TensorFlow Lite C API Reference
Structs
Parameters for asymmetric quantization across a dimension (i.e per output channel quantization).
bfloat16 data type compatible with the Google Brain definition.
Parameters for blockwise quantization across the output channels dimension.
Double-precision complex data type compatible with the C99 definition.
Single-precision complex data type compatible with the C99 definition.
TfLiteContext
allows an op to access the tensors.Defines a custom memory allocation not owned by the runtime.
WARNING: This is an experimental interface that is subject to change.
WARNING: This is an experimental interface that is subject to change.
Struct to hold all the methods for a delegate plugin.
Metadata to encode each dimension in a sparse tensor.
Light-weight tensor struct for TF Micro runtime.
An external context is a collection of information unrelated to the TF Lite framework, but useful to a subset of the ops.
Half precision data type compatible with the C99 definition.
Fixed size list of floats. Used for per-channel quantization.
Fixed size list of integers.
A structure representing an instance of a node.
TfLiteOpaqueDelegateBuilder
is used for constructing TfLiteOpaqueDelegate
, see TfLiteOpaqueDelegateCreate
in c_api_opaque.h
.WARNING: This is an experimental interface that is subject to change.
Structure specifying the quantization used by the tensor, if-any.
Legacy.
TfLiteRegistration
defines the implementation of an operation (a built-in op, custom op, or custom delegate kernel).Parameters used to encode a sparse 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
A union of pointers that points to memory for a given tensor.
