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.dev202208130508.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 105215b6e89720f72b7a1deacd6a8513e319e6d0ad6ff86fc64c4b2321c9b0d1 |
|
MD5 | 7c272d5693d13e792306522f5aaf8ca3 |
|
BLAKE2b-256 | 9c1fd6b9f0ff18837bfc03d98c8820826ce7f3bf9b5916c7d669b97ac562ddf0 |
Hashes for tflite_model_maker_nightly-0.4.2.dev202208130508-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | aae6eea948a2be080e787cfd5d5ad0b3b246cb767cd80e9c110c95ac6bde8f10 |
|
MD5 | fa6adcd8ba246a11f07b7a6018315680 |
|
BLAKE2b-256 | f3eb7d152fd7ddc1b73d64e6b3a493607f0243b487ca7b2bbf179b133fbf674f |