AI models
PyramidNet
Training compute
2.3×10¹⁵ FLOP
Parameters
26M
Published
Sep 6, 2017
PyramidNet is an AI model developed by Korea Advanced Institute of Science and Technology (KAIST) (South Korea), first published in September 2017. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 2.3×10¹⁵ FLOP of compute (estimation method: operation counting). The model has 26,000,000 parameters. It was trained on roughly 1.3M datapoints.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 750 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Korea Advanced Institute of Science and Technology (KAIST)
- Country of organization
- South Korea
- Domain
- Vision
- Task
- Image classification
- Training compute
- 2.3×10¹⁵ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 26,000,000
- Dataset size
- 1.3M
- Numerical format
- FP32
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 750
- Epoch confidence
- Likely
More from Korea Advanced Institute of Science and Technology (KAIST)
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