AI models
TA-CNN
Training compute
1.1×10¹⁶ FLOP
Parameters
706K
Published
Nov 29, 2014
TA-CNN is an AI model developed by Chinese University of Hong Kong (CUHK) (Hong Kong), first published in November 2014. It works in the vision domain, on tasks such as object detection.
Training it took an estimated 1.1×10¹⁶ FLOP of compute (estimation method: hardware). The model has 706,048 parameters. It was trained on roughly 45K datapoints.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Chinese University of Hong Kong (CUHK)
- Country of organization
- Hong Kong
- Domain
- Vision
- Task
- Object detection
- Training compute
- 1.1×10¹⁶ FLOP
- Compute estimation method
- Hardware
- Parameters
- 706,048
- Dataset size
- 45K
- Chips used
- 1
- Training time
- 3 h
- Model accessibility
- Unreleased
- Open weights
- No
- Epoch confidence
- Likely
More from Chinese University of Hong Kong (CUHK)
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