AI models
EnhanceNet
Training compute
1.3×10¹⁷ FLOP
Parameters
814.5K
Published
Dec 23, 2016
EnhanceNet is an AI model developed by Max Planck Institute for Intelligent Systems (Germany), first published in December 2016. It works in the vision domain, on tasks such as image super-resolution.
Training it took an estimated 1.3×10¹⁷ FLOP of compute (estimation method: hardware). The model has 814,464 parameters. It was trained on roughly 9.8B datapoints. Training ran on 1 NVIDIA Tesla K40c for about 24 hours.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Max Planck Institute for Intelligent Systems
- Country of organization
- Germany
- Domain
- Vision
- Task
- Image super-resolution
- Training compute
- 1.3×10¹⁷ FLOP
- Compute estimation method
- Hardware
- Parameters
- 814,464
- Dataset size
- 9.8B
- Training hardware
- NVIDIA Tesla K40c
- Chips used
- 1
- Training time
- 24 h
- Training power draw
- 282 W
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Confident
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