Project AURIONAI Use-Cases Research & Innovation
Google
visionfamily

EfficientNet

Google family of image classifiers that scale depth, width and resolution together; one of the most used backbones for crop, defect and medical image classifiers and for EfficientDet.

GoogleGoogleUSA
Diagram of model scaling by width, depth, resolution and the compound scaling used by EfficientNet, from the model card.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released28 May 2019
Opennessunknown
Runs onmobile or NPU, CPU server, microcontroller
Statusactive

Lineage

2019202020212022EfficientNet-B0EfficientNet-B0, May 2019EfficientNet-B7, May 2019EfficientNet-Lite, May 2019EfficientNetV2EfficientNetV2, Apr 2021
GoogleEfficientNetV2 belongs to this familyvision1 Apr 202121.61M
GoogleEfficientNet-B0 belongs to this familyvision28 May 20195.3M
GoogleEfficientNet-B7 belongs to this familyvision28 May 201966M
GoogleEfficientNet-Lite belongs to this familyvision28 May 2019
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 devicesexemplar

Identity

Developer
Google
Family
not in the notes
Released
28 May 2019 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
EfficientNet B0 to B7, Noisy Student and AdvProp weights, EfficientNet-Lite 0 to 4, EfficientNet-EdgeTPU, EfficientNetV2 S, M, L.
Context length
not in the notes
Input
image
Output
not in the notes
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, microcontroller
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO, Edge Impulse, STM32 model zoo, TI edge AI model zoo, MediaPipe.
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/1905.11946 https://arxiv.org/abs/1905.11946
  2. Model Garden on Gemini Enterprise Agent Platform cloud.google.com https://cloud.google.com/model-garden
  3. huggingface.co/google/efficientnet-b7 https://huggingface.co/google/efficientnet-b7
  4. 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
  5. huggingface.co/timm/tf_efficientnetv2_s.in21k_ft_in1k https://huggingface.co/timm/tf_efficientnetv2_s.in21k_ft_in1k
  6. aihub.qualcomm.com/models/efficientnet_b0 https://aihub.qualcomm.com/models/efficientnet_b0
  7. github.com/pytorch/vision/blob/main/torchvision/models/e... https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py

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