Skip to main content

TFLite Model Maker: a model customization library for on-device applications.

Project description

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. For more detail, you could refer to Colab for image classification.

  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 and label file in export_dir.
model.export(export_dir='/tmp/')

Notebook

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

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Built Distribution

File details

Details for the file tflite-model-maker-nightly-0.1.2.dev202008101438.tar.gz.

File metadata

  • Download URL: tflite-model-maker-nightly-0.1.2.dev202008101438.tar.gz
  • Upload date:
  • Size: 43.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.3.0 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.7.7

File hashes

Hashes for tflite-model-maker-nightly-0.1.2.dev202008101438.tar.gz
Algorithm Hash digest
SHA256 62be523fcba18d6282ac8383e3a031847888276c628c61000e05b5e025abc2db
MD5 8c744dd1e12177e05494d50c56659f05
BLAKE2b-256 9eb94e5d6fa6eff52e892b4df3c4732e29cb3938babcc36b3cf6aec05700d874

See more details on using hashes here.

File details

Details for the file tflite_model_maker_nightly-0.1.2.dev202008101438-py3-none-any.whl.

File metadata

File hashes

Hashes for tflite_model_maker_nightly-0.1.2.dev202008101438-py3-none-any.whl
Algorithm Hash digest
SHA256 51b0c3db6ee42c3cdd89101387e7cba3e443cd54a1a3d2327f5df1e85f567bfa
MD5 7f29acb6342f54dc8ef71a8ff741b378
BLAKE2b-256 d8b9f148107bd59be646503be027431acb9eeaaab8746ab90022732d55d6c7ad

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page