Implementation of ETSformer, state of the art time-series Transformer, in Pytorch

Related tags

Deep Learningdeep-learningtime-seriestransformersartificial-intelligenceexponential-smoothing
Overview

ETSformer - Pytorch

Implementation of ETSformer, state of the art time-series Transformer, in Pytorch

Install

$ pip install etsformer-pytorch

Usage

import torch
from etsformer_pytorch import ETSFormer

model = ETSFormer(
    time_features = 4,
    model_dim = 512,                # in paper they use 512
    embed_kernel_size = 3,          # kernel size for 1d conv for input embedding
    layers = 2,                     # number of encoder and corresponding decoder layers
    heads = 8,                      # number of exponential smoothing attention heads
    K = 4,                          # num frequencies with highest amplitude to keep (attend to)
    dropout = 0.2                   # dropout (in paper they did 0.2)
)

timeseries = torch.randn(1, 1024, 4)

pred = model(timeseries, num_steps_forecast = 32) # (1, 32, 4) - (batch, num steps forecast, num time features)

For using ETSFormer for classification, using cross attention pooling on all latents and level output

import torch
from etsformer_pytorch import ETSFormer, ClassificationWrapper

etsformer = ETSFormer(
    time_features = 1,
    model_dim = 512,
    embed_kernel_size = 3,
    layers = 2,
    heads = 8,
    K = 4,
    dropout = 0.2
)

adapter = ClassificationWrapper(
    etsformer = etsformer,
    dim_head = 32,
    heads = 16,
    dropout = 0.2,
    level_kernel_size = 5,
    num_classes = 10
)

timeseries = torch.randn(1, 1024)

logits = adapter(timeseries) # (1, 10)

Citation

@misc{woo2022etsformer,
    title   = {ETSformer: Exponential Smoothing Transformers for Time-series Forecasting}, 
    author  = {Gerald Woo and Chenghao Liu and Doyen Sahoo and Akshat Kumar and Steven Hoi},
    year    = {2022},
    eprint  = {2202.01381},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG}
}
Comments
  • What are your thoughts on using latents for additional classification task

    What are your thoughts on using latents for additional classification task

    Hi! I was wondering if you have thought about aggregating seasonal and growth latents for additional tasks (for example classification)? What are the possible ways to bring latents into single feature vector in your opinion? The easiest one would be just get the mean along layers and time dimensions but that seams to be too naive. Another idea I had it to use Cross Attention mechanic with single time query key to aggregate latents:

    all_latents = torch.cat([latent_growths, latent_seasonals], dim=-1)
all_latents = rearrange(all_latents, 'b n l d -> (b l) n d')
# q = nn.Parameter(torch.randn(all_latents_dim))
q = repeat(q, 'd -> b 1 d', b = all_latents.shape[0])
agg_latent = cross_attention(query=q, context=all_latents)
agg_latent = rearrange(all_latents, '(b l) n d -> b (l n) d')
agg_latent = agg_latent.mean(dim=1) # may be we should have done it before cross attention?

    Would be great to hear your thoughts

    opened by inspirit 15
  • Pre LayerNorm might be required for k,v?

    Pre LayerNorm might be required for k,v?

    https://github.com/lucidrains/ETSformer-pytorch/blob/2561053007e919409b3255eb1d0852c68799d24f/etsformer_pytorch/etsformer_pytorch.py#L440

    In my early tests I see some instability in training results, I was wondering if it might be good idea to LayerNorm latents before constructing key and values?

    opened by inspirit 5
  • growth_term calculation error

    growth_term calculation error

    https://github.com/lucidrains/ETSformer-pytorch/blob/e1d8514b44d113ead523aa6307986833e68eecc5/etsformer_pytorch/etsformer_pytorch.py#L233-L235

    It looks like you are not using growth and growth_smoothing_weightsto calculate growth_term

    opened by inspirit 4
  • Backward gradient error

    Backward gradient error

    Hello,

    i was trying to run the provided class and see following error: Function ScatterBackward0 returned an invalid gradient at index 1 - got [64, 4, 128] but expected shape compatible with [64, 33, 128]

    model = ETSFormer(
            time_features = 9,
            model_dim = 128,
            embed_kernel_size = 3,
            layers = 2,
            heads = 4,
            K = 4,
            dropout = 0.2
        )

    input = torch.rand(64, 64, 9) x = model(input, num_steps_forecast = 16)

    opened by inspirit 3
  • Does ETS-Former allow adding features

    Does ETS-Former allow adding features

    @lucidrains Thanks for making the code of the model available!

    In your paper, you state that the model infers seasonal patterns itself, so that there is no need to add time features like week, month, etc.

    Still, to increase the applicability of your approach, does the current implementation allow to add any (time-invariant and time-varying) features, e.g., categorical or numeric?

    opened by StatMixedML 2
  • wrong order of arguments

    wrong order of arguments

    https://github.com/lucidrains/ETSformer-pytorch/blob/2e0d465576c15fc8d84c4673f93fdd71d45b799c/etsformer_pytorch/etsformer_pytorch.py#L327

    you pass latents on wrong order to Level module: according to forward method first should be growth and then seasonal

    opened by inspirit 1
  • Clarification regarding data pre-processing

    Clarification regarding data pre-processing

    Hello,

    I was trying to run the ETSformer for ETT dataset. The paper mentions that the dataset is split as 60/20/20 for train, validation and test. Could you give some insight as to how the dataset split is happening in the code.

    Thank you.

    opened by vageeshmaiya 2
Owner
Phil Wang
Working with Attention. It's all we need
Phil Wang
GitHub Repository
Inflated i3d network with inception backbone, weights transfered from tensorflow

I3D models transfered from Tensorflow to PyTorch This repo contains several scripts that allow to transfer the weights from the tensorflow implementat

Yana 479 Dec 08, 2022
Repository for "Exploring Sparsity in Image Super-Resolution for Efficient Inference", CVPR 2021

SMSR Reposity for "Exploring Sparsity in Image Super-Resolution for Efficient Inference" [arXiv] Highlights Locate and skip redundant computation in S

Longguang Wang 225 Dec 26, 2022
Supporting code for "Autoregressive neural-network wavefunctions for ab initio quantum chemistry".

naqs-for-quantum-chemistry This repository contains the codebase developed for the paper Autoregressive neural-network wavefunctions for ab initio qua

Tom Barrett 24 Dec 23, 2022
Improving Non-autoregressive Generation with Mixup Training

MIST Training MIST TRAIN_FILE=/your/path/to/train.json VALID_FILE=/your/path/to/valid.json OUTPUT_DIR=/your/path/to/save_checkpoints CACHE_DIR=/your/p

7 Nov 22, 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
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
Finding all things on-prem Microsoft for password spraying and enumeration.

msprobe About Installing Usage Examples Coming Soon Acknowledgements About Finding all things on-prem Microsoft for password spraying and enumeration.

205 Jan 09, 2023
StarGAN - Official PyTorch Implementation (CVPR 2018)

StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

Yunjey Choi 5.1k Dec 30, 2022
Atomistic Line Graph Neural Network

Table of Contents Introduction Installation Examples Pre-trained models Quick start using colab JARVIS-ALIGNN webapp Peformances on a few datasets Use

National Institute of Standards and Technology 91 Dec 30, 2022
My take on a practical implementation of Linformer for Pytorch.

Linformer Pytorch Implementation A practical implementation of the Linformer paper. This is attention with only linear complexity in n, allowing for v

Peter 349 Dec 25, 2022
Code for Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid

SPN: Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid Code for Fully Context-Aware Image Inpainting with a Learned Semantic Pyrami

12 Jun 27, 2022
FedGS: A Federated Group Synchronization Framework Implemented by LEAF-MX.

FedGS: Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoT Preparation For instructions on generating data, plea

Lizonghang 9 Dec 22, 2022
[ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving

NEAT: Neural Attention Fields for End-to-End Autonomous Driving Paper | Supplementary | Video | Poster | Blog This repository is for the ICCV 2021 pap

254 Jan 02, 2023
[NeurIPS 2021] Garment4D: Garment Reconstruction from Point Cloud Sequences

Garment4D [PDF] | [OpenReview] | [Project Page] Overview This is the codebase for our NeurIPS 2021 paper Garment4D: Garment Reconstruction from Point

Fangzhou Hong 112 Dec 23, 2022
Using NumPy to solve the equations of fluid mechanics together with Finite Differences, explicit time stepping and Chorin's Projection methods

Computational Fluid Dynamics in Python Using NumPy to solve the equations of fluid mechanics 🌊 🌊 🌊 together with Finite Differences, explicit time

Felix Köhler 4 Nov 12, 2022
Code Repository for Liquid Time-Constant Networks (LTCs)

Liquid time-constant Networks (LTCs) [Update] A Pytorch version is added in our sister repository: https://github.com/mlech26l/keras-ncp This is the o

Ramin Hasani 553 Dec 27, 2022
Array Camera Ptychography

Array Camera Ptychography This repository provides the code for the following papers: Schulz, Timothy J., David J. Brady, and Chengyu Wang. "Photon-li

Brady lab in Optical Sciences 1 Nov 15, 2021
《Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement》(ECCV 2020) GitHub: [fig9]

Unsupervised 3D Human Pose Representation [Paper] The implementation of our paper Unsupervised 3D Human Pose Representation with Viewpoint and Pose Di

42 Nov 24, 2022
The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting".

IGMTF The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting". Requirements The framework

Wentao Xu 24 Dec 05, 2022
Image Completion with Deep Learning in TensorFlow

Image Completion with Deep Learning in TensorFlow See my blog post for more details and usage instructions. This repository implements Raymond Yeh and

Brandon Amos 1.3k Dec 23, 2022