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-0.4.2.dev202208130508.tar.gz.

File metadata

  • Download URL: tflite-model-maker-nightly-0.4.2.dev202208130508.tar.gz
  • Upload date:
  • Size: 368.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.12.0 pkginfo/1.8.3 requests/2.28.1 requests-toolbelt/0.9.1 tqdm/4.64.0 CPython/3.7.13

File hashes

Hashes for tflite-model-maker-nightly-0.4.2.dev202208130508.tar.gz
Algorithm Hash digest
SHA256 105215b6e89720f72b7a1deacd6a8513e319e6d0ad6ff86fc64c4b2321c9b0d1
MD5 7c272d5693d13e792306522f5aaf8ca3
BLAKE2b-256 9c1fd6b9f0ff18837bfc03d98c8820826ce7f3bf9b5916c7d669b97ac562ddf0

See more details on using hashes here.

File details

Details for the file tflite_model_maker_nightly-0.4.2.dev202208130508-py3-none-any.whl.

File metadata

File hashes

Hashes for tflite_model_maker_nightly-0.4.2.dev202208130508-py3-none-any.whl
Algorithm Hash digest
SHA256 aae6eea948a2be080e787cfd5d5ad0b3b246cb767cd80e9c110c95ac6bde8f10
MD5 fa6adcd8ba246a11f07b7a6018315680
BLAKE2b-256 f3eb7d152fd7ddc1b73d64e6b3a493607f0243b487ca7b2bbf179b133fbf674f

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