# tflite_elixir v1.0.1 - Table of Contents

> TensorFlow Lite Elixir binding with optional TPU support.

## Modules

- [TFLiteElixir](TFLiteElixir.md): This module contains some helper functions from the `tflite`
namespace in TensorFlow Lite's codebase.

- [TFLiteElixir.Coral](TFLiteElixir.Coral.md): 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](https://coral.ai/products/).

- [TFLiteElixir.Delegate](TFLiteElixir.Delegate.md): TfLite delegates: graph accelerators an interpreter builder can be given.

- [TFLiteElixir.ErrorReporter](TFLiteElixir.ErrorReporter.md): ErrorReporter to provide reporting destinations.

- [TFLiteElixir.FlatBufferModel](TFLiteElixir.FlatBufferModel.md): An RAII object that represents a read-only tflite model, copied from disk, or
mmapped.

- [TFLiteElixir.ImageClassification](TFLiteElixir.ImageClassification.md): Experimental image classification module.

- [TFLiteElixir.Interpreter](TFLiteElixir.Interpreter.md): An interpreter for a graph of nodes that input and output from tensors.

- [TFLiteElixir.Interpreter.Server](TFLiteElixir.Interpreter.Server.md): 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.
- [TFLiteElixir.InterpreterBuilder](TFLiteElixir.InterpreterBuilder.md): Build an interpreter capable of interpreting model.

- [TFLiteElixir.LiteRT.CompiledModel](TFLiteElixir.LiteRT.CompiledModel.md): A model compiled through LiteRT, which is where the accelerators and the
per-operator profile live.
- [TFLiteElixir.LiteRT.CompiledModel.Isolated](TFLiteElixir.LiteRT.CompiledModel.Isolated.md): A compiled model on a node of its own, so that a crash inside the runtime
costs one node instead of yours.
- [TFLiteElixir.LiteRT.CompiledModel.Server](TFLiteElixir.LiteRT.CompiledModel.Server.md): A compiled model that lives inside a process, so several processes can share
one model without taking turns badly.
- [TFLiteElixir.MobileBert](TFLiteElixir.MobileBert.md)
- [TFLiteElixir.ObjectDetection](TFLiteElixir.ObjectDetection.md): Experimental object detection module.

- [TFLiteElixir.Ops.Builtin.BuiltinResolver](TFLiteElixir.Ops.Builtin.BuiltinResolver.md): This built-in op resolver provides a list of TfLite delegates that could be
applied by TfLite interpreter by default.

- [TFLiteElixir.SignatureRunner](TFLiteElixir.SignatureRunner.md): A runner for one of a model's signatures.
- [TFLiteElixir.TFLiteQuantizationParams](TFLiteElixir.TFLiteQuantizationParams.md): Quantization parameters that corresponds to the table QuantizationParameters
in the [TFLite Model schema file].
- [TFLiteElixir.TFLiteTensor](TFLiteElixir.TFLiteTensor.md): A typed multi-dimensional array used in Tensorflow Lite.
- [TFLiteElixir.Tokenizer.BasicTokenizer](TFLiteElixir.Tokenizer.BasicTokenizer.md): Runs basic tokenization such as punctuation spliting, lower casing.

- [TFLiteElixir.Tokenizer.FullTokenizer](TFLiteElixir.Tokenizer.FullTokenizer.md): Runs end-to-end tokenization.
- [TFLiteElixir.Tokenizer.WordpieceTokenizer](TFLiteElixir.Tokenizer.WordpieceTokenizer.md): Runs WordPiece tokenziation.

## Mix Tasks

- [mix classify_image](Mix.Tasks.ClassifyImage.md): Image classification mix task: `mix help classify_image`
- [mix detect_image](Mix.Tasks.DetectImage.md): Image detection mix task: `mix help detect_image`
- [mix list_edgetpu](Mix.Tasks.ListEdgetpu.md): List all available Edge Tpu mix task: `mix help list_edgetpu`