The PyCoral API (the
pycoral module) is built atop the TensorFlow Lite Python
API to simplify your code when running an
inference on the Edge TPU, and to provide advanced features for the Edge TPU such as model
pipelining across multiple Edge TPUs, and on-device transfer learning.
If you're new to this API, check out our guide to run inference on the Edge TPU with Python.
To install the library, see the software downloads page.
Utilities to help process a dataset.
Utilities for using the TensorFlow Lite Interpreter with Edge TPU.
Functions to work with any model.
Functions to work with a classification model.
Functions to work with a detection model.
The pipeline API allows you to run a segmented model across multiple Edge TPUs.
For more information, see Pipeline a model with multiple Edge TPUs.
A softmax regression model for on-device backpropagation of the last layer.
A weight imprinting engine that performs low-shot transfer-learning for image classification models.
For more information about how to use this API and how to create the type of model required, see Retrain a classification model on-device with weight imprinting.
Is this content helpful?