YOLOv3

Training compute

1.3×10¹⁹ FLOP

Parameters

56.9M

Published

Apr 8, 2018

YOLOv3 is an AI model developed by University of Washington (United States), first published in April 2018. It works in the vision domain, on tasks such as object detection.

Training it took an estimated 1.3×10¹⁹ FLOP of compute (estimation method: operation counting). The model has 56,933,216 parameters. It was trained on roughly 5.4M datapoints. Training ran on NVIDIA M40,NVIDIA GeForce GTX TITAN X.

Access: Unreleased. Its weights are not openly released. The reference paper has 25,147 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: University of Washington
Country of organization: United States
Domain: Vision
Task: Object detection
Training compute: 1.3×10¹⁹ FLOP
Compute estimation method: Operation counting
Parameters: 56,933,216
Dataset size: 5.4M
Training hardware: NVIDIA M40, NVIDIA GeForce GTX TITAN X
Model accessibility: Unreleased
Open weights: No
Citations: 25,147
Epoch confidence: Likely