Converting a TensorFlow Lite Model#

You can download a TensorFlow Lite model from Kaggle or Hugging Face. To convert the model, run model conversion with the path to the .tflite model file:

import openvino as ov
ov.convert_model('your_model_file.tflite')
ovc your_model_file.tflite

Note

TensorFlow Lite model file can be loaded by openvino.Core.read_model or openvino.Core.compile_model methods by OpenVINO runtime API without preparing OpenVINO IR first. Refer to the inference example for more details. Using openvino.convert_model is still recommended if model load latency matters for the inference application.

Supported TensorFlow Lite Layers#

For the list of supported standard layers, refer to the Supported Operations page.

Supported TensorFlow Lite Models#

More than eighty percent of public TensorFlow Lite models are supported from open sources Kaggle and MediaPipe. Unsupported models usually have custom TensorFlow Lite operations.