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-0.4.3.dev202305090529.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | f4c8714861bedf1eb50acbc1bcaf06be01706f4a6e7176498b08d0624e6e2030 |
|
MD5 | 423c0b1dcc7506c9a24a942d3d9beb0a |
|
BLAKE2b-256 | 9a8a58b3a9f1908d83afd240e6f4902202752258a5c313e8d5d714e87e0a2622 |
Hashes for tflite_model_maker_nightly-0.4.3.dev202305090529-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e93a8e7b5bd3d58d370ae04bac46ebc636cce4ba6602c06c5df50fc93dd44453 |
|
MD5 | ad17e22a23ebf27d0eaaa62271c602e5 |
|
BLAKE2b-256 | e8859a3b4e3f72e49714aabad904e554356f1f0f2c4a84d71c12d631e324e881 |