efficientnet

library1.1.1pypypi✓ verified 81d ago

Re-implementation of EfficientNet models for Keras and TensorFlow Keras, providing pretrained ImageNet weights for B0–B7 and Noisy Student weights for B0–B7. Current version 1.1.1, low maintenance.

ai-ml

pip install efficientnet

github ↗package ↗

INSTALL

IMPORT

SIG · EFFICIENTNET

efficientnet

ai-mlpythonv1.1.1

Install

10.5s avg

Import

—

Disk

324MB

Pass rate

8/ 10

Env Coverage8 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.1.1 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✓ 10.5s

py 3.11

✓ —

✓ 10s

py 3.12

✓ —

✓ 10.2s

py 3.13

✓ —

✓ 10.1s

py 3.9

✕ build_error

✓ 11.7s

324MB installed

● package 324MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

EfficientNetB0

✓ from efficientnet import inject_keras_modules

✗ from efficientnet import EfficientNetB0

Load an EfficientNetB0 model with ImageNet weights and run a prediction.

from efficientnet import EfficientNetB0 from tensorflow.keras.applications.imagenet_utils import decode_predictions import numpy as np # Load model with pretrained weights model = EfficientNetB0(weights='imagenet') # Create a dummy image (224x224) dummy = np.random.rand(1, 224, 224, 3).astype(np.float32) # Predict preds = model.predict(dummy) print(decode_predictions(preds, top=3)[0])

Debug

Known issues

breakingAPI changed in v1.0.0: models must be imported from framework-specific modules. Previously trained models are not compatible; use model.load_weights or roll back.

fix

Use the new import pattern (from efficientnet import EfficientNetB0). Re-train or load weights carefully.

affects: >=0.0.4,<1.0.0

deprecatedThe 'swish' custom object is no longer required; the library now uses Keras' built-in Swish activation. If you have custom code relying on 'swish', update it.

fix

Remove any custom swish registration; use keras.activations.swish directly.

affects: >=1.0.0b2

Upgrade

Version history

1.1.1latest on PyPI · released Sep 15, 2020

Audit

Dependencies

kerasrequiredCore dependency for model implementation.

tensorflowoptionalRequired for tf.keras backend.

Agent activity

12 hits · last 30 days

node

Amazon

OpenAI (training)

Resources

githubhttps://github.com/qubvel/efficientnet ↗

packagehttps://pypi.org/project/efficientnet/ ↗