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.dev202203020607.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | e1c3e10e6f3b55e2548300f1ea68d8e8ed0ea0a1d186c4ed14f15252321ed9cc |
|
MD5 | 2b6dbbff2b58842a691a70f6955a330d |
|
BLAKE2b-256 | db618230f53a94766c6cca1bdd0b1d8972c790e0ea35e72b336ca4c81e23adf9 |
Hashes for tflite_model_maker_nightly-0.3.5.dev202203020607-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3269a3c69e85490e7eaff0ef30abb011d9ddd693ba79f15d1e42a76b71e70e3c |
|
MD5 | 09d0f53dc0e44408f66aac0489b92219 |
|
BLAKE2b-256 | 1029119f524ccabc435a20967837e3cbd5e5bde6f645fff0189a4bebdea50ab5 |