Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · google

efficientnet-b3

efficientnet-b3 is an EfficientNet image-classification model from google. According to the model card, it was trained on ImageNet-1k at 300x300 resolution and introduced in the EfficientNet scaling paper.

Publisher
google
Task
image-classification
Model type
efficientnet
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

efficientnet-b3 is published by google as an image-classification model. The captured configuration identifies EfficientNetForImageClassification with an efficientnet model type. According to the model card, it is the B3 EfficientNet variant trained on ImageNet-1k at 300x300 resolution.

Recorded capabilities

B3 ImageNet-1k training

According to the model card, this B3 model was trained on ImageNet-1k at 300x300 resolution.

Compound scaling design

The card describes a mobile-friendly pure ConvNet that uniformly scales depth, width, and resolution with a compound coefficient.

EfficientNet paper provenance

According to the model card, the model was introduced in EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan and Quoc V. Le.

Transformers usage path

The card demonstrates classification of a COCO 2017 image into ImageNet classes with EfficientNetImageProcessor and EfficientNetForImageClassification.

Use cases in the source record

  • Raw image classification into 1,000 ImageNet classes using the documented Transformers processor and model classes.
  • Starting point for selecting task-specific EfficientNet fine-tunes through the model hub.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No evaluation results were extracted from this record.
  • The card notes it was written by the Hugging Face team because the releasing team did not provide one, so details are secondary documentation rather than publisher-authored claims.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: google/efficientnet-b3

Captured: Unknown. Processed: 2026-09-07T19:34:45.804311+00:00.

EfficientNet (b3 model) EfficientNet model trained on ImageNet-1k at resolution 300x300. It was introduced in the paper EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan and Quoc V. Le, and first released in this repository . Disclaimer: The team releasing EfficientNet did not write a model card for this model so this model card has been written by the Hugging Face team. Model description EfficientNet is a mobile friendly pure convolutional model (ConvNet) that proposes a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compou…

F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015