DNN EM segmentation

Closed weights IDSIA,SUPSI 218.9K parameters December 2012

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
3 December 2012
Authors
D. Ciresan, A. Giusti, L. Gambardella, J. Schmidhuber

What it does

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

Domain
Vision
Task
Image segmentation
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
218.9K

Table 1 shows architecture 1st layer CNN: 48*4*4=768 2nd layer CNN: 48*48*5*5=57600 3rd layer CNN: 48*48*4*4=36864 4th layer CNN: 48*48*4*4=36864 1st layer FC: 48*3*3*200=86400 2nd layer FC: 200*2=400 Total parameters: 768+57600+36864+36864+86400+400=218896

Training data
3,000,000 tokens

[images] "This amounts to 3 million training examples in total, in which both classes are equally represented."

Epochs
30

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
4.8 × 10¹⁷ FLOP

"This amounts to 3 million training examples in total, in which both classes are equally represented. [...] We take advantage of this property, and synthetically augment the training set at the beginning of each epoch by randomly mirroring each training instance, and/or rotating it by ±90◦" Assuming 3 x training examples per epoch due to data augmentation Counting estimate: 1st layer CNN: 2*92*92*48*4*4=13000704 2nd layer CNN: 2*42*42*48*48*5*5=203212800 3rd layer CNN: 2*18*18*48*48*4*4=2388787…

How it was established
Operation counting,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 580
Chips used
4
Wall-clock time
17 hours

Training time for one epoch varies from approximately 170 minutes for N1 (w = 65) to 340 minutes for N4 (w = 95). All nets are trained for 30 epochs, which leads to a total training time of several days.

Power draw
2.1 kW
Compute cost
$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.

Frontier model
Yes
Why it is tracked
Historical significance,Highly cited
Record confidence
Confident

Sources

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

Reference
Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images
Last updated
28 November 2025

What the numbers mean

About this model

DNN EM segmentation was published by IDSIA,SUPSI, in Switzerland, in December 2012. academia,Academia is the category the publisher falls under.

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

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

Training it took roughly 4.8 × 10¹⁷ FLOP of computation, on NVIDIA GeForce GTX 580 — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 3,000,000 tokens.

The reason it appears in this catalogue at all is historical significance,Highly cited.

Answers

DNN EM segmentation — common questions

01

What is DNN EM segmentation used for?

DNN EM segmentation works in Vision, and is recorded as handling image segmentation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

How much compute was used to train DNN EM segmentation?

Around 4.8 × 10¹⁷ FLOP, on 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.

03

What GPU do I need to run DNN EM segmentation?

None. DNN EM segmentation 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 DNN EM segmentation open source?

No. DNN EM segmentation has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does DNN EM segmentation have?

DNN EM segmentation has 218.9K parameters. Table 1 shows architecture 1st layer CNN: 48*4*4=768 2nd layer CNN: 48*48*5*5=57600 3rd layer CNN: 48*48*4*4=36864 4th layer CNN: 48*48*4*4=36864 1st layer FC: 48*3*3*200=86400 2nd layer FC: 200*2=400 Total parameters: 768+57600+36864+36864+86400+400=218896. 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 DNN EM segmentation?

DNN EM segmentation was published by IDSIA,SUPSI, based in Switzerland, categorised as academia,Academia.

07

When was DNN EM segmentation released?

DNN EM segmentation was published in December 2012. 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 28 November 2025

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.