OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Etsformer Pytorch

Etsformer Pytorch is a Python implementation of ETSformer built with PyTorch. It provides an ETSFormer model for multi-step time-series forecasting and a ClassificationWrapper that produces class logits from sequential inputs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Etsformer Pytorch — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a Python and PyTorch project needs the documented ETSformer forecasting interface or its classification wrapper, and the surrounding data and application workflow will be handled separately.

Who it is for

  • Python developers adding time-series forecasting to an application or analysis pipeline.
  • Practitioners building classification workflows for sequential data.

Documented uses

  • Generate a specified number of forecast steps from multivariate time-series inputs.
  • Produce class logits from sequence data using the documented classification wrapper.
  • Use an ETSformer model component within a larger time-series workflow.
Before you choose

Requirements & limits

The repository is public and lists an MIT license.

  • Forecasting inputs are represented as batches with time features; the example returns the same feature dimension across the requested forecast horizon.
  • Classification uses a separate wrapper, with num_classes and pooling-related settings configured explicitly.
  • The documented installation command is pip install etsformer-pytorch.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the package and prepare a forecasting call

Install the Python package and set up the documented ETSformer input and forecast call.

Before you start

  • Python environment with pip
  • PyTorch, imported as torch

Steps

  1. Install the package with the command below.

    Documented command
    pip install etsformer-pytorch

  2. Import torch and ETSFormer from etsformer_pytorch.

  3. Construct ETSFormer with time_features and model settings such as model_dim, layers, heads, K and dropout.

  4. Pass a time-series tensor to the model with num_steps_forecast set to the desired forecast horizon.

Expected outcome

The README example returns a forecast tensor shaped as batch × forecast steps × time features.

Guide limitations

  • The example values are provided as a usage illustration, not as dataset-specific recommendations.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
lucidrains/ETSformer-pytorch · Official homepage title · retained in its source language
How we review sourcesSuggest a correction