AI models
DCNN
Training compute
4.8×10¹⁷ FLOP
Parameters
5M
Published
Aug 7, 2015
DCNN is an AI model developed by University of Maryland and Rutgers University (United States), first published in August 2015. It works in the vision domain, on tasks such as face verification.
Training it took an estimated 4.8×10¹⁷ FLOP of compute (estimation method: operation counting,hardware). The model has 5,006,000 parameters. It was trained on roughly 490.4K datapoints. Training ran on 1 NVIDIA Tesla K40c for about 216 hours.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Maryland, Rutgers University
- Country of organization
- United States
- Domain
- Vision
- Task
- Face verification
- Training compute
- 4.8×10¹⁷ FLOP
- Compute estimation method
- Operation counting, Hardware
- Parameters
- 5,006,000
- Dataset size
- 490.4K
- Training hardware
- NVIDIA Tesla K40c
- Chips used
- 1
- Training time
- 216 h
- Training power draw
- 286 W
- Model accessibility
- Unreleased
- Open weights
- No
- 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