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

Morpheus 1

Morpheus 1 is a Python/PyTorch implementation of a multimodal transformer that accepts volumetric fMRI tensors and EEG embeddings and returns an output tensor.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Morpheus 1 — 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 inspect or adapt a Python model implementation for joint fMRI and EEG tensor input, rather than call a hosted inference service.

Who it is for

  • Researchers prototyping multimodal pipelines for fMRI and EEG tensors.
  • Python developers exploring transformer models that combine volumetric and time-series inputs.

Documented uses

  • Inspect a model implementation that accepts fMRI and EEG inputs together.
  • Prototype a research pipeline that passes volumetric and time-series tensors to a transformer.
  • Adjust model configuration parameters such as attention heads, depth, dropout and convolution settings.
Before you choose

Requirements & limits

The repository is public and states an MIT license. Its README provides `pip install morpheus-torch` as the installation command.

  • The documented example uses randomly generated inputs, not validated results on real brain data.
  • The repository flags its brain-scan and EEG tensor shapes for further checking against research papers.
  • The README documents model invocation but not a hosted inference API or a full data-preparation pipeline.

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 for model invocation

Install the named package and identify the documented input tensor shapes and model interface.

Before you start

  • Python environment with pip
  • PyTorch, imported as torch in the example

Steps

  1. Install the package with the command below.

    Documented command
    pip install morpheus-torch

  2. Import Morpheus from morpheus_torch.model.

  3. Prepare fMRI tensors in (batch_size, in_channels, D, H, W) form and EEG embeddings in [batch_size, channels, time_samples] form.

Expected outcome

The package installation command, model import path, and two documented input shapes are identified for subsequent development.

Guide limitations

  • The README flags checking tensor shapes against relevant brain-scan, EEG and fMRI papers as a TODO.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
kyegomez/MORPHEUS-1 · Official homepage title · retained in its source language
How we review sourcesSuggest a correction