3-ensemble of Self-ensembles on CIFAR-100

Parameters

60.2M

Published

Aug 8, 2024

3-ensemble of Self-ensembles on CIFAR-100 is an AI model developed by Google DeepMind (United States), first published in August 2024. It works in the vision domain, on tasks such as image classification.

Epoch AI has no training-compute estimate for this model. The model has 60,200,000 parameters. Training ran on NVIDIA A100.

Access: Unreleased. Its weights are not openly released. It is built on top of ResNet-152 (ImageNet). Epoch AI rates the confidence of this record as likely.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Vision
Task: Image classification
Compute estimation method: Operation counting, Hardware
Parameters: 60,200,000
Training hardware: NVIDIA A100
Model accessibility: Unreleased
Open weights: No
Base model: ResNet-152 (ImageNet)
Epoch confidence: Likely