Dropout (ImageNet)

Training compute

2.7×10¹⁷ FLOP

Published

Jun 3, 2012

Dropout (ImageNet) is an AI model developed by University of Toronto (Canada), first published in June 2012. It works in the vision domain, on tasks such as image classification. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 2.7×10¹⁷ FLOP of compute (estimation method: hardware). It was trained on roughly 2.6M datapoints. Training ran on NVIDIA GeForce GTX 580 for about 96 hours. The compute alone is estimated at $8 in 2023 dollars.

Access: Unreleased. Its weights are not openly released. The reference paper has 7,999 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of Toronto
Country of organization: Canada
Domain: Vision
Task: Image classification
Training compute: 2.7×10¹⁷ FLOP
Compute estimation method: Hardware
Dataset size: 2.6M
Training hardware: NVIDIA GeForce GTX 580
Training time: 96 h
Training cost (2023 USD): $8
Numerical format: FP32
Model accessibility: Unreleased
Open weights: No
Citations: 7,999
Epoch confidence: Confident