CNN committee (traffic sign)

Training compute

9.9×10¹⁴ FLOP

Parameters

1.4M

Published

Oct 3, 2011

CNN committee (traffic sign) is an AI model developed by IDSIA (Switzerland), first published in October 2011. It works in the vision domain, on tasks such as image classification.

Training it took an estimated 9.9×10¹⁴ FLOP of compute (estimation method: operation counting). The model has 1,388,800 parameters. It was trained on roughly 53.3K datapoints. Training ran on 4 NVIDIA GeForce GTX 580,NVIDIA GeForce GTX 480.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.

Full record

Organization: IDSIA
Country of organization: Switzerland
Domain: Vision
Task: Image classification
Training compute: 9.9×10¹⁴ FLOP
Compute estimation method: Operation counting
Parameters: 1,388,800
Dataset size: 53.3K
Training hardware: NVIDIA GeForce GTX 580, NVIDIA GeForce GTX 480
Chips used: 4
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Likely