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

Anomaly Transformer Pytorch

Anomaly Transformer Pytorch is an open-source PyTorch implementation of the Anomaly Transformer method, which applies association discrepancy to time-series anomaly detection. The repository documents configuring custom datasets and training the model.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Anomaly Transformer 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 you want to explore or train the Anomaly Transformer approach on a custom time-series dataset and are prepared to work with a repository described as a work in progress.

Who it is for

  • Developers adapting an anomaly-detection model to custom time-series data.
  • Researchers or practitioners prototyping time-series anomaly detection with PyTorch.

Documented uses

  • Configure a custom time-series dataset for the implementation.
  • Set model hyperparameters through the provided Hydra configuration files.
  • Start model training with the documented training script.
Before you choose

Requirements & limits

The implementation is publicly available on GitHub and is identified as MIT licensed.

  • The README lists Python 3.8.11 and dependency installation through requirements.txt.
  • Custom data properties must be reflected in conf/data/default.yaml.
  • The repository is marked as a work in progress.

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

Configure a custom dataset and start model training

Prepare a custom time-series dataset for the repository’s documented training command.

Before you start

  • Python 3.8.11 is the version listed by the project.
  • A virtual environment and the repository’s requirements.txt dependencies.
  • A custom time-series dataset.

Steps

  1. Create and activate a virtual environment.

  2. Install dependencies from requirements.txt.

  3. Place the dataset in the data/ directory and edit conf/data/default.yaml to describe its properties.

  4. Set other hyperparameters in the Hydra configuration files, then run python train.py.

Expected outcome

The configured training script is started for the custom dataset.

Guide limitations

  • The repository describes itself as a work in progress.
  • The documented instructions do not specify evaluation or deployment steps.
Documentation 1 ↗
Evidence and transparency

Sources & review

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