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-0.3.3.dev202107072257.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 28d44f58e4908b5ad704c6f0cd7b23101bc4973226edf1973d2b9d3fb446b50e |
|
MD5 | 445436907eeafd6b13502d2021142a2b |
|
BLAKE2b-256 | 5c5348ae9984da0cebb476f07c4d580273f44197d56fc98f158844cea5da0fb0 |
Hashes for tflite_model_maker_nightly-0.3.3.dev202107072257-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6be5173225b64e9c0b7b6ba5794d8ed6bba835b70e24a08255857c198fbc9597 |
|
MD5 | 3ac4f48b0b751b81f7cbb46498bc1426 |
|
BLAKE2b-256 | 149d79308407dc36a0c4b9d208273db3ed86323eee826fede6a36764e202450d |