SexNet compression
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.
- Published
- 1 October 1990
- Authors
- B. Golomb, D. T. Lawrence, T. Sejnowski
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image representation
- 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
- 72.9K
- Training data
- 81,000 tokens
- Epochs
- 2,000
900*40*2+40+900=72940 “Images sampled at 30x30 were compressed using a 900x40x900 fully connected back-propagation network”
“The compression network trained for 2000 runs on each of 90 faces”
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
- 7.9 × 10¹⁰ FLOP
- How it was established
- Operation counting
2*72940*3*90*2000=78775200000 “The compression network trained for 2000 runs on each of 90 faces”
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
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- SEXNET: A Neural Network Identifies Sex From Human Faces
- Last updated
- 28 November 2025
What the numbers mean
About this model
SexNet compression was published by its authors, in October 1990.
It works in Vision, and is recorded as doing image representation.
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 around 7.9 × 10¹⁰ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
It was trained on about 81,000 tokens of text.
Its inclusion criterion is historical significance.
Answers
SexNet compression — common questions
Is SexNet compression open source?
The licensing for SexNet compression was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does SexNet compression have?
SexNet compression has 72.9K parameters. 900*40*2+40+900=72940 “Images sampled at 30x30 were compressed using a 900x40x900 fully connected back-propagation network”. 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.
When was SexNet compression released?
SexNet compression was published in October 1990. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is SexNet compression used for?
SexNet compression works in Vision, and is recorded as handling image representation. 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.
How much compute was used to train SexNet compression?
Around 7.9 × 10¹⁰ 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.
What GPU do I need to run SexNet compression?
None. SexNet compression 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.
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.