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.dev202201230609.tar.gz.

File metadata

  • Download URL: tflite-model-maker-nightly-0.3.5.dev202201230609.tar.gz
  • Upload date:
  • Size: 355.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.10.1 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.7.12

File hashes

Hashes for tflite-model-maker-nightly-0.3.5.dev202201230609.tar.gz
Algorithm Hash digest
SHA256 cac954358e34edb488af25c010fcf1ca00014b04808adc284dd97eab111fd7fc
MD5 7f571d007d585ea03f9d4ac7473e9a2a
BLAKE2b-256 4446ce8d0c0ebc1eab1ee7f993632d75fbdd886d89c46a4673c7559d4e8dd7b0

See more details on using hashes here.

File details

Details for the file tflite_model_maker_nightly-0.3.5.dev202201230609-py3-none-any.whl.

File metadata

File hashes

Hashes for tflite_model_maker_nightly-0.3.5.dev202201230609-py3-none-any.whl
Algorithm Hash digest
SHA256 d06064841b6b72659da2e17bfa447372c2a33c5350785c7f6e690b53833e195d
MD5 8e5861fb175788e76365e88709e346ef
BLAKE2b-256 8c8cdb5fda734fb9d6b9c712d5c5b61175a8d47bdd5e062f3c7d1fa9eab33389

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