create_deep_counting_modelT_create_deep_counting_modelCreateDeepCountingModelCreateDeepCountingModelcreate_deep_counting_model (算子)
名称
create_deep_counting_modelT_create_deep_counting_modelCreateDeepCountingModelCreateDeepCountingModelcreate_deep_counting_model — 创建用于计数对象的深度计数模型。
签名
void CreateDeepCountingModel(const HTuple& GenParamName, const HTuple& GenParamValue, HTuple* DeepCountingHandle)
void HDlModelCounting::HDlModelCounting(const HTuple& GenParamName, const HTuple& GenParamValue)
void HDlModelCounting::HDlModelCounting(const HString& GenParamName, double GenParamValue)
void HDlModelCounting::HDlModelCounting(const char* GenParamName, double GenParamValue)
void HDlModelCounting::HDlModelCounting(const wchar_t* GenParamName, double GenParamValue)
(
Windows only)
void HDlModelCounting::CreateDeepCountingModel(const HTuple& GenParamName, const HTuple& GenParamValue)
void HDlModelCounting::CreateDeepCountingModel(const HString& GenParamName, double GenParamValue)
void HDlModelCounting::CreateDeepCountingModel(const char* GenParamName, double GenParamValue)
void HDlModelCounting::CreateDeepCountingModel(const wchar_t* GenParamName, double GenParamValue)
(
Windows only)
描述
create_deep_counting_modelcreate_deep_counting_modelCreateDeepCountingModelCreateDeepCountingModelCreateDeepCountingModelcreate_deep_counting_model creates a Deep Counting model and returns
its handle in DeepCountingHandleDeepCountingHandleDeepCountingHandleDeepCountingHandledeepCountingHandledeep_counting_handle。
Internally create_deep_counting_modelcreate_deep_counting_modelCreateDeepCountingModelCreateDeepCountingModelCreateDeepCountingModelcreate_deep_counting_model builds a backbone based on
the pretrained network 'pretrained_dl_classifier_resnet50.hdl'"pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl",
which must be available.
See read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model for details on where the file is searched.
Additional parameters of the Deep Counting model can be set using the
generic parameters GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name and GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value.
See get_deep_counting_model_paramget_deep_counting_model_paramGetDeepCountingModelParamGetDeepCountingModelParamGetDeepCountingModelParamget_deep_counting_model_param for a list of parameters and their
possible values. The parameters can either be set during model creation,
or later using set_deep_counting_model_paramset_deep_counting_model_paramSetDeepCountingModelParamSetDeepCountingModelParamSetDeepCountingModelParamset_deep_counting_model_param。
Note that before using the returned Deep Counting model with
apply_deep_counting_modelapply_deep_counting_modelApplyDeepCountingModelApplyDeepCountingModelApplyDeepCountingModelapply_deep_counting_model, templates must be stored in the model
using prepare_deep_counting_modelprepare_deep_counting_modelPrepareDeepCountingModelPrepareDeepCountingModelPrepareDeepCountingModelprepare_deep_counting_model。
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*)
Parameter names.
默认值：
[]
值列表：
'angle_end'"angle_end""angle_end""angle_end""angle_end""angle_end", 'angle_start'"angle_start""angle_start""angle_start""angle_start""angle_start", 'angle_step'"angle_step""angle_step""angle_step""angle_step""angle_step", 'device'"device""device""device""device""device", 'max_overlap'"max_overlap""max_overlap""max_overlap""max_overlap""max_overlap", 'min_score'"min_score""min_score""min_score""min_score""min_score", 'scale_max'"scale_max""scale_max""scale_max""scale_max""scale_max", 'scale_min'"scale_min""scale_min""scale_min""scale_min""scale_min", 'scale_step'"scale_step""scale_step""scale_step""scale_step""scale_step"
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (输入控制) attribute.value(-array) → HTupleMaybeSequence[Union[float, int, str]]HTupleHtuple (real / integer / string) (double / int / long / string) (double / Hlong / HString) (double / Hlong / char*)
Parameter values.
默认值：
[]
DeepCountingHandleDeepCountingHandleDeepCountingHandleDeepCountingHandledeepCountingHandledeep_counting_handle (输出控制) deep_counting → HDlModelCounting, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Deep Counting model for counting objects.
结果
如果参数有效，算子 create_deep_counting_modelcreate_deep_counting_modelCreateDeepCountingModelCreateDeepCountingModelCreateDeepCountingModelcreate_deep_counting_model 返回值 2 ( H_MSG_TRUE )。如有必要，则抛出异常。
可能的后继
set_deep_counting_model_paramset_deep_counting_model_paramSetDeepCountingModelParamSetDeepCountingModelParamSetDeepCountingModelParamset_deep_counting_model_param,
get_deep_counting_model_paramget_deep_counting_model_paramGetDeepCountingModelParamGetDeepCountingModelParamGetDeepCountingModelParamget_deep_counting_model_param,
prepare_deep_counting_modelprepare_deep_counting_modelPrepareDeepCountingModelPrepareDeepCountingModelPrepareDeepCountingModelprepare_deep_counting_model,
apply_deep_counting_modelapply_deep_counting_modelApplyDeepCountingModelApplyDeepCountingModelApplyDeepCountingModelapply_deep_counting_model
替代
read_deep_counting_modelread_deep_counting_modelReadDeepCountingModelReadDeepCountingModelReadDeepCountingModelread_deep_counting_model
另见
get_deep_counting_model_paramget_deep_counting_model_paramGetDeepCountingModelParamGetDeepCountingModelParamGetDeepCountingModelParamget_deep_counting_model_param
模块
匹配