gesture Recognition Deep learning based hand gesture recognition using LSTM and MediaPipie. Demo video using PingPong Robot Files Pretrained mode

Brad 19 Jun 14, 2022
Image Captioning using CNN ,LSTM and Attention

Image Captioning using CNN ,LSTM and Attention This is a deeplearning model which tries to summarize an image into a text . Installation Install this

ASUTOSH GHANTO 1 Dec 16, 2021
End-to-end image captioning with EfficientNet-b3 + LSTM with Attention

Image captioning End-to-end image captioning with EfficientNet-b3 + LSTM with Attention Model is seq2seq model. In the encoder pretrained EfficientNet

null 2 Feb 10, 2022
Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Deep Image Search - AI-Based Image Search Engine Deep Image Search is an AI-based image search engine that includes deep transfer learning features Ex

null 71 Jun 27, 2022
The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

Watermark-Robustness-Toolbox - Official PyTorch Implementation This repository contains the official PyTorch implementation of the following paper to

null 33 Jun 13, 2022
Automatic deep learning for image classification.

AutoDL AutoDL automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few line

wenqi 1 Nov 4, 2021
paper: Hyperspectral Remote Sensing Image Classification Using Deep Convolutional Capsule Network

DC-CapsNet This is a tensorflow and keras based implementation of DC-CapsNet for HSI in the Remote Sensing Letters R. Lei et al., "Hyperspectral Remot

LEI 6 May 5, 2022
Using LSTM write Tang poetry

本教程将通过一个示例对LSTM进行介绍。通过搭建训练LSTM网络,我们将训练一个模型来生成唐诗。本文将对该实现进行详尽的解释,并阐明此模型的工作方式和原因。并不需要过多专业知识,但是可能需要新手花一些时间来理解的模型训练的实际情况。为了节省时间,请尽量选择GPU进行训练。

null 56 May 25, 2022
Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

anaGo anaGo is a Python library for sequence labeling(NER, PoS Tagging,...), implemented in Keras. anaGo can solve sequence labeling tasks such as nam

Hiroki Nakayama 1.5k Jun 28, 2022
Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

anaGo anaGo is a Python library for sequence labeling(NER, PoS Tagging,...), implemented in Keras. anaGo can solve sequence labeling tasks such as nam

Hiroki Nakayama 1.4k Feb 17, 2021
Tensorflow-based CNN+LSTM trained with CTC-loss for OCR

Overview This collection demonstrates how to construct and train a deep, bidirectional stacked LSTM using CNN features as input with CTC loss to perfo

Jerod Weinman 485 Jun 18, 2022
CNN+LSTM+CTC based OCR implemented using tensorflow.

CNN_LSTM_CTC_Tensorflow CNN+LSTM+CTC based OCR(Optical Character Recognition) implemented using tensorflow. Note: there is No restriction on the numbe

Watson Yang 354 May 11, 2022
A small C++ implementation of LSTM networks, focused on OCR.

clstm CLSTM is an implementation of the LSTM recurrent neural network model in C++, using the Eigen library for numerical computations. Status and sco

Tom 791 Jun 23, 2022
OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network

Stock Price Prediction of Apple Inc. Using Recurrent Neural Network OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network Dataset:

Nouroz Rahman 366 Jun 14, 2022
Using multidimensional LSTM neural networks to create a forecast for Bitcoin price

Multidimensional LSTM BitCoin Time Series Using multidimensional LSTM neural networks to create a forecast for Bitcoin price. For notes around this co

Jakob Aungiers 315 Jun 19, 2022
Multi-layer convolutional LSTM with Pytorch

Convolution_LSTM_pytorch Thanks for your attention. I haven't got time to maintain this repo for a long time. I recommend this repo which provides an

Zijie Zhuang 721 Jun 23, 2022