High Performance CNN (NORB)

Closed weights IDSIA,SUPSI 4.9M parameters July 2011

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
IDSIA,SUPSI
Organisation type
Academia,Academia
Country
Switzerland
Published
16 July 2011
Authors
Dan C. Ciresan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber

What it does

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

Domain
Vision
Task
Image classification
Approach
Supervised

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
4.9M

L1: 6*300*6*6=64800 L3: 500*600*4*4=4800000 L5: (108/4)*500=13500 Total: 64800+4800000+13500=4878300

Training data
50,000 tokens
Epochs
7

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
2.6 × 10¹⁶ FLOP

7 epochs, 35 min per epoch 2 GTX 480 + 2 GTX 580 580 FLOP: 1580000000000 480 FLOP: 1345000000000 FLOP: 7*35*60*(2*1580000000000+2*1345000000000)*0.3=25798500000000000=2.6e16

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA GeForce GTX 480,NVIDIA GeForce GTX 580
Chips used
4
Wall-clock time
4 hours

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
Unreleased

How it is classified

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

Why it is tracked
Historical significance,SOTA improvement
Record confidence
Likely

Sources

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

Reference
Flexible, High Performance Convolutional Neural Networks for Image Classification
Last updated
11 February 2026

What the numbers mean

Where it came from

High Performance CNN (NORB) was published by IDSIA,SUPSI, in Switzerland, in July 2011. The organisation is categorised as academia,Academia.

It works in Vision, and is recorded as doing 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

Training it took roughly 2.6 × 10¹⁶ FLOP of computation, on NVIDIA GeForce GTX 480,NVIDIA GeForce GTX 580 — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 50,000 tokens.

Its inclusion criterion is historical significance,SOTA improvement.

Answers

High Performance CNN (NORB) — common questions

01

What GPU do I need to run High Performance CNN (NORB)?

None. High Performance CNN (NORB) 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.

02

Is High Performance CNN (NORB) open source?

No. High Performance CNN (NORB) has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does High Performance CNN (NORB) have?

High Performance CNN (NORB) has 4.9M parameters. L1: 6*300*6*6=64800 L3: 500*600*4*4=4800000 L5: (108/4)*500=13500 Total: 64800+4800000+13500=4878300. 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.

04

Who created High Performance CNN (NORB)?

High Performance CNN (NORB) was published by IDSIA,SUPSI, based in Switzerland, categorised as academia,Academia.

05

When was High Performance CNN (NORB) released?

High Performance CNN (NORB) was published in July 2011. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is High Performance CNN (NORB) used for?

High Performance CNN (NORB) works in Vision, and is recorded as handling image classification. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

07

How much compute was used to train High Performance CNN (NORB)?

Around 2.6 × 10¹⁶ FLOP, on NVIDIA GeForce GTX 480,NVIDIA GeForce GTX 580. 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.

Source

Original publication

Record last updated 11 February 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.