Skip to content
Branch: master
Find file History

Latest commit

ziyeqinghan and Copybara-Service Add metadata in image classification colab.
PiperOrigin-RevId: 304582910
Latest commit 70be2b2 Apr 3, 2020

Files

Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
cli Add EfficientNet-lite models and set EfficientNet-Lite0 as the defaul… Mar 6, 2020
core Fix saved model conversion failure Apr 2, 2020
demo Add metadata in image classification colab. Apr 3, 2020
README.md Fix typos for model maker Mar 17, 2020
__init__.py Change names. Feb 28, 2020
requirements.txt tensorflow-hub 0.8.0 has been released; let ModelMaker use it (or lat… Apr 2, 2020

README.md

TFLite Model Maker

Overview

The TFLite Model Maker library simplifies the process of adapting and converting a TensorFlow neural-network model to particular input data when deploying this model for on-device ML applications.

Requirements

  • Refer to requirements.txt for dependent libraries that're needed to use the library and run the demo code.

Installation

Two alternative methods to install Model Maker library with its dependencies.

  • Install directly.
pip install git+https://github.com/tensorflow/examples.git#egg=tensorflow-examples[model_maker]
  • Clone the repo from the HEAD, and then install with pip.
git clone https://github.com/tensorflow/examples
cd examples
pip install .[model_maker]

End-to-End Example

For instance, it could have an end-to-end image classification example that utilizes this library with just 4 lines of code, each of which representing one step of the overall process:

  1. Load input data specific to an on-device ML app.
data = ImageClassifierDataLoader.from_folder('flower_photos/')
  1. Customize the TensorFlow model.
model = image_classifier.create(data)
  1. Evaluate the model.
loss, accuracy = model.evaluate()
  1. Export to Tensorflow Lite model.
model.export('flower_classifier.tflite', 'flower_label.txt')

Notebook

Currently, we support image classification and text classification tasks and provide demo code and colab for each of them in demo folder.

You can’t perform that action at this time.