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.
  • Note that you might also need to install sndfile for Audio tasks. On Debian/Ubuntu, you can do so by sudo apt-get install libsndfile1

Installation

There are two ways to install Model Maker.

pip install tflite-model-maker

If you want to install nightly version tflite-model-maker-nightly, please follow the command:

pip install tflite-model-maker-nightly
  • Clone the source code from GitHub and install.
git clone https://github.com/tensorflow/examples
cd examples/tensorflow_examples/lite/model_maker/pip_package
pip install -e .

TensorFlow Lite Model Maker depends on TensorFlow pip package. For GPU support, please refer to TensorFlow's GPU guide or installation guide.

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.

  • Step 1. Import the required modules.
from tflite_model_maker import image_classifier
from tflite_model_maker.image_classifier import DataLoader
  • Step 2. Load input data specific to an on-device ML app.
data = DataLoader.from_folder('flower_photos/')
  • Step 3. Customize the TensorFlow model.
model = image_classifier.create(data)
  • Step 4. Evaluate the model.
loss, accuracy = model.evaluate()
  • Step 5. Export to Tensorflow Lite model and label file in export_dir.
model.export(export_dir='/tmp/')

Notebook

Currently, we support image classification, text classification and question answer tasks. Meanwhile, we provide demo code 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-0.3.5.dev202112080608.tar.gz.

File metadata

  • Download URL: tflite-model-maker-nightly-0.3.5.dev202112080608.tar.gz
  • Upload date:
  • Size: 354.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.8.2 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.7.12

File hashes

Hashes for tflite-model-maker-nightly-0.3.5.dev202112080608.tar.gz
Algorithm Hash digest
SHA256 45349a9dad8e3ad5281ac23b3296b7c018bfd70d560f8c531b39c17e6d2c883d
MD5 bb0e5f72d29baf6bb7aa9c417b7d1d0e
BLAKE2b-256 0a719b0b6eb3b4d20e64d2de9e90c81771e4102c06cd19dc808f8e35be1e94fe

See more details on using hashes here.

File details

Details for the file tflite_model_maker_nightly-0.3.5.dev202112080608-py3-none-any.whl.

File metadata

File hashes

Hashes for tflite_model_maker_nightly-0.3.5.dev202112080608-py3-none-any.whl
Algorithm Hash digest
SHA256 a50bea6de727084f2c1f423995ef55581ea1950a2f116d219e9a2b2c28e6852b
MD5 a64bb04a2dd671e6fe396d5095fb79fa
BLAKE2b-256 9a2412cc53f71aef8cb865375e88a10ecc02b54e834d20411733c06a581af50c

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