CapsNet (MNIST)
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
- Google Brain
- Organisation type
- Industry
- Country
- United States of America
- Published
- 26 October 2017
- Authors
- S Sabour, N Frosst, GE Hinton
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Character recognition (OCR)
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
- 8.2M
- Training data
- 60,000 tokens
"In terms of number of parameters the baseline has 35.4M while CapsNet has 8.2M parameters and 6.8M parameters without the reconstruction subnetwork"
Section 5: The dataset has 60K and 10K images for training and testing respectively.
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 5,094
Sources
Where this record came from and when it was last checked.
- Reference
- Dynamic Routing Between Capsules
- Last updated
- 25 May 2026
What the numbers mean
About this model
CapsNet (MNIST) was published by Google Brain, in United States of America, in October 2017. industry is the category the publisher falls under.
It works in Vision, and is recorded as doing character recognition (OCR).
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
It was trained on about 60,000 tokens of text.
Answers
CapsNet (MNIST) — common questions
Is CapsNet (MNIST) open source?
The licensing for CapsNet (MNIST) 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 CapsNet (MNIST) have?
CapsNet (MNIST) has 8.2M parameters. "In terms of number of parameters the baseline has 35.4M while CapsNet has 8.2M parameters and 6.8M parameters without the reconstruction subnetwork". 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 CapsNet (MNIST)?
CapsNet (MNIST) was published by Google Brain, based in United States of America, categorised as industry.
When was CapsNet (MNIST) released?
CapsNet (MNIST) was published in October 2017. 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 CapsNet (MNIST) used for?
CapsNet (MNIST) works in Vision, and is recorded as handling character recognition (OCR). 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.
What GPU do I need to run CapsNet (MNIST)?
None. CapsNet (MNIST) 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.