query_available_dl_devicesT_query_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices（算子）
名称
query_available_dl_devicesT_query_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices — 获取支持深度学习的硬件设备列表。
签名
描述
query_available_dl_devicesquery_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices returns a list of handles. Each
handle refers to a deep-learning-capable hardware device
(hereafter referred to as device) that can be
used for inference or training of a deep learning model. For each
returned device, every parameter mentioned in GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name
must be equal to at least one of its corresponding values that appear
in GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value. A parameter can have more than one value
by duplicating its name in GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name and adding different
corresponding value in GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value。
A deep-learning-capable device is either supported directly
through HALCON or through an AI
2-interface.
The devices that are supported directly through HALCON are equivalent
to those that can be set to a deep learning model via
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param using 'runtime'"runtime""runtime""runtime""runtime""runtime" = 'cpu'"cpu""cpu""cpu""cpu""cpu" 或
'runtime'"runtime""runtime""runtime""runtime""runtime" = 'gpu'"gpu""gpu""gpu""gpu""gpu". HALCON provides an internal
implementation for the inference or training of a deep learning model
for those devices. See 深度学习 for more details.
Devices that are supported through the AI
2-interface
can also be set to a deep learning model using set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param。In this case the inference is not executed by HALCON but by the device
itself.
query_available_dl_devicesquery_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices returns a handle for each
deep-learning-capable device supported through HALCON and through an
inference engine.
If a device is supported through HALCON and one or several inference
engines, query_available_dl_devicesquery_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices returns a handle for HALCON
and for each inference engine.
GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name can be used to filter for the devices.
All GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name that are gettable by get_dl_device_paramget_dl_device_paramGetDlDeviceParamGetDlDeviceParamGetDlDeviceParamget_dl_device_param
and that do not return a handle-typed value for GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value
are supported for filtering. See the operator reference of
get_dl_device_paramget_dl_device_paramGetDlDeviceParamGetDlDeviceParamGetDlDeviceParamget_dl_device_param for the list of gettable parameters.
In addition, the following values are supported:
- 'runtime'"runtime""runtime""runtime""runtime""runtime"：
-
The devices, which are directly supported by
HALCON for this device type.
Possible values (standard):
'cpu'"cpu""cpu""cpu""cpu""cpu", 'gpu'"gpu""gpu""gpu""gpu""gpu".
GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name can have multiple entries for the same value.
In this case filter combines the entries with a logical 'or'.
Please see the example code below for some examples how to use the
filter.
执行信息
- 多线程类型：可重入（与非独占算子并行运行）。
- 多线程作用域：全局（可从任何线程调用）。
- 未采用并行化处理。
此算子返回一个句柄。请注意，即使该句柄被用作特定算子的输入参数，这些算子仍可能改变此句柄类型的实例状态。
参数
GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (输入控制) attribute.name(-array) → HTupleMaybeSequence[str]HTupleHtuple (string) (string) (HString) (char*)
泛型参数的名称。
默认值：
[]
值列表：
'ai_accelerator_interface'"ai_accelerator_interface""ai_accelerator_interface""ai_accelerator_interface""ai_accelerator_interface""ai_accelerator_interface", 'calibration_precisions'"calibration_precisions""calibration_precisions""calibration_precisions""calibration_precisions""calibration_precisions", 'cast_precisions'"cast_precisions""cast_precisions""cast_precisions""cast_precisions""cast_precisions", 'conversion_supported'"conversion_supported""conversion_supported""conversion_supported""conversion_supported""conversion_supported", 'id'"id""id""id""id""id", 'inference_only'"inference_only""inference_only""inference_only""inference_only""inference_only", 'name'"name""name""name""name""name", 'optimize_for_inference_params'"optimize_for_inference_params""optimize_for_inference_params""optimize_for_inference_params""optimize_for_inference_params""optimize_for_inference_params", 'precisions'"precisions""precisions""precisions""precisions""precisions", 'runtime'"runtime""runtime""runtime""runtime""runtime", 'settable_device_params'"settable_device_params""settable_device_params""settable_device_params""settable_device_params""settable_device_params", 'type'"type""type""type""type""type"
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (输入控制) attribute.value(-array) → HTupleMaybeSequence[Union[int, float, str]]HTupleHtuple (string / integer / real) (string / int / long / double) (HString / Hlong / double) (char* / Hlong / double)
Value of the generic parameter.
默认值：
[]
建议值：
DLDeviceHandlesDLDeviceHandlesDLDeviceHandlesDLDeviceHandlesDLDeviceHandlesdldevice_handles (输出控制) dl_device(-array) → HDlDevice, HTupleSequence[HHandle]HTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Tuple of DLDevice handles
示例（HDevelop）
* Query all deep-learning-capable hardware devices
query_available_dl_devices ([], [], DLDeviceHandles)
* Query all GPUs with ID 0 or 2
query_available_dl_devices (['type', 'id', 'id'], ['gpu', 0, 2],\
DLDeviceHandles)
* Query the unique GPU with ID 1 supported by HALCON
query_available_dl_devices (['runtime', 'id'], ['gpu', 1], DLDeviceHandles)
结果
如果参数有效，算子
query_available_dl_devicesquery_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices 返回值 2 (H_MSG_TRUE)。如有必要，则抛出异常。
可能的后继
get_dl_device_paramget_dl_device_paramGetDlDeviceParamGetDlDeviceParamGetDlDeviceParamget_dl_device_param
模块
基础