Perceiver IO (optical flow)

Parameters

27.9M

Published

Feb 8, 2020

Perceiver IO (optical flow) is an AI model developed by DeepMind (United Kingdom), first published in February 2020. It works in the multimodal, language and vision domain, on tasks such as language modeling/generation and image captioning.

Epoch AI has no training-compute estimate for this model. The model has 27,900,000 parameters. It was trained on roughly 146B datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 816 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: DeepMind
Country of organization: United Kingdom
Domain: Multimodal, Language, Vision
Task: Language modeling/generation, Image captioning
Parameters: 27,900,000
Dataset size: 146B
Model accessibility: Unreleased
Open weights: No
Citations: 816
Epoch confidence: Confident