AIMET Examples

AIMET Examples provide reference code (in the form of Jupyter Notebooks) to learn how to apply AIMET quantization and compression features. It is also a quick way to become familiar with AIMET usage and APIs.

For more details on each of the features and APIs please refer: Links to User Guide and API Documentation

Browse the notebooks

The following table has links to browsable versions of the notebooks for different features. | Model Quantization Examples

Features	PyTorch	TensorFlow	Keras
Quantization-Aware Training (QAT)	Link	Link
QAT with Range Learning	Link	Link
Cross-Layer Equalization (CLE)	Link	Link	Link
Adaptive Rounding (AdaRound)	Link	Link	Link
AutoQuant	Link	Link
BN Re-estimation	Link

Model Compression Examples

Features	PyTorch	TensorFlow
Channel Pruning	Link	Link
Spatial SVD	Link	Link
Spatial SVD + Channel Pruning	Link	Link

Running the notebooks

Install Jupyter

• Install the Jupyter metapackage as follows (pre-pend with “sudo -H” if appropriate):

python3 -m pip install jupyter

• Start the notebook server as follows (please customize the command line options if appropriate):

jupyter notebook –ip=* –no-browser &

• The above command will generate and display a URL in the terminal. Copy and paste it into your browser.

Download the Example notebooks and related code

• Clone the AIMET repo as follows to any location: * WORKSPACE=”<absolute_path_to_workspace>” * mkdir $WORKSPACE && cd $WORKSPACE * Go to https://github.com/quic/aimet/releases and identify the release tag (<release_tag>) of the AIMET package that you’re working with. * git clone https://github.com/quic/aimet.git –branch <release_tag> * Update the environment variable as follows: export PYTHONPATH=$PYTHONPATH:${WORKSPACE}/aimet

• The dataloader, evaluator, and trainer utilized in the examples is for the ImageNet dataset. To run the example, please download the ImageNet dataset from here: https://www.image-net.org/download.php

• Install AIMET and its dependencies using the instructions in the Installation section’

Run the notebooks

• Navigate to one of the following paths under the Examples directory and launch your chosen Jupyter Notebook (.ipynb extension): - Examples/torch/quantization/ - Examples/torch/compression/ - Examples/tensorflow/quantization/ - Examples/tensorflow/compression/

• Follow the instructions therein to execute the code.