get_dl_classifier_paramT_get_dl_classifier_paramGetDlClassifierParamGetDlClassifierParamget_dl_classifier_param (算子)
名称
get_dl_classifier_paramT_get_dl_classifier_paramGetDlClassifierParamGetDlClassifierParamget_dl_classifier_param — 返回基于深度学习的分类器的参数。
警告
get_dl_classifier_paramget_dl_classifier_paramGetDlClassifierParamGetDlClassifierParamGetDlClassifierParamget_dl_classifier_param 已过时，仅出于向后兼容性考虑而保留。 New applications should use common
CNN-based operator get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param instead.
签名
描述
get_dl_classifier_paramget_dl_classifier_paramGetDlClassifierParamGetDlClassifierParamGetDlClassifierParamget_dl_classifier_param returns the parameter values
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value of GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name of the neural
network DLClassifierHandleDLClassifierHandleDLClassifierHandleDLClassifierHandleDLClassifierHandledlclassifier_handle。
The hyperparameters and network parameters can be set with the operator
set_dl_classifier_paramset_dl_classifier_paramSetDlClassifierParamSetDlClassifierParamSetDlClassifierParamset_dl_classifier_param, in whose reference entry they are described
in detail. With get_dl_classifier_paramget_dl_classifier_paramGetDlClassifierParamGetDlClassifierParamGetDlClassifierParamget_dl_classifier_param you can query all these
values.
Additionally, there are parameters defined by the network which are
read-only. These parameters are:
- 'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min"：
Minimum gray value.
- 'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max"：
-
Maximum gray value.
The precise values for these parameters and the default parameters for the
image dimension depend on the concrete network, see
read_dl_classifierread_dl_classifierReadDlClassifierReadDlClassifierReadDlClassifierread_dl_classifier。
Every image that is fed into the network must be present according to the
parameters defining the image properties.
To preprocess images accordingly, the procedure
preprocess_dl_classifier_images is available.
有关基于深度学习的分类概念的说明，请参阅 深度学习 / 分类 一章的引言。涉及此遗留算子的工作流在
遗留 / 深度学习分类 一章中有详细说明。
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。
参数
DLClassifierHandleDLClassifierHandleDLClassifierHandleDLClassifierHandleDLClassifierHandledlclassifier_handle (输入控制) dl_classifier → HDlClassifier, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
基于深度学习分类器的句柄。
GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (输入控制) attribute.name(-array) → HTupleMaybeSequence[str]HTupleHtuple (string) (string) (HString) (char*)
Name of the generic parameter.
默认值：
'gpu'
"gpu"
"gpu"
"gpu"
"gpu"
"gpu"
值列表：
'batch_size'"batch_size""batch_size""batch_size""batch_size""batch_size", 'batch_size_multiplier'"batch_size_multiplier""batch_size_multiplier""batch_size_multiplier""batch_size_multiplier""batch_size_multiplier", 'classes'"classes""classes""classes""classes""classes", 'gpu'"gpu""gpu""gpu""gpu""gpu", 'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions""image_dimensions", 'image_height'"image_height""image_height""image_height""image_height""image_height", 'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels", 'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max", 'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min", 'image_width'"image_width""image_width""image_width""image_width""image_width", 'learning_rate'"learning_rate""learning_rate""learning_rate""learning_rate""learning_rate", 'momentum'"momentum""momentum""momentum""momentum""momentum", 'runtime'"runtime""runtime""runtime""runtime""runtime", 'runtime_init'"runtime_init""runtime_init""runtime_init""runtime_init""runtime_init", 'weight_prior'"weight_prior""weight_prior""weight_prior""weight_prior""weight_prior"
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (输出控制) attribute.name(-array) → HTupleSequence[Union[str, float, int]]HTupleHtuple (integer / string / real) (int / long / string / double) (Hlong / HString / double) (Hlong / char* / double)
Value of the generic parameter.
结果
如果参数有效，算子 get_dl_classifier_paramget_dl_classifier_paramGetDlClassifierParamGetDlClassifierParamGetDlClassifierParamget_dl_classifier_param 返回值 2 ( H_MSG_TRUE )。如有必要，则抛出异常。
可能的前趋
read_dl_classifierread_dl_classifierReadDlClassifierReadDlClassifierReadDlClassifierread_dl_classifier,
set_dl_classifier_paramset_dl_classifier_paramSetDlClassifierParamSetDlClassifierParamSetDlClassifierParamset_dl_classifier_param
可能的后继
train_dl_classifier_batchtrain_dl_classifier_batchTrainDlClassifierBatchTrainDlClassifierBatchTrainDlClassifierBatchtrain_dl_classifier_batch,
apply_dl_classifierapply_dl_classifierApplyDlClassifierApplyDlClassifierApplyDlClassifierapply_dl_classifier
替代
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param
另见
set_dl_classifier_paramset_dl_classifier_paramSetDlClassifierParamSetDlClassifierParamSetDlClassifierParamset_dl_classifier_param
模块
深度学习推理