In this project, the contributor will gain experience with C++ and Python programming, TensorFlow/Keras and its storage formats for trained machine learning models, and JAX/FLAX for accelerated machine learning. They will begin by familiarizing themselves with SOFIE and its Keras parser. After researching the changes required to support the latest TensorFlow version, they will implement functionalities to ensure the successful generation of inference code for the latest Keras models. In the next phase, they will explore the JAX/FLAX library and investigate its potential integration with SOFIE.
0 commit comments