GdoongMathew / EfficientNetV2

Implementation of EfficientNetV2 model in TensorFlow 2 Keras.

EfficientNetV2 in TensorFlow

This repo is a reimplementation of EfficientNet V2. The code base is heavily inspired by TensorFlow implementation and EfficientNet Keras

Architectures

Model	params	ImageNet Acc	CIFAR-10
EfficientNetV2_Base	7M	-	-
EfficientNetV2_S	22M	83.9	98.7
EfficientNetV2_M	54M	85.1	99.0
EfficientNetV2_L	120M	85.7	99.1
EfficientNetV2_XL (21K)	208M	87.3	-

Pretrained EfficientNetV2 Weights

Ported from automl efficientnetv2 imagenet21k pretrained weights

Arch	imagenet	imagenet21k	imagenet21k-ft1k
EfficientNetV2_S	h5	h5	h5
EfficientNetV2_M	h5	h5	h5
EfficientNetV2_L	h5	h5	h5
EfficientNetV2_XL	-	h5	h5

Examples

---

• Start the model and reload weights

from efficientnetv2 import EfficientNetV2_L
model = EfficientNetV2_L(input_shape=(512, 512, 3), weights=None)
model.load_weights('path_to_model.h5')

• Reloading pretrained ImageNet21K weight

from efficientnetv2 import EfficientNetV2_S
model = EfficientNetV2_S(weights='imagenet21k-ft1k')

Installation

---

Requirements

• TensorFlow >= 2.4

From source

pip install -U git+https://github.com/GdoongMathew/EfficientNetV2