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-0.4.2.dev202206240509.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | c6dcda3a98a0680f86a8a4aff845a3dd6b800d24269c0b5bb33913fa21a10b49 |
|
MD5 | 23f81f3a1323f466dd85a6c3b8c8471d |
|
BLAKE2b-256 | 83ae123814d9d9f26a108ecde815c87eed388ecd3dce2c93f6ab8c9cb6f37675 |
Hashes for tflite_model_maker_nightly-0.4.2.dev202206240509-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 699529b7a7c321c220b52f80de1f3fdc8c4a6a39a36becc2ead3f64126c0465b |
|
MD5 | a980709f2fd155e1a544d8b02d8e1150 |
|
BLAKE2b-256 | 0b810ed88fea8d5bc36fe0113ccd8cd236c33cd288fad14a26ffdf107ec2cf73 |