AI models
HR-ResNet101
Training compute
7.1×10¹⁸ FLOP
Parameters
44.5M
Published
Dec 13, 2016
HR-ResNet101 is an AI model developed by Carnegie Mellon University (CMU) (United States), first published in December 2016. It works in the vision domain, on tasks such as face detection.
Training it took an estimated 7.1×10¹⁸ FLOP of compute (estimation method: operation counting). The model has 44,500,000 parameters. It was trained on roughly 8.2M datapoints.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of ResNet-101 (ImageNet). Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Carnegie Mellon University (CMU)
- Country of organization
- United States
- Domain
- Vision
- Task
- Face detection
- Training compute
- 7.1×10¹⁸ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 44,500,000
- Dataset size
- 8.2M
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- ResNet-101 (ImageNet)
- Epoch confidence
- Confident
More from Carnegie Mellon University (CMU)
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