keras/mobilenet_v3_large_100_imagenet

Model Overview

Instantiates the MobileNetV3 architecture.

References

• Searching for MobileNetV3 (ICCV 2019)
  • Based on the Original keras.applications MobileNetv3

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Links

• MobileNetV3 Quickstart Notebook
• [MobileNetV3 API Documentation](coming soon)
• MobileNetV3 Model Card
• KerasHub Beginner Guide
• KerasHub Model Publishing Guide

Installation

Keras and KerasHub can be installed with:

pip install -U -q keras-hub
pip install -U -q keras

Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instructions on installing them in another environment see the Keras Getting Started page.

Presets

The following model checkpoints are provided by the Keras team. Full code examples for each are available below.

Preset name	Parameters	Description
mobilenet_v3_small_050_imagenet	278.78K	Small MobileNet V3 model pre-trained on the ImageNet 1k dataset at a 224x224 resolution.
mobilenet_v3_large_100_imagenet
mobilenet_v3_large_100_imagenet_21k
mobilenet_v3_small_100_imagenet

Arguments

• stackwise_expansion: list of ints or floats, the expansion ratio for each inverted residual block in the model.
• stackwise_filters: list of ints, number of filters for each inverted residual block in the model.
• stackwise_stride: list of ints, stride length for each inverted residual block in the model.
• include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(scale=1 / 255) layer.
• input_shape: optional shape tuple, defaults to (None, None, 3).
• input_tensor: optional Keras tensor (i.e., output of layers.Input()) to use as image input for the model.
• alpha: float, controls the width of the network. This is known as the depth multiplier in the MobileNetV3 paper, but the name is kept for consistency with MobileNetV1 in Keras.
  • If alpha < 1.0, proportionally decreases the number of filters in each layer.
  • If alpha > 1.0, proportionally increases the number of filters in each layer.
  • If alpha = 1, default number of filters from the paper are used at each layer.

Example Usage

import keras_cv
import numpy as np

input_data = np.ones(shape=(8, 224, 224, 3))

model = keras_cv.models.MobileNetV3Backbone.from_preset("mobilenet_v3_large_100_imagenet")
output = model(input_data)

Example Usage with Hugging Face URI

import keras_cv
import numpy as np

input_data = np.ones(shape=(8, 224, 224, 3))

model = keras_cv.models.MobileNetV3Backbone.from_preset("hf://keras/mobilenet_v3_large_100_imagenet")
output = model(input_data)