AI models
Self-Attention and Convolutional Layers
Training compute
6.8×10¹⁷ FLOP
Parameters
29.5M
Published
Nov 8, 2019
Self-Attention and Convolutional Layers is an AI model developed by Ecole Polytechnique Federale de Lausanne (EPFL) (Switzerland), first published in November 2019. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 6.8×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 29,500,000 parameters.
Access: Unreleased. Its weights are not openly released. The reference paper has 630 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Ecole Polytechnique Federale de Lausanne (EPFL)
- Country of organization
- Switzerland
- Domain
- Vision
- Task
- Image classification
- Training compute
- 6.8×10¹⁷ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 29,500,000
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 630
- Epoch confidence
- Confident
More from Ecole Polytechnique Federale de Lausanne (EPFL)
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