Pooling CNN (Caltech 101)
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
- University of Bonn
- Organisation type
- Academia
- Country
- Germany
- Published
- 15 September 2010
- Authors
- Dominik Scherer, Andreas C. Müller, Sven Behnke
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
- 294.9K
- Training data
- 3,060 tokens
- Epochs
- 300
C1: 3*16*16*16=12288 C3: 16*128*6*6=73728 F5: 128*4*4*102=208896 Total: 12288+73728+208896=294912
30 * 102 = 3060
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
- 1.2 × 10¹⁵ FLOP
- How it was established
- Operation counting
Forward FLOP C1: 2*3*16*16*16*125*125=384000000 C3: 2*16*128*6*6*20*20=58982400 F5: 2*128*4*4*102=417792 Total: 384000000+58982400+417792=443400192 300 epochs 30*102=3060 training examples 443400192*3*3060*300=1221124128768000=1.2e15
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
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,Highly cited,SOTA improvement
- Record confidence
- Confident
"we achieve state-of-the-art error rates of 4.57% on the NORB normalized-uniform dataset and 5.6% on the NORB jittered-cluttered dataset."
Sources
Where this record came from and when it was last checked.
- Reference
- Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
- Last updated
- 11 February 2026
What the numbers mean
What this model is
Pooling CNN (Caltech 101) was published by University of Bonn, in Germany, in September 2010. academia is the category the publisher falls under.
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
Producing it required around 1.2 × 10¹⁵ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
The training set ran to roughly 3,060 tokens.
Its inclusion criterion is historical significance,Highly cited,SOTA improvement.
Answers
Pooling CNN (Caltech 101) — common questions
When was Pooling CNN (Caltech 101) released?
Pooling CNN (Caltech 101) was published in September 2010. 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 Pooling CNN (Caltech 101) used for?
Pooling CNN (Caltech 101) 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.
How much compute was used to train Pooling CNN (Caltech 101)?
Around 1.2 × 10¹⁵ 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 Pooling CNN (Caltech 101)?
None. Pooling CNN (Caltech 101) 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.
Is Pooling CNN (Caltech 101) open source?
No. Pooling CNN (Caltech 101) has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Pooling CNN (Caltech 101) have?
Pooling CNN (Caltech 101) has 294.9K parameters. C1: 3*16*16*16=12288 C3: 16*128*6*6=73728 F5: 128*4*4*102=208896 Total: 12288+73728+208896=294912. 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.
Who created Pooling CNN (Caltech 101)?
Pooling CNN (Caltech 101) was published by University of Bonn, based in Germany, categorised as academia.
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.