AI models
PNASNet-5
Training compute
6.6×10¹⁹ FLOP
Parameters
86.1M
Published
Dec 2, 2017
PNASNet-5 is an AI model developed by Johns Hopkins University, Google AI and Stanford University (United States), first published in December 2017. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 6.6×10¹⁹ FLOP of compute (estimation method: comparison with other models). The model has 86,100,000 parameters. It was trained on roughly 1.3M datapoints.
The reference paper has 2,140 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Johns Hopkins University, Google AI, Stanford University
- Country of organization
- United States
- Domain
- Vision
- Task
- Image classification
- Training compute
- 6.6×10¹⁹ FLOP
- Compute estimation method
- Comparison with other models
- Parameters
- 86,100,000
- Dataset size
- 1.3M
- Citations
- 2,140
- Epoch confidence
- Likely
More from Johns Hopkins University,Google AI,Stanford University
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models