# TensorFlow Lite C API Reference

| ## Structs ||
|---|---|
| [TfLiteAffineQuantization](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-affine-quantization) | Parameters for asymmetric quantization across a dimension (i.e per output channel quantization). |
| [TfLiteBFloat16](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-b-float16) | bfloat16 data type compatible with the Google Brain definition. |
| [TfLiteBlockwiseQuantization](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-blockwise-quantization) | Parameters for blockwise quantization across the output channels dimension. |
| [TfLiteComplex128](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-complex128) | Double-precision complex data type compatible with the C99 definition. |
| [TfLiteComplex64](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-complex64) | Single-precision complex data type compatible with the C99 definition. |
| [TfLiteContext](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-context) | `https://developers.google.com/edge/api/tflite/c/struct/tf-lite-context#struct_tf_lite_context` allows an op to access the tensors. |
| [TfLiteCustomAllocation](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-custom-allocation) | Defines a custom memory allocation not owned by the runtime. |
| [TfLiteDelegate](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-delegate) | WARNING: This is an experimental interface that is subject to change. |
| [TfLiteDelegateParams](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-delegate-params) | WARNING: This is an experimental interface that is subject to change. |
| [TfLiteDelegatePlugin](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-delegate-plugin) | Struct to hold all the methods for a delegate plugin. |
| [TfLiteDimensionMetadata](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-dimension-metadata) | Metadata to encode each dimension in a sparse tensor. |
| [TfLiteEvalTensor](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-eval-tensor) | Light-weight tensor struct for TF Micro runtime. |
| [TfLiteExternalContext](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-external-context) | An external context is a collection of information unrelated to the TF Lite framework, but useful to a subset of the ops. |
| [TfLiteFloat16](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-float16) | Half precision data type compatible with the C99 definition. |
| [TfLiteFloatArray](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-float-array) | Fixed size list of floats. Used for per-channel quantization. |
| [TfLiteIntArray](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-int-array) | Fixed size list of integers. |
| [TfLiteNode](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-node) | A structure representing an instance of a node. |
| [TfLiteOpaqueDelegateBuilder](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-opaque-delegate-builder) | `https://developers.google.com/edge/api/tflite/c/struct/tf-lite-opaque-delegate-builder#struct_tf_lite_opaque_delegate_builder` is used for constructing `TfLiteOpaqueDelegate`, see `TfLiteOpaqueDelegateCreate` in [c_api_opaque.h](https://developers.google.com/edge/api/tflite/c/c/api-opaque-8h-source#c__api__opaque_8h_source). |
| [TfLiteOpaqueDelegateParams](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-opaque-delegate-params) | WARNING: This is an experimental interface that is subject to change. |
| [TfLiteQuantization](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-quantization) | Structure specifying the quantization used by the tensor, if-any. |
| [TfLiteQuantizationParams](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-quantization-params) | Legacy. |
| [TfLiteRegistration](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration) | `https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration#struct_tf_lite_registration` defines the implementation of an operation (a built-in op, custom op, or custom delegate kernel). |
| [TfLiteRegistration_V1](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration-v1) | \\private Old version of `https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration#struct_tf_lite_registration` to maintain binary backward compatibility. |
| [TfLiteRegistration_V2](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration-v2) | \\private Old version of `https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration#struct_tf_lite_registration` to maintain binary backward compatibility. |
| [TfLiteRegistration_V3](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration-v3) | \\private Old version of `https://developers.google.com/edge/api/tflite/c/struct/tf-lite-registration#struct_tf_lite_registration` to maintain binary backward compatibility. |
| [TfLiteSparsity](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-sparsity) | Parameters used to encode a sparse tensor. |
| [TfLiteTensor](https://developers.google.com/edge/api/tflite/c/struct/tf-lite-tensor) | A tensor in the interpreter system which is a wrapper around a buffer of data including a dimensionality (or NULL if not currently defined). |

| ## Unions ||
|---|---|
| [TfLitePtrUnion](https://developers.google.com/edge/api/tflite/c/union/tf-lite-ptr-union) | A union of pointers that points to memory for a given tensor. |