Self-Attention and Convolutional Layers

Closed weights Ecole Polytechnique F´ed´erale de Lausanne (EPFL) 29.5M parameters November 2019

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Ecole Polytechnique F´ed´erale de Lausanne (EPFL)
Organisation type
Academia
Country
Switzerland
Published
8 November 2019
Authors
Jean-Baptiste Cordonnier, Andreas Loukas & Martin Jaggi

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image classification

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
29.5M

from Table 1

Training data
tokens

size of CIFAR-10

Epochs
300

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
6.8 × 10¹⁷ FLOP

(15e9) * (300) * (50000) * 3 = 6.75e+17 (inference compute) * (epochs) * (dataset size) * (constant to account for backpropagation) epochs from appendix B table 2 inference compute from table 1

How it was established
Operation counting

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

Apache 2.0 for train/eval code: https://github.com/epfml/attention-cnn data is CIFAR which doesn't have a clear license

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident
Citations
630

Sources

Where this record came from and when it was last checked.

Reference
On the Relationship between Self-Attention and Convolutional Layers
Last updated
25 May 2026

What the numbers mean

What this model is

Self-Attention and Convolutional Layers was published by Ecole Polytechnique F´ed´erale de Lausanne (EPFL), in the country recorded as Switzerland, during November 2019. It comes out of an organisation categorised as academia.

It works in the domain of Vision, and is recorded as performing the task of image classification.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Producing it required arithmetic totalling around 6.8 × 10¹⁷ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

Self-Attention and Convolutional Layers — common questions

01

Self-Attention and Convolutional Layers— who created it?

It was published by Ecole Polytechnique F´ed´erale de Lausanne (EPFL), based in Switzerland, an organisation categorised as academia.

02

Self-Attention and Convolutional Layers— when was it released?

It was published in November 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

Self-Attention and Convolutional Layers— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

Self-Attention and Convolutional Layers— how much compute was used to train it?

Training consumed around 6.8 × 10¹⁷ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

05

Self-Attention and Convolutional Layers— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

06

Self-Attention and Convolutional Layers— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

07

Self-Attention and Convolutional Layers— how many parameters does it have?

It has a parameter count of 29.5M. from Table 1. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.