CNN committee (traffic sign)

Closed weights IDSIA 1.4M parameters October 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
Organisation type
Academia
Country
Switzerland
Published
3 October 2011
Authors
D. Ciresan, U. Meier, Jonathan Masci, J. 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
1.4M

Parameters L1: 3*3*3*100=2700 L3: 100*4*4*150=240000 L5: 150*3*3*250=337500 L7: 250*4*4*200=800000 L8: 200*43=8600 Total: 2700+240000+337500+800000+8600=1388800

Training data
53,280 tokens

[images] “The training set consists of 26640 images“ “we resize all images to 48 × 48 pixels”

Epochs
50

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
9.9 × 10¹⁴ FLOP

Training FLOP L1: 3*3*3*46*46*100=5713200 L3: 100*4*4*20*20*150=96000000 L5: 150*3*3*8*8*250=21600000 L7: 250*4*4*200=800000 L8: 200*43=8600 Total: 2*(5713200+96000000+21600000+800000+8600)=248243600 Training Compute: 248243600*3*26640*50=991981425600000=9.9e14

How it was established
Operation counting

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 580,NVIDIA GeForce GTX 480
Chips used
4

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

"We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. "

Record confidence
Likely

Sources

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

Reference
A committee of neural networks for traffic sign classification
Last updated
11 February 2026

What the numbers mean

Where it came from

CNN committee (traffic sign) was published by IDSIA, in Switzerland, in October 2011. It comes out of academia.

It works in Vision, and is recorded as doing image classification.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Training it took roughly 9.9 × 10¹⁴ FLOP of computation, on NVIDIA GeForce GTX 580,NVIDIA GeForce GTX 480 — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 53,280 tokens.

The reason it appears in this catalogue at all is historical significance,SOTA improvement.

Answers

CNN committee (traffic sign) — common questions

01

What is CNN committee (traffic sign) used for?

CNN committee (traffic sign) works in Vision, and is recorded as handling image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

How much compute was used to train CNN committee (traffic sign)?

Around 9.9 × 10¹⁴ FLOP, on NVIDIA GeForce GTX 580,NVIDIA GeForce GTX 480. 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.

03

What GPU do I need to run CNN committee (traffic sign)?

None. CNN committee (traffic sign) 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.

04

Is CNN committee (traffic sign) open source?

No. CNN committee (traffic sign) has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does CNN committee (traffic sign) have?

CNN committee (traffic sign) has 1.4M parameters. Parameters L1: 3*3*3*100=2700 L3: 100*4*4*150=240000 L5: 150*3*3*250=337500 L7: 250*4*4*200=800000 L8: 200*43=8600 Total: 2700+240000+337500+800000+8600=1388800. 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.

06

Who created CNN committee (traffic sign)?

CNN committee (traffic sign) was published by IDSIA, based in Switzerland, categorised as academia.

07

When was CNN committee (traffic sign) released?

CNN committee (traffic sign) was published in October 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.

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.