Functions | |
__attribute__ ((visibility("default"))) ie_version_t ie_c_api_version(void) | |
Returns number of version that is exported. Use the ie_version_free() to free memory. More... | |
Variables | |
ie_core_t ** | core |
const char * | device_name |
const char ie_core_versions_t * | versions |
const char * | xml |
const char const char * | weights_file |
const char const char ie_network_t ** | network |
const uint8_t * | xml_content |
const uint8_t size_t | xml_content_size |
const uint8_t size_t const ie_blob_t * | weight_blob |
const ie_network_t const char const ie_config_t * | config |
const ie_network_t const char const ie_config_t ie_executable_network_t ** | exe_network |
const ie_config_t * | ie_core_config |
const char * | plugin_name |
const char * | xml_config_file |
const char * | extension_path |
const char const char * | metric_name |
const char const char ie_param_t * | param_result |
const char const char * | config_name |
ie_available_devices_t * | avai_devices |
Set of functions dedicated to working with registered plugins and loading network to the registered devices.
__attribute__ | ( | (visibility("default")) | ) |
Returns number of version that is exported. Use the ie_version_free() to free memory.
Gets precision of blob's tensor.
Gets layout of blob's tensor.
Gets dimensions of blob's tensor.
Gets read-only access to the allocated memory.
Gets access to the allocated memory .
Releases previously allocated data.
Gets the size of the current Blob in bytes.
Gets the total number of elements, which is a product of all the dimensions.
Creates I420 blob from three planes Y, U and V.
Creates a NV12 blob from two planes Y and UV.
Creates a blob describing given roi_t instance based on the given blob with pre-allocated memory.
Creates a blob with the given tensor descriptor from the pointer to the pre-allocated memory.
Creates a blob with the specified dimensions, layout and to allocate memory.
Releases momory occupied by input_name or output_name.
Releases memory occupied by input_shapes.
Gets dimensions/shape of the output data with reversed order.
Changes the layout of the output data named "output_name".
Gets a layout of the output data.
Changes the precision of the output data named "output_name".
Gets a precision of the output data named "output_name".
Gets number of output for the network.
Run shape inference with new input shapes for the network.
Helper method collect all input shapes with input names of corresponding input data. Use the ie_network_input_shapes_free() method to free memory.
Changes the color format of the input data.
Gets color format of the input data.
Sets resize algorithm to be used during pre-processing.
Gets pre-configured resize algorithm.
Changes the layout of the input data named "input_name". This function should be called before loading the network to the device.
Gets a layout of the input data.
Changes the precision of the input data provided by the user. This function should be called before loading the network to the device.
Gets a precision of the input data provided by user.
Gets name corresponding to the "number". Use the ie_network_name_free() method to free memory.
Gets number of inputs for the network.
Get name of network.
When netowrk is loaded into the Infernece Engine, it is not required anymore and should be released.
Sets new batch size for certain infer request when dynamic batching is enabled in executable network that created this request.
Waits for the result to become available. Blocks until specified timeout elapses or the result becomes available, whichever comes first.
Sets a callback function that will be called on success or failure of asynchronous request.
Starts asynchronous inference of the infer request and fill outputs.
Starts synchronous inference of the infer request and fill outputs.
Sets input/output data to inference.
Gets input/output data for inference.
Releases memory occupied by ie_infer_request_t instance.
Gets configuration for current executable network. The method is responsible to extract information which affects executable network execution.
Sets configuration for current executable network. Currently, the method can be used when the network run on the Multi device and the configuration paramter is only can be "MULTI_DEVICE_PRIORITIES".
Gets general runtime metric for an executable network. It can be network name, actual device ID on which executable network is running or all other properties which cannot be changed dynamically.
Creates an inference request instance used to infer the network. The created request has allocated input and output blobs (that can be changed later). Use the ie_infer_request_free() method to free memory.
Releases memory occupied by ExecutableNetwork.
Releases memory occpuied by ie_available_devices_t.
Gets available devices for neural network inference.
Gets configuration dedicated to device behaviour. The method is targeted to extract information which can be set via SetConfig method.
Gets general runtime metric for dedicated hardware. The method is needed to request common device properties which are executable network agnostic. It can be device name, temperature, other devices-specific values.
Loads extension library to the device with a specified device name.
Unregisters a plugin with a specified device name.
Registers plugins specified in an ".xml" configuration file.
Registers a new device and a plugin which implement this device inside Inference Engine.
Sets configuration for device.
Creates an executable network from a network object. Users can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources). Use the ie_exec_network_free() method to free memory.
Reads the model from an xml string and a blob of the bin part of the IR. Use the ie_network_free() method to free memory.
Reads the model from the .xml and .bin files of the IR. Use the ie_network_free() method to free memory.
Releases memory occupied by ie_core_versions.
Gets version information of the device specified. Use the ie_core_versions_free() method to free memory.
Releases memory occupied by core.
Constructs Inference Engine Core instance using XML configuration file with devices description. See RegisterPlugins for more details. Use the ie_core_free() method to free memory.
Release the memory allocated by ie_param_t.
Release the memory allocated by ie_c_api_version.
version | A pointer to the ie_version_t to free memory. |
version | A pointer to the ie_param_t to free memory. |
xml_config_file | A path to .xml file with devices to load from. If XML configuration file is not specified, then default Inference Engine devices are loaded from the default plugin.xml file. |
core | A pointer to the newly created ie_core_t. |
core | A pointer to the core to free memory. |
core | A pointer to ie_core_t instance. |
device_name | Name to indentify device. |
versions | A pointer to versions corresponding to device_name. |
vers | A pointer to the ie_core_versions to free memory. |
core | A pointer to ie_core_t instance. |
xml | .xml file's path of the IR. |
weights_file | .bin file's path of the IR, if path is empty, will try to read bin file with the same name as xml and if bin file with the same name was not found, will load IR without weights. |
network | A pointer to the newly created network. |
core | A pointer to ie_core_t instance. |
xml_content | Xml content of the IR. |
xml_content_size | Number of bytes in the xml content of the IR. |
weight_blob | Blob containing the bin part of the IR. |
network | A pointer to the newly created network. |
core | A pointer to ie_core_t instance. |
network | A pointer to ie_network instance. |
device_name | Name of device to load network to. |
config | Device configuration. |
exe_network | A pointer to the newly created executable network. |
core | A pointer to ie_core_t instance. |
ie_core_config | Device configuration. |
device_name | An optinal name of a device. If device name is not specified, the config is set for all the registered devices. |
core | A pointer to ie_core_t instance. |
plugin_name | A name of a plugin. Depending on a platform, plugin_name is wrapped with a shared library suffix and a prefix to identify a full name of the library. |
device_name | A device name to register plugin for. If not specified, the method registers a plugin with the default name. |
core | A pointer to ie_core_t instance. |
xml_config_file | A full path to ".xml" file containing plugins configuration. |
core | A pointer to ie_core_t instance. |
device_name | A device name of the device to unregister. |
core | A pointer to ie_core_t instance. |
extension_path | Path to the extensions library file to load to a device. |
device_name | A device name of a device to load the extensions to. |
core | A pointer to ie_core_t instance. |
device_name | A name of a device to get a metric value. |
metric_name | A metric name to request. |
param_result | A metric value corresponding to the metric_name. |
core | A pointer to ie_core_t instance. |
device_name | A name of a device to get a configuration value. |
config_name | Name of a configuration. |
param_result | A configuration value corresponding to the config_name. |
core | A pointer to ie_core_t instance. |
avai_devices | The devices are returned as { CPU, FPGA.0, FPGA.1, MYRIAD } If there more than one device of specific type, they are enumerated with .# suffix |
avai_devices | A pointer to the ie_available_devices_t to free memory. |
ie_exec_network | A pointer to the ExecutableNetwork to free memory. |
ie_exec_network | A pointer to ie_executable_network_t instance. |
request | A pointer to the newly created ie_infer_request_t instance |
ie_exec_network | A pointer to ie_executable_network_t instance. |
metric_name | A metric name to request. |
param_result | A metric value corresponding to the metric_name. |
ie_exec_network | A pointer to ie_executable_network_t instance. |
param_config | A pointer to device configuration.. |
ie_exec_network | A pointer to ie_executable_network_t instance. |
metric_config | A configuration parameter name to request. |
param_result | A configuration value corresponding to a configuration paramter name. |
infer_request | A pointer to the ie_infer_request_t to free memory. |
infer_request | A pointer to ie_infer_request_t instance. |
name | Name of input or output blob. |
blob | A pointer to input or output blob. The type of Blob must match the network input precision and size. |
infer_request | A pointer to ie_infer_request_t instance. |
name | Name of input or output blob. |
blob | Reference to input or output blob. The type of a blob must match the network input precision and size. |
infer_request | A pointer to ie_infer_request_t instance. |
infer_request | A pointer to ie_infer_request_t instance. |
callback | A function to be called. |
infer_request | A pointer to ie_infer_request_t instance. |
timeout | Maximum duration in milliseconds to block for |
infer_request | A pointer to ie_infer_request_t instance. |
size | New batch size to be used by all the following inference calls for this request. |
network | The pointer to the instance of the ie_network_t to free. |
name | Name of the network. |
network | A pointer to the instance of the ie_network_t to get number of input information. |
size_result | A number of the instance's input information. |
network | A pointer to theinstance of the ie_network_t to get input information. |
number | An id of input information . |
name | Input name corresponding to the number. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
prec_result | A pointer to the precision used for input blob creation. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
p | A new precision of the input data to set (eg. precision_e.FP16). |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
layout_result | A pointer to the layout used for input blob creation. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
l | A new layout of the input data to set. |
@Gets dimensions/shape of the input data with reversed order.
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
dims_result | A pointer to the dimensions used for input blob creation. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. @parm resize_alg_result The pointer to the resize algorithm used for input blob creation. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
resize_algo | Resize algorithm. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
colformat_result | The pointer to the color format used for input blob creation. @reutrn Status code of the operation: OK(0) for success. |
network | A pointer to ie_network_t instance. |
input_name | Name of input data. |
color_format | Color format of the input data. @reutrn Status code of the operation: OK(0) for success. |
network | A pointer to the instance of the ie_network_t to get input shapes. |
shapes | A pointer to the input_shapes. |
network | A pointer to the instance of the ie_network_t to reshape. |
shapes | A new input shapes to set for the network. |
network | A pointer to the instance of the ie_network_t to get number of ouput information. |
size_result | A number of the network's output information. |
network | A pointer to theinstance of the ie_network_t to get output information. |
number | An id of output information . |
name | Output name corresponding to the number. |
network | A pointer to ie_network_t instance. |
output_name | Name of output data. |
prec_result | A pointer to the precision used for output blob creation. |
network | A pointer to ie_network_t instance. |
output_name | Name of output data. |
p | A new precision of the output data to set (eg. precision_e.FP16). |
network | A pointer to ie_network_t instance. |
output_name | Name of output data. |
layout_result | A pointer to the layout used for output blob creation. |
network | A pointer to ie_network_t instance. |
output_name | Name of output data. |
l | A new layout of the output data to set. |
network | A pointer to ie_network_t instance. |
output_name | Name of output data. |
dims_result | A pointer to the dimensions used for output blob creation. |
inputShapes | A pointer to the input_shapes to free memory. |
name | A pointer to the input_name or output_name to free memory. |
tensorDesc | Tensor descriptor for Blob creation. |
blob | A pointer to the newly created blob. |
tensorDesc | Tensor descriptor for Blob creation. |
ptr | Pointer to the pre-allocated memory. |
size | Length of the pre-allocated array. |
blob | A pointer to the newly created blob. |
inputBlob | original blob with pre-allocated memory. |
roi | A roi_tinstance inside of the original blob. |
blob | A pointer to the newly created blob. |
y | A pointer to the ie_blob_t instance that represents Y plane in NV12 color format. |
uv | A pointer to the ie_blob_t instance that represents UV plane in NV12 color format. |
nv12Blob | A pointer to the newly created blob. |
y | A pointer to the ie_blob_t instance that represents Y plane in I420 color format. |
u | A pointer to the ie_blob_t instance that represents U plane in I420 color format. |
v | A pointer to the ie_blob_t instance that represents V plane in I420 color format. |
i420Blob | A pointer to the newly created blob. |
blob | A pointer to the blob. |
size_result | The total number of elements. |
blob | A pointer to the blob. |
bsize_result | The size of the current blob in bytes. |
blob | A pointer to the blob to free memory. |
blob | A pointer to the blob. |
blob_buffer | A pointer to the copied data from the given blob. |
blob | A pointer to the blob. |
blob_cbuffer | A pointer to the coped data from the given pointer to the blob and the data is read-only. |
blob | A pointer to the blob. |
dims_result | A pointer to the dimensions of blob's tensor. |
blob | A pointer to the blob. |
layout_result | A pointer to the layout of blob's tensor. |
blob | A pointer to the blob. |
prec_result | A pointer to the precision of blob's tensor. |
@Releases the memory occupied by the ie_blob_t pointer.
blob | A pointer to the blob pointer to release memory. |