Perceiver IO (optical flow)
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
- DeepMind
- Organisation type
- Industry
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 8 February 2020
- Authors
- Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, João Carreira
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Multimodal, Language, Vision
- Task
- Language modeling/generation, Image captioning
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
- 27.9M
- Training data
- 146,022,400,000 tokens
- Epochs
- 480
Optical flow model (SOTA) was 27.9M params. There are other, larger models described in this paper, e.g. for language. "For the pixel- and patch-based models, total computational complexity for a forward pass on a 368 × 496 image is roughly 987 billion FLOPs, and there are roughly 27.9 million parameters."
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
- SOTA improvement
- Record confidence
- Confident
- Citations
- 816
"Perceiver IO... achieves state-of-the-art performance on Sintel optical flow estimation"
Sources
Where this record came from and when it was last checked.
- Reference
- Perceiver IO: A General Architecture for Structured Inputs & Outputs
- Last updated
- 25 May 2026
What the numbers mean
About this model
Perceiver IO (optical flow) was published by DeepMind, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during February 2020. The publishing organisation is categorised as industry.
It works in the domain of Multimodal, Language, Vision, and is recorded as performing the task of language modeling/generation, Image captioning.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
The training set ran to roughly 146,022,400,000 tokens of text.
The reason it appears in this catalogue at all: sOTA improvement.
Answers
Perceiver IO (optical flow) — common questions
Perceiver IO (optical flow)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Perceiver IO (optical flow)— how many parameters does it have?
It has a parameter count of 27.9M. Optical flow model (SOTA) was 27.9M params. There are other, larger models described in this paper, e.g. for language. "For the pixel- and patch-based models, total computational complexity for a forward pass on a 368 × 496 image is roughly 987 billion FLOPs, and there are roughly 27.9 million parameters.". 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.
Perceiver IO (optical flow)— who created it?
It was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.
Perceiver IO (optical flow)— when was it released?
It was published in February 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Perceiver IO (optical flow)— what is it used for?
It works in the domain of Multimodal, Language, Vision, and is recorded as handling the task of language modeling/generation, Image captioning. These are the areas it was designed around; they describe intent rather than a hard boundary.
Perceiver IO (optical flow)— what GPU do I need to run it?
None. This 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.