View Source API Reference tflite_elixir v1.0.0

This module contains some helper functions from the tflite namespace in TensorFlow Lite's codebase.

This module contains libcoral C++ API, which provides convenient functions to perform inferencing and on-device transfer learning with TensorFlow Lite models on Coral devices.

TfLite delegates: graph accelerators an interpreter builder can be given.

ErrorReporter to provide reporting destinations.

An RAII object that represents a read-only tflite model, copied from disk, or mmapped.

Experimental image classification module.

An interpreter for a graph of nodes that input and output from tensors.

An interpreter that lives inside a process, so that feeding it, running it and reading the result back is one step that nothing can interleave with.

Build an interpreter capable of interpreting model.

A model compiled through LiteRT, which is where the accelerators and the per-operator profile live.

A compiled model on a node of its own, so that a crash inside the runtime costs one node instead of yours.

A compiled model that lives inside a process, so several processes can share one model without taking turns badly.

Experimental object detection module.

This built-in op resolver provides a list of TfLite delegates that could be applied by TfLite interpreter by default.

A runner for one of a model's signatures.

Quantization parameters that corresponds to the table QuantizationParameters in the TFLite Model schema file.

A typed multi-dimensional array used in Tensorflow Lite.

Runs basic tokenization such as punctuation spliting, lower casing.

Runs end-to-end tokenization.

Runs WordPiece tokenziation.

Image classification mix task: mix help classify_image

Image detection mix task: mix help detect_image

List all available Edge Tpu mix task: mix help list_edgetpu