Project AURIONAI Use-Cases Research & Innovation
Google
visionfamily

EfficientDet

Google family of scalable detectors combining an EfficientNet backbone with a BiFPN feature network; Lite versions target phones and edge NPUs.

GoogleGoogleUSA
Figure from the EfficientDet paper: feature network designs from FPN and PANet to the BiFPN used by EfficientDet.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released20 Nov 2019
Opennessunknown
Runs onCPU server, mobile or NPU
Statusactive

Lineage

20192020EfficientDet-D0EfficientDet-D0, Nov 2019EfficientDet-D7, Nov 2019EfficientDet-Lite, Nov 2019
GoogleEfficientDet-D0 belongs to this familyvision20 Nov 20193.9M
GoogleEfficientDet-D7 belongs to this familyvision20 Nov 2019
GoogleEfficientDet-Lite belongs to this familyvision20 Nov 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

Real-time object detection (YOLO and DETR lines)produced by

Identity

Developer
Google
Family
not in the notes
Released
20 Nov 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
D0 to D7 and EfficientDet-Lite0 to Lite4.
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
CPU server, mobile or NPU
Footprint
Edge or toolkit builds listed in: OpenVINO, NXP eIQ 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/1911.09070 https://arxiv.org/abs/1911.09070
  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. github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/efficientdet-d0-tf
  4. catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/efficientdet__tf... https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/efficientdet__tf2_ckpt
  5. github.com/NXP/eiq-model-zoo/tree/main/tasks/vision/obje... https://github.com/NXP/eiq-model-zoo/tree/main/tasks/vision/object-detection
  6. github.com/TexasInstruments/edgeai-tensorlab/tree/main/e... https://github.com/TexasInstruments/edgeai-tensorlab/tree/main/edgeai-modelzoo/models/vision/detection/coco
  7. modelzoo.co/model/yet-another-efficientdet-pytorch https://modelzoo.co/model/yet-another-efficientdet-pytorch

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