Emgu.TF.Lite Namespace |
Wrapper of Tensorflow Lite functions.
Classes| Class | Description | |
|---|---|---|
 | AllocationType |
Memory allocation strategies.
|
| BuildinOpResolver |
The default tensor flow lite buildin op resolver.
|
| Complex64 |
Complex number
|
| DataType |
Types supported by tensor
|
| DynamicBuffer |
DynamicBuffer holds temporary buffer that will be used to create a dynamic tensor.
|
| FlatBufferModel |
An RAII object that represents a read-only tflite model, copied from disk,
or mmapped. This uses flatbuffers as the serialization format.
|
| GpuDelegateV2 | |
| IntArray |
A tensorflow integer array
|
| Interpreter |
The tensorflow lite interpreter.
|
| QuantizationParams |
Parameters for asymmetric quantization.
|
| StatefulNnApiDelegate | |
| Status |
Tensorflow lite status
|
| Tensor |
A tensorflow lite tensor
|
| TfLiteInvoke |
Class that provide access to native tensorflow lite functions
|
| TfLiteInvokeTfliteErrorCallback |
Define the functional interface for the error callback
|
Interfaces| Interface | Description | |
|---|---|---|
 | IDelegate |
Abstract interface that returns a pointer to the delegate
|
| IOpResolver |
Abstract interface that returns TfLiteRegistrations given op codes or custom
op names. This is the mechanism that ops being referenced in the flatbuffer
model are mapped to executable function pointers (TfLiteRegistrations)
|