Project AURIONAI Use-Cases Research & Innovation
Megvii
visionfamily

ShuffleNet

Family of efficient mobile CNNs that use channel shuffle and group convolutions.

MegviiMegviiChina
Figure from the ShuffleNet paper: Channel shuffle with two stacked group convolutions.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released4 Jul 2017
Opennessunknown
Runs onmobile or NPU, CPU server
Statusactive

Lineage

MegviiShuffleNet v2 belongs to this familyvision30 Jul 2018
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Efficient vision networks for mobile and edge devicesproduced by

Identity

Developer
Megvii
Family
not in the notes
Released
4 Jul 2017 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
ShuffleNet v1 and v2 (x0.5 to x2.0).
Context length
not in the notes
Input
image
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU, CPU server
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/1707.01083 https://arxiv.org/abs/1707.01083
  2. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  3. aihub.qualcomm.com/models/shufflenet_v2 https://aihub.qualcomm.com/models/shufflenet_v2
  4. github.com/pytorch/vision/blob/main/torchvision/models/s... https://github.com/pytorch/vision/blob/main/torchvision/models/shufflenetv2.py
  5. github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/shufflenet-v2-x1.0
  6. pytorch.org/hub/pytorch_vision_shufflenet_v2 https://pytorch.org/hub/pytorch_vision_shufflenet_v2
  7. raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_shufflenet_... https://raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_shufflenet_v2.md
  8. arxiv.org/html/1707.01083 https://arxiv.org/html/1707.01083

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "ShuffleNet", https://aurion.semai.id/models/shufflenet/, records of October 2026.