ShuffleNet v1

Parameters

2.4M

Published

Jul 3, 2017

ShuffleNet v1 is an AI model developed by Megvii Inc (China), first published in July 2017. It works in the vision domain, on tasks such as object detection and image classification.

Epoch AI has no training-compute estimate for this model. The model has 2,430,000 parameters. It was trained on roughly 1.3M datapoints.

The reference paper has 8,325 citations.

Full record

Organization: Megvii Inc
Country of organization: China
Domain: Vision
Task: Object detection, Image classification
Parameters: 2,430,000
Dataset size: 1.3M
Numerical format: FP32
Citations: 8,325