Google Colaboratory (Colab) Notebooks

These Colab notebooks contain interactive sample applications using IREE's Python bindings and ML framework integrations.

Notebooks

Framework	Notebook file	Description	Link
Generic	low_level_invoke_function.ipynb	Shows off some concepts of the low level IREE python bindings
PyTorch	pytorch_jit.ipynb	Uses SHARK-Turbine for eager execution in a PyTorch session
TensorFlow	edge_detection.ipynb	Performs image edge detection using TF and IREE
TensorFlow	mnist_training.ipynb	Compile, train, and execute a neural network with IREE
TensorFlow	resnet.ipynb	Loads a pretrained ResNet50 model and runs it using IREE
TensorFlow	tensorflow_hub_import.ipynb	Runs a pretrained MobileNet V2 model using IREE
TFLite	tflite_text_classification.ipynb	Runs a pretrained text classification model using IREE

Working with GitHub

Refer to Colab's GitHub demo for general information about using Colab with GitHub.

To make changes to a notebook in this repository, one possible workflow is:

• Open or create the notebook in Colab
• Connect to a hosted or local runtime
• Make your changes, run the notebook, etc.
• Download the modified notebook using File > Download .ipynb
• Move the downloaded notebook file into a clone of this repository and submit a pull request

Testing

This notebooks are tested continuously by the samples.yml CI job.