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 bysudo apt-get install libsndfile1
Installation
There are two ways to install Model Maker.
- Install a prebuilt pip package:
tflite-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
Hashes for tflite-model-maker-nightly-0.3.5.dev202205010514.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5e1c57c8bd023494d0ac92e6f197827fc75297d0cd3abd9c4e5e2b6c2f9bf4e4 |
|
MD5 | 26f87b3d29336e2e02127a6a86a8c8ed |
|
BLAKE2b-256 | 7076c2077323ca7caf07e9a42016398886f4e15ed81d50a32d46bd28fa86f371 |
Hashes for tflite_model_maker_nightly-0.3.5.dev202205010514-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 789d68a624df15c21b55e1e8a6cd6276b4e3b1de7289f31d4d2f7a115920201c |
|
MD5 | ba7c391e421bfe3c8abb2d8be3a4886a |
|
BLAKE2b-256 | dc7b257c2a581bc22e08b8920a20559faf86e75b5d421e41d78736a2d527af69 |