OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

EfficientNet Keras

EfficientNet Keras is a Python implementation of the EfficientNet convolutional neural network architecture for Keras and TensorFlow Keras, with model variants and pretrained weights for image classification and transfer learning.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

EfficientNet Keras — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a Keras or TensorFlow Keras project needs an EfficientNet model implementation, pretrained weights, or the documented checkpoint-conversion workflow.

Who it is for

  • Developers building image-classification applications with Keras or TensorFlow Keras.
  • Practitioners adapting pretrained EfficientNet models for transfer-learning workflows.

Documented uses

  • Initialize an EfficientNet B0–B7 model with ImageNet or Noisy-Student weights.
  • Load a saved model using the relevant EfficientNet framework module.
  • Convert original TensorFlow checkpoints to Keras HDF5 using the repository's converter script.
Before you choose

Requirements & limits

The implementation is available in a public GitHub repository under the Apache-2.0 license.

  • Choose the Keras or TensorFlow Keras interface that matches the project; the repository documents separate module imports.
  • The listed prerequisites include Keras or TensorFlow, keras_applications, and scikit-image.
  • The README identifies version 0.0.4 as the version to use when loading models trained before the July 24, 2019 library update.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the EfficientNet package

Add the package to a Python environment for use with Keras or TensorFlow Keras.

Before you start

  • Keras 2.2.0 or later, or TensorFlow 1.12.0 or later
  • keras_applications 1.0.7 or later
  • scikit-image

Steps

  1. Install the documented requirements in your Python environment.

  2. Install the package from PyPI with the command below, or install the repository version with the command below.

    Documented command
    pip install -U efficientnet
    Documented command
    pip install -U git+https://github.com/qubvel/efficientnet

Expected outcome

The EfficientNet package is installed for use with the documented Keras or TensorFlow Keras interfaces.

Guide limitations

  • The README lists a separate --pre PyPI command for the latest release with Keras and tf.keras support.
  • Models trained before the July 24, 2019 library update may require efficientnet version 0.0.4.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
qubvel/efficientnet · Official homepage title · retained in its source language
How we review sourcesSuggest a correction