Filters
Filter values by
Classification object
  • Classifier context - predefined CNN
  • Classifier context - tree ensemble
  • Dataset context - images
  • Dataset context - features
  • Training context - CNN
  • Training context - tree ensemble
| Customize Help
| Save Settings

MclassInquire


Function Map
Syntax
Description
Parameters
- ContextOrResultClassId
Table: For specifying the classification context
- LabelOrIndex
Table: For specifying what to inquire
- InquireType
- UserVarPtr
Parameter Associations
Table: For a classifier context (predefined CNN)
Table: For a classifier context's source layer (predefined CNN)
Table: For a classifier context (tree ensemble)
Table: For a classifier context (predefined CNN or tree ensemble)
Table: For a dataset context (images or a features)
Table: For a class definition in a classifier or dataset context (any)
Table: For a training context (CNN)
Table: For a training context (tree ensemble)
Table: For a training context (CNN or tree ensemble)
Table: For a classifier or training context (CNN or tree ensemble)
Table: For any supported context
+ combination: For inquiring the size of a string
+ combination: For inquiring the default value of an inquire type
+ combination: For inquiring whether an inquire type is supported
+ combination: For specifying the data type
Return value
Compilation information
Synopsis
Inquire about a classifier context, a dataset context, a training context, class definitions, or the source layer of a predefined CNN.
Syntax
MIL_INT MclassInquire(
MIL_ID ContextOrResultClassId, //in
MIL_INT64 LabelOrIndex, //in
MIL_INT64 InquireType, //in
void *UserVarPtr //out
)
Description

This function inquires about a setting of a classifier context, a dataset context, a training context, class definitions, or the source layer of a predefined CNN. Note, class definitions are held in dataset and classifier contexts.

If the inquired setting is set to M_DEFAULT (for example, using MclassControl()), MclassInquire() will return M_DEFAULT. To inquire the actual default value, add M_DEFAULT to the InquireType parameter.

Note that this function reference has not been updated for a MIL system added during a MIL update. Refer to the MIL system's release note to see which MIL system’s documentation you should use in its place and any possible differences.
Parameters
This function is not supported on the selected boards.
This function reference has not been updated for the selected MIL system. To show the content of this page, choose a second MIL system; refer to the MIL system's release note to see which MIL system’s documentation to choose and any possible differences.
Parameters
ContextOrResultClassId

Specifies the identifier of the classification context about which to inquire.

function map For specifying the classification context
Click to summarizeValue Description
Click to summarize ContextClassifierId

Specifies the identifier of a predefined CNN or tree ensemble classifier context. These contexts must have been previously allocated on the required system using MclassAlloc() with M_CLASSIFIER_CNN_PREDEFINED or M_CLASSIFIER_TREE_ENSEMBLE.

(summarize)
Click to summarize ContextDatasetId

Specifies the identifier of an images or features dataset context. These contexts must have been previously allocated on the required system using MclassAlloc() with M_DATASET_IMAGES or M_DATASET_FEATURES.

(summarize)
Click to summarize ContextTrainId

Specifies the identifier of a CNN or tree ensemble training context. These contexts must have been previously allocated on the required system using MclassAlloc() with M_TRAIN_CNN or M_TRAIN_TREE_ENSEMBLE.

(summarize)
LabelOrIndex

Specifies what to inquire. This parameter can be set to one of the following values:

function map For specifying what to inquire
Click to summarizeValue Description
Click to summarize M_DEFAULT

Same as M_CONTEXT.
Click to summarize

Specifies the author (in the dataset) about which to inquire.

(summarize)
Parameters

Set this parameter to the following:
0 <= Value < M_NUMBER_OF_AUTHORS

Specifies the index of the author. You can inquire the total number of authors, using M_NUMBER_OF_AUTHORS.
Click to summarize

Specifies the class definition about which to inquire.

(summarize)
Parameters

Set this parameter to the following:
0 <= Value < M_NUMBER_OF_CLASSES

Specifies the index. If you inquire about a class definition that you did not explicitly control, you will not get back any information, but there will be no error.
Click to summarize M_CONTEXT

Specifies to inquire about a global setting of a classification context.
Click to summarize M_DEFAULT_SOURCE_LAYER

Specifies to inquire about the input (initial) layer of the CNN in a classification context. In this case, you must set the ContextOrResultClassId parameter to the identifier of a predefined CNN classifier.

(summarize)
InquireType

Specifies the type of setting about which to inquire.

See the Parameter associations section for possible values that can be specified.

UserVarPtr
Accepts the address of one of the following (see the Parameter associations section for specifics on which is expected):
  • array of type MIL_DOUBLE [optionally, in C++: a reference to a std::vector<MIL_DOUBLE> ]
  • array of type MIL_ID [optionally, in C++: a reference to a std::vector<MIL_ID> ]
  • array of type MIL_INT [optionally, in C++: a reference to a std::vector<MIL_INT> ]
  • array of type MIL_INT32 [optionally, in C++: a reference to a std::vector<MIL_INT32> ]
  • array of type MIL_INT64 [optionally, in C++: a reference to a std::vector<MIL_INT64> ]
  • array of type MIL_TEXT_CHAR [optionally, in C++: a reference to a MIL_STRING]
  • MIL_DOUBLE
  • MIL_ID
  • MIL_INT
  • MIL_INT32
  • MIL_INT64
  • MIL_UUID

Specifies the address in which to write the requested information. Since the MclassInquire() function also returns the requested information, you can set this parameter to M_NULL.

See the Parameter associations section for possible values that can be returned.

Parameter associations

The tables below list possible values for the InquireType parameter and possible values returned to the UserVarPtr parameter.

To inquire about a global setting of a predefined CNN classifier context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a predefined CNN classifier context, and set the LabelOrIndex parameter to M_CONTEXT.

function map For a classifier context (predefined CNN)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_CLASSIFIER_CNN_PREDEFINED_TYPE +

Inquires the type of predefined CNN classifier context that you are using. These contexts are built by Matrox. The type of predefined CNN classifier context that you are using is typically specified when you call MclassAlloc() with M_CLASSIFIER_CNN_PREDEFINED.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_CUSTOM

Specifies a custom classifier context. M_CLASSIFIER_CNN_PREDEFINED_TYPE can only return M_CUSTOM if you contacted Matrox and received a classifier context that was customized for you.

(summarize)
Click to summarize M_FCNET_COLOR_XL

Specifies an extra large FCNET classifier context that is intended for color images.
Click to summarize M_FCNET_M

Specifies a medium FCNET classifier context.
Click to summarize M_FCNET_MONO_XL

Specifies an extra large FCNET classifier context that is intended for monochrome images.
Click to summarize M_FCNET_S

Specifies a small FCNET classifier context.
Click to summarize M_FCNET_XL

Specifies an extra large FCNET classifier context.
Click to summarize M_UNDEFINED

Specifies an undefined classifier context. M_UNDEFINED is returned if you allocate a predefined CNN classifier context (M_CLASSIFIER_CNN_PREDEFINED) without specifying a specific one (for example, M_FCNET_M).

If your classifier context is undefined, and you copy the result of a trained classifier context into it, the type of that undefined context is modified according to the type of the context copied into it. For example, if you copy an M_FCNET_M context into an undefined classifier context, that context's classifier type is now also M_FCNET_M.

(summarize)
Click to summarize M_EXPIRY_DATE_STRING +

Inquires the expiration date of the context in string format. The date returned is formatted as follow: "2999-12-31 23:59:59".

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: array of type MIL_TEXT_CHAR [optionally, in C++: MIL_STRING ] MORE
Click to summarize MIL_TEXT("2999-12-31 23:59:59") 1

Specifies the expiration date, if there is one.

MIL returns the date as a regular string, consisting of all characters including the terminating null character. The date in the string is organized as follows: YYYY-MM-DD HH:MM:SS , where YYYY refers to the year, MM refers to the month, DD refers to the day, HH refers to the hour, MM refers to the minute, and SS refers to the second. An example of an expiration date that MIL might one day return is: "2999-12-31 23:59:59\0".

(summarize)
Click to summarize MIL_TEXT("None") 1

Specifies that there is no expiration date.
Click to summarize M_TARGET_IMAGE_SIZE_X +

Inquires the size of the image input to MclassPredict(). If equal to 0 (default value), the preprocessing assumes the size of the target image is the same as the default source layer, M_SIZE_X. M_TARGET_IMAGE_SIZE_X and M_TARGET_IMAGE_SIZE_Y are paired: both must be equal to 0, or both must be greater or equal to M_SIZE_X and M_SIZE_Y, respectively. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 0. INFO
Click to summarize Value >= 0

Specifies the X-size.
Click to summarize M_TARGET_IMAGE_SIZE_Y +

Inquires the size of the image input to MclassPredict(). If equal to 0 (default value), the preprocessing assumes the size of the target image is the same as the default source layer, M_SIZE_Y. M_TARGET_IMAGE_SIZE_X and M_TARGET_IMAGE_SIZE_Y are paired: both must be equal to 0, or both must be greater or equal to M_SIZE_X and M_SIZE_Y, respectively. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 0. INFO
Click to summarize Value >= 0

Specifies the Y-size.
Click to summarize M_TRAINABLE_COMPLETE +

Inquires whether you can perform a complete type of training on the context.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FALSE

Specifies that you cannot perform a complete training. That is, you cannot set M_RESET_TRAINING_VALUES to M_COMPLETE.

(summarize)
Click to summarize M_TRUE

Specifies that you can perform a complete training. That is, you can set M_RESET_TRAINING_VALUES to M_COMPLETE.

(summarize)
Click to summarize M_TRAINABLE_FINE_TUNING +

Inquires whether you can perform a fine tuning type of training on the context.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FALSE

Specifies that you cannot perform a fine tuning type of training. That is, you cannot set M_RESET_TRAINING_VALUES to M_FINE_TUNING.

(summarize)
Click to summarize M_TRUE

Specifies that you can perform a fine tuning type of training. That is, you can set M_RESET_TRAINING_VALUES to M_FINE_TUNING.

(summarize)
Click to summarize M_TRAINABLE_TRANSFER_LEARNING +

Inquires whether you can perform a transfer learning type of training on the context.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FALSE

Specifies that you cannot perform a transfer learning type of training. That is, you cannot set M_RESET_TRAINING_VALUES to M_TRANSFER_LEARNING.

(summarize)
Click to summarize M_TRUE

Specifies that you can perform a transfer learning type of training. That is, you can set M_RESET_TRAINING_VALUES to M_TRANSFER_LEARNING.

(summarize)

1 If the value was passed in a variable, it won't be returned enclosed in MIL_TEXT().

To inquire about the source layer of the classifier in a predefined CNN classifier context, the InquireType parameter can be set to one of the following values. In this case, set the LabelOrIndex parameter to M_DEFAULT_SOURCE_LAYER.

function map For a classifier context's source layer (predefined CNN)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_BAND_ORDER +

Inquires the order of the input bands of the CNN. This corresponds to the order in which the network interpreted the bands of the images that were used in the training phase. If the bands in the target image (MclassPredict()) do not follow this order, MIL internally compensates by temporarily copying the bands to be the order that the network expects.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_RGB.
Click to summarize M_BGR

Specifies that the bands are ordered according to the BGR (Blue, Green, Red) convention.
Click to summarize M_RGB

Specifies that the bands are ordered according to the RGB (Red, Green, Blue) convention.
Click to summarize M_SIZE_BAND +

Inquires the number of input bands of the CNN. This corresponds to the number of bands of the images that were used in the training phase.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 1

Specifies the number of bands.
Click to summarize M_SIZE_X +

Inquires the width of the CNN's source layer. This corresponds to the width of the images that were used in the training phase.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 1

Specifies the width.
Click to summarize M_SIZE_Y +

Inquires the height of the CNN's source layer. This corresponds to the height of the images that were used in the training phase.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 1

Specifies the height.
Click to summarize M_STEP_X +

Inquires the appropriate increment, in the X-direction, of the target image size for prediction. Note the following calculation, to establish the target image's X-size: M_TARGET_IMAGE_SIZE_X = M_SIZE_X + m * M_STEP_X , where m is an integer that is greater than or equal to 0.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 1

Specifies the appropriate increment, in the X-direction.
Click to summarize M_STEP_Y +

Inquires the appropriate increment, in the Y-direction, of the target image size for prediction. Note the following calculation, to establish the target image's Y-size: M_TARGET_IMAGE_SIZE_Y = M_SIZE_Y + m * M_STEP_Y , where m is an integer that is greater than or equal to 0.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 1

Specifies the appropriate increment, in the X-direction.
Click to summarize M_TRAIN_IMAGE_MIN_SIZE_X +

Inquires the minimum image size, along the X-axis, required to train this context.

Valid image sizes are given by the following formulas (for X and Y), where k and j are integers greater than or equal to zero:

M_TRAIN_IMAGE_MIN_SIZE_X + k * M_TRAIN_IMAGE_STEP_X and M_TRAIN_IMAGE_MIN_SIZE_Y + j * M_TRAIN_IMAGE_STEP_Y .

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value > 0

Inquires the minimum image size, in the X-axis, required to train this context.
Click to summarize M_TRAIN_IMAGE_MIN_SIZE_Y +

Inquires the minimum image size, along the Y-axis, required to train this context.

Valid image sizes are given by the following formulas (for X and Y), where k and j are integers greater than or equal to zero:

M_TRAIN_IMAGE_MIN_SIZE_X + k * M_TRAIN_IMAGE_STEP_X and M_TRAIN_IMAGE_MIN_SIZE_Y + j * M_TRAIN_IMAGE_STEP_Y .

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value > 0

Inquires the minimum image size, in the Y-axis, required to train this context.
Click to summarize M_TRAIN_IMAGE_STEP_X +

Inquires the increment in image size, along the X-axis, to train this context.

Valid image sizes are given by the following formulas (for X and Y), where k and j are integers greater than or equal to zero:

M_TRAIN_IMAGE_MIN_SIZE_X + k * M_TRAIN_IMAGE_STEP_X and M_TRAIN_IMAGE_MIN_SIZE_Y + j * M_TRAIN_IMAGE_STEP_Y .

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Inquires the minimum image size, in the X-axis, required to train this context.
Click to summarize M_TRAIN_IMAGE_STEP_Y +

Inquires the increment in image size, along the Y-axis, to train this context.

Valid image sizes are given by the following formulas (for X and Y), where k and j are integers greater than or equal to zero:

M_TRAIN_IMAGE_MIN_SIZE_X + k * M_TRAIN_IMAGE_STEP_X and M_TRAIN_IMAGE_MIN_SIZE_Y + j * M_TRAIN_IMAGE_STEP_Y .

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Inquires the minimum image size, in the Y-axis, required to train this context.
Click to summarize M_TYPE +

Inquires the input type of the CNN. This corresponds to the data type and depth of the images that were used in the training phase (for example, M_UNSIGNED + 8).

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FLOAT + Depth value

Specifies the floating-point data type, along with the depth, in bits.
Click to summarize M_SIGNED + Depth value

Specifies the signed data type, along with the depth, in bits.
Click to summarize M_UNSIGNED + Depth value

Specifies the unsigned data type, along with the depth, in bits.

To inquire about a global setting of a tree ensemble classifier context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a tree ensemble classifier context and set the LabelOrIndex parameter to M_CONTEXT.

function map For a classifier context (tree ensemble)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_NUMBER_OF_FEATURES +

Inquires the number of features in Entries that are used to train the classifier.

Note that all Entries used for a predict must have exactly the number of features returned by this inquire.

You can only retrieve this value after calling MclassPreprocess().

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value > 0

Specifies the number of features used to train the classifier.

To inquire about a global setting of a predefined CNN or tree ensemble classifier context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a tree ensemble or predefined CNN classifier context and set the LabelOrIndex parameter to M_CONTEXT.

Note, these values apply to a predefined CNN or tree ensemble classifier context, unless otherwise specified.

function map For a classifier context (predefined CNN or tree ensemble)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_CLASSIFIER_STATUS +

Inquires the state of the classifier.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default state of the classifier.

For a predefined CNN classifier context, it is the same as M_UNDEFINED.

For a tree ensemble classifier context, it is the same as M_UNTRAINED.

(summarize)
Click to summarize M_PRETRAINED

Specifies a classifier that is trained by Matrox.

A classifier in this state can be used for MclassPredict() and MclassTrain().

Note that this state only occurs for predefined CNN classifier contexts.

(summarize)
Click to summarize M_UNDEFINED

Specifies an undefined classifier.

A predefined CNN classifier context is considered undefined if it was allocated but does not specify an FCNet classifier. You cannot train (or predict) with such a classifier.

Note that this state only occurs for predefined CNN classifier contexts.

(summarize)
Click to summarize M_UNTRAINED

Specifies a classifier that has not been trained yet.

A classifier in this state can be used for MclassTrain().

(summarize)
Click to summarize M_USER_TRAINED

Specifies a classifier that is trained by the user.

A classifier in this state can be used for MclassPredict() and MclassTrain().

(summarize)
Click to summarize M_NUMBER_OF_CLASSES +

Inquires the number of class definitions (classes).

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Specifies the number of classes.

To inquire about a dataset context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a dataset context, and set the LabelOrIndex parameter to M_CONTEXT, unless otherwise specified.

Note, these values apply to an images or a features dataset context, unless otherwise specified.

function map For a dataset context (images or a features)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_ACTIVE_AUTHOR_INDEX +

Inquires the author that is automatically added for labeling operations performed on a dataset. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_CURRENT_USER.
Click to summarize M_CURRENT_USER

Specifies the system's current username as the author that is automatically defined for each dataset entry. INFO
Click to summarize M_ACTIVE_AUTHOR_UPDATE +

Inquires the behavior of the entry's author after a modification was performed on the entry. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_ENABLE.
Click to summarize M_DISABLE

Specifies to keep the existing author's information.
Click to summarize M_ENABLE

Specifies that when an entry's information (an entry's region information) is modified, its author is automatically modified according to M_ACTIVE_AUTHOR_INDEX. INFO
Click to summarize M_AUTHOR_KEY +

Inquires the author's key (UUID). You must set the LabelOrIndex parameter to M_AUTHOR_INDEX().

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_UUID
Click to summarize MIL_UUID Value

Specifies the key of the author. The key is defined as a MIL universal unique identifier (UUID).

(summarize)
Click to summarize M_AUTHOR_NAME +

Inquires the name of an author in the dataset. You must set the LabelOrIndex parameter to M_AUTHOR_INDEX(). SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: array of type MIL_TEXT_CHAR [optionally, in C++: MIL_STRING ] MORE
Click to summarize MIL_TEXT("AuthorName") 1

Specifies the name of an author.
Click to summarize M_NUMBER_OF_AUGMENTED_ENTRIES +

Inquires the number of entries that are augmented.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Retrieves the number of augmented entries.
Click to summarize M_NUMBER_OF_AUTHORS +

Inquires the number of authors currently defined in the dataset.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Retrieves the number of authors.
Click to summarize M_NUMBER_OF_ENTRIES +

Inquires the number of entries defined in the dataset.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Retrieves the number of entries in the dataset.
Click to summarize M_NUMBER_OF_ENTRIES_GROUND_TRUTH +

Inquires the number of entries that have their ground truth specified (M_CLASS_INDEX_GROUND_TRUTH).

To inquire the number of entries for every class in the context, set the LabelOrIndex parameter to M_CONTEXT. To inquire the number of entries for a specific class in the context, set the LabelOrIndex parameter to that class using M_CLASS_INDEX().

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Retrieves the number of entries that have a ground truth.
Click to summarize M_NUMBER_OF_ENTRIES_PREDICTED +

Inquires the number of entries that have their predicted class specified (M_CLASS_INDEX_PREDICTED).

To inquire the number of entries for every class in the context, set the LabelOrIndex parameter to M_CONTEXT. To inquire the number of entries for a specific class in the context, set the LabelOrIndex parameter to that class using M_CLASS_INDEX().

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0

Retrieves the number of entries that have a predicted class.
Click to summarize M_PREDICTED_SCORE_AVERAGE +

Inquires the average predicted best score among the entries counted in M_NUMBER_OF_ENTRIES_PREDICTED.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0.0

Retrieves the average predicted score among the entries counted in M_NUMBER_OF_ENTRIES_PREDICTED.
Click to summarize M_PREDICTED_SCORE_MAX +

Inquires the maximum predicted best score among the entries counted in M_NUMBER_OF_ENTRIES_PREDICTED.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0.0

Retrieves the maximum predicted score among the entries counted in M_NUMBER_OF_ENTRIES_PREDICTED.
Click to summarize M_PREDICTED_SCORE_MIN +

Inquires the minimum predicted best score among the entries counted in M_NUMBER_OF_ENTRIES_PREDICTED.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value >= 0.0

Retrieves the minimum predicted score among the entries counted in M_NUMBER_OF_ENTRIES_PREDICTED.
Click to summarize M_ROOT_PATH +

Inquires the root file path, such that M_ROOT_PATH + M_FILE_PATH gives a valid path. If M_ROOT_PATH is empty, M_FILE_PATH should be an absolute path, otherwise it should be a relative path to M_ROOT_PATH.

This value only applies to an images dataset context. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: array of type MIL_TEXT_CHAR [optionally, in C++: MIL_STRING ] MORE

1 If the value was passed in a variable, it won't be returned enclosed in MIL_TEXT().

To inquire about a class definition in a classifier or dataset context, set the InquireType parameter to one of the values below. Unless otherwise specified, set the ContextOrResultClassId parameter to the identifier of any type of dataset or classifier context, and set the LabelOrIndex parameter to a specific class definition using M_CLASS_INDEX().

Note, these values apply to class definitions in a predefined CNN or tree ensemble classifier context, or in an images or features dataset context, unless otherwise specified.

function map For a class definition in a classifier or dataset context (any)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_CLASS_DRAW_COLOR +

Inquires the color assigned to a class definition. This color is used as a visual label. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE
Click to summarize Byte-encoded RGB value

Specifies an encoded RGB value. To verify if the value is a byte-encoded RGB value, use the M_IS_RGB888 macro. To retrieve the R, G, and B components, use the M_RGB888_R, M_RGB888_G, and M_RGB888_B macros.

(summarize)
Click to summarize M_CLASS_ICON_ID +

Inquires the identifier of the image associated to the specified class definition. The identifier returned is not the same as the one supplied using MclassControl() with M_CLASS_ICON_ID. MIL copies that image to the context and assigns it a new identifier, which is returned here. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_NULL

Specifies that the image associated with the class definition is freed.

Note that if the specified class definition does not have an associated image, this setting has no effect.

(summarize)
Click to summarize MIL image identifier

Specifies the identifier of the image buffer that MIL associates to the class definition.
Click to summarize M_CLASS_KEY +

Inquires the UUID (key), which is to be used to link between datasets, class labels, and a context class definition.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_UUID
Click to summarize MIL_UUID Value

Specifies the unique identifier of the class definition.
Click to summarize M_CLASS_NAME +

Inquires the name of a class definition. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: array of type MIL_TEXT_CHAR [optionally, in C++: MIL_STRING ] MORE
Click to summarize MIL_TEXT("ClassDefinitionName") 1

Retrieves the name of a class definition.
Click to summarize M_CLASS_WEIGHT +

Inquires the class definition's weight. M_CLASS_WEIGHT can only have an effect if M_CLASS_WEIGHT_MODE is set to M_USER_DEFINED).

Note that this inquire is only supported for a features dataset context or a tree ensemble classifier context. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 1.0.
Click to summarize Value >= 0.0

Specifies the weight.

1 If the value was passed in a variable, it won't be returned enclosed in MIL_TEXT().

To inquire about a global setting of a CNN training context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a CNN training context, and set the LabelOrIndex parameter to M_CONTEXT.

function map For a training context (CNN)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_CNN_TRAIN_ENGINE +

Inquires the engine (processing unit) that MIL uses to perform the training process. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_AUTO.
Click to summarize M_AUTO

Specifies the engine automatically. INFO
Click to summarize M_CPU

Specifies the CPU.
Click to summarize M_GPU

Specifies the GPU.
Click to summarize M_CNN_TRAIN_ENGINE_IS_INSTALLED +

Inquires whether a TrainDll is installed.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FALSE

Specifies that a TrainDll is not installed.
Click to summarize M_TRUE

Specifies that a TrainDll is installed.
Click to summarize M_CNN_TRAIN_ENGINE_USED +

Inquires which train engine is used. The context must be preprocessed.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_CPU

Specifies that a CPU is used as the train engine.
Click to summarize M_GPU

Specifies that a GPU is used as the train engine.
Click to summarize M_CNN_TRAIN_ENGINE_USED_DESCRIPTION +

Inquires the description of the engine (device) on which training is done (M_CNN_TRAIN_ENGINE_USED). To inquire this information, the context must be preprocessed.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: array of type MIL_TEXT_CHAR [optionally, in C++: MIL_STRING ] MORE
Click to summarize MIL_TEXT("TrainingDeviceName") 1

Specifies the description of the engine. Examples of descriptions you can retrieve are "GeForce RTX (tm) 2060 6GB" and "Intel(R) Core(TM) i7-8700 CPU 3.20GHZ".

(summarize)
Click to summarize M_CPU_TRAIN_ENGINE_LOAD_STATUS +

Inquires the status of the CPU train engine. This information can help you detect issues related to training with the CPU. M_CPU_TRAIN_ENGINE_LOAD_STATUS is only available if M_CNN_TRAIN_ENGINE is set to M_CPU, or if it is set to M_AUTO or M_DEFAULT and MIL selected the CPU.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FAILURE

Specifies that an unknown error occurred while trying to load the CPU train engine.
Click to summarize M_SUCCESS

Specifies that the CPU train engine loaded successfully (no issues were detected) and is ready for training.
Click to summarize M_UNABLE_TO_FIND_CPU_TRAIN_ENGINE

Specifies that the CPU train engine was not found.
Click to summarize M_UNABLE_TO_LOAD_CPU_TRAIN_ENGINE

Specifies that the CPU train engine was not loaded.
Click to summarize M_GPU_TRAIN_ENGINE_LOAD_STATUS +

Inquires the status of the GPU train engine. This information can help you detect issues related to training with the GPU. M_GPU_TRAIN_ENGINE_LOAD_STATUS is only available if M_CNN_TRAIN_ENGINE is set to M_GPU, or if it is set to M_AUTO or M_DEFAULT and MIL selected the GPU.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_CUDA_FAIL

Specifies that an unknown error occurred with CUDA.
Click to summarize M_FAILURE

Specifies that an unknown error occurred while trying to load the GPU train engine.
Click to summarize M_JIT_COMPILATION_REQUIRED

Specifies that the GPU has a major compute capability that is higher than the train engine. There could be a delay before the training starts.

(summarize)
Click to summarize M_JIT_COMPILER_NOT_FOUND

Specifies that a JIT compiler was not found. A JIT compilation is required; verify that the proper Nvidia drivers are installed.

(summarize)
Click to summarize M_SUCCESS

Specifies that the GPU train engine loaded successfully (no issues were detected) and is ready for training.
Click to summarize M_UNABLE_TO_FIND_GPU_TRAIN_ENGINE

Specifies that the GPU train engine was not found.
Click to summarize M_UNABLE_TO_FIND_VALID_GPU

Specifies that an Nvidia GPU was not found, or that the GPU's major compute capability is lower than 3.
Click to summarize M_UNABLE_TO_LOAD_GPU_TRAIN_ENGINE

Specifies that the GPU train engine was not loaded.
Click to summarize M_INITIAL_LEARNING_RATE +

Inquires the initial learning rate of training. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 0.005.
Click to summarize Value > 0.0

Specifies the learning rate.
Click to summarize M_LATEST_USED_RESET_TRAINING_VALUES +

Inquires the latest value passed to M_RESET_TRAINING_VALUES.

Note that this inquire does not indicate if any of the values set by M_RESET_TRAINING_VALUES have been changed since the last call with M_RESET_TRAINING_VALUES. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_COMPLETE.
Click to summarize M_COMPLETE

Specifies a complete training mode. INFO
Click to summarize M_FINE_TUNING

Specifies a fine tuning training mode. INFO
Click to summarize M_TRANSFER_LEARNING

Specifies a transfer learning mode. INFO
Click to summarize M_LEARNING_RATE_DECAY +

Inquires the learning rate decay of training. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 0.1.
Click to summarize Value > 0.0

Specifies the learning rate decay.
Click to summarize M_MAX_EPOCH +

Inquires the maximum number of epochs. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 60.
Click to summarize Value >= 0

Specifies the maximum number.
Click to summarize M_MINI_BATCH_SIZE +

Inquires the size of each mini-batch. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 32.
Click to summarize Value > 0

Specifies the size.
Click to summarize M_SCHEDULER_TYPE +

Inquires the scheduler type. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_CYCLICAL_DECAY.
Click to summarize M_CYCLICAL_DECAY

Specifies to decay the learning rate at an internally established cyclical schedule.
Click to summarize M_DECAY

Specifies to decay the learning rate, as weights are updated.

1 If the value was passed in a variable, it won't be returned enclosed in MIL_TEXT().

To inquire about a global setting of a tree ensemble training context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a tree ensemble training context, and set the LabelOrIndex parameter to M_CONTEXT.

function map For a training context (tree ensemble)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_BOOTSTRAP +

Inquires whether to use the bootstrap samples when building trees. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_WITH_REPLACEMENT.
Click to summarize M_DISABLE

Specifies not to use bootstrap aggregation.
Click to summarize M_WITH_REPLACEMENT

Specifies to use bootstrap aggregation, and allow replacement (chosen entries in a training set can be chosen again).
Click to summarize M_WITHOUT_REPLACEMENT

Specifies to use bootstrap aggregation, and not allow replacement (chosen entries in a training set cannot be chosen again).
Click to summarize M_CLASS_WEIGHT_MODE +

Inquires how to establish the weight of a class definition. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_NONE.
Click to summarize M_BALANCE

Specifies a balanced weight.
Click to summarize M_NONE

Specifies no weight.
Click to summarize M_USER_DEFINED

Specifies to use the weight defined with M_CLASS_WEIGHT.
Click to summarize M_COMPUTE_OUT_OF_BAG_RESULTS +

Inquires whether to use out-of-bag dataset entries to estimate the generalization accuracy. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_ENABLE.
Click to summarize M_DISABLE

Specifies not to use out-of-bag entries.
Click to summarize M_ENABLE

Specifies to use out-of-bag entries.
Click to summarize M_COMPUTE_PROXIMITY_MATRIX +

Inquires whether to calculate the proximity measure matrix when building trees. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_DISABLE.
Click to summarize M_DISABLE

Specifies not to calculate the proximity measure matrix when building trees.
Click to summarize M_ENABLE

Specifies to calculate the proximity measure matrix when building trees.
Click to summarize M_FEATURE_IMPORTANCE_MODE +

Inquires how to establish the importance of the features. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_MEAN_DECREASE_IMPURITY.
Click to summarize M_DISABLE

Specifies to disable the feature importance mode. INFO
Click to summarize M_DROP_COLUMN

Specifies that the feature importance is based on the drop column of features. INFO
Click to summarize M_MEAN_DECREASE_IMPURITY

Specifies that the feature importance is based on a decreasing impurity process. INFO
Click to summarize M_PERMUTATION

Specifies that the feature importance is based on feature permutation. INFO
Click to summarize M_FEATURE_IMPORTANCE_SET +

Inquires how to establish the group of features with which to determine feature importance. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_AUTO.
Click to summarize M_AUTO

Specifies to automatically establish the feature set to use. INFO
Click to summarize M_DEV_DATASET

Specifies to use the development dataset.
Click to summarize M_OUT_OF_BAG

Specifies to use the out-of-bag set. INFO
Click to summarize M_MIN_IMPURITY_DECREASE +

Inquires a decrease of impurity requirement for splitting a node. That is, MIL will split a node if it induces a decrease of impurity greater than or equal to the specified value.

The weighted impurity decrease equation is as follows: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity), where N is the total number of dataset entries, N_t is the number of dataset entries related to the current node, N_t_L is the number of dataset entries related to the left child, and N_t_R is the number of dataset entries related to the right child. N, N_t, N_t_R, and N_t_L all refer to the weighted sum, if weights (entry weights and class weights) are used. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 0.0.
Click to summarize Value >= 0.0

Specifies the impurity value.
Click to summarize M_MIN_NUMBER_OF_ENTRIES_LEAF +

Inquires the minimum number of related dataset entries, or a percentage of the minimum number of related dataset entries, that MIL uses to identify a leaf node. MIL uses this value to establish M_MIN_NUMBER_OF_ENTRIES_LEAF_MODE.

Note that if Round((Value/100) * NumberEntriesLeaf) == 0, then NumberEntriesLeaf = 1. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 1.
Click to summarize 0.0 < MinNumPercent <= 100.0

Specifies the minimum number of entries, as a percentage. INFO
Click to summarize Value >= 1

Specifies the minimum number of entries. INFO
Click to summarize M_MIN_NUMBER_OF_ENTRIES_LEAF_MODE +

Inquires how to establish the minimum number of related dataset entries required to be at a leaf node. A split point at any depth will only be considered if it leaves at least the minimum number of entries (leaf training entries) in each of the left and right branches. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_USER_DEFINED_VALUE.
Click to summarize M_USER_DEFINED_PERCENTAGE

Specifies to use a percentage, determined from the minimum number of entries defined with M_MIN_NUMBER_OF_ENTRIES_LEAF.
Click to summarize M_USER_DEFINED_VALUE

Specifies to use the minimum number of entries defined with M_MIN_NUMBER_OF_ENTRIES_LEAF.
Click to summarize M_MIN_NUMBER_OF_ENTRIES_SPLIT +

Inquires the minimum number of related dataset entries, or a percentage of the minimum number of related dataset entries, that MIL uses to determine how to best split the internal nodes of the trees. MIL uses this value to establish M_MIN_NUMBER_OF_ENTRIES_SPLIT_MODE.

Note that if Round((Value/100) * NumberEntriesSplit) == 0, then NumberEntriesSplit = 2. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 2.
Click to summarize 0.0 < MinNumPercent <= 100.0

Specifies the minimum number of entries, as a percentage. INFO
Click to summarize Value >= 1

Specifies the minimum number of entries. INFO
Click to summarize M_MIN_NUMBER_OF_ENTRIES_SPLIT_MODE +

Inquires how to establish the minimum number of related dataset entries required to split an internal node. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_USER_DEFINED_VALUE.
Click to summarize M_USER_DEFINED_PERCENTAGE

Specifies to use a percentage, determined from the minimum number of entries defined with M_MIN_NUMBER_OF_ENTRIES_SPLIT.
Click to summarize M_USER_DEFINED_VALUE

Specifies to use the minimum number of entries defined with M_MIN_NUMBER_OF_ENTRIES_SPLIT.
Click to summarize M_MIN_WEIGHT_FRACTION_LEAF +

Inquires the minimum weighted fraction of the sum total of weights (of all the dataset entries) required to be at a leaf node. Entries gave equal weight when M_CLASS_WEIGHT_MODE is set to M_NONE. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 0.0.
Click to summarize 0.0 <= Value <= 0.5

Specifies the minimum weighted fraction.
Click to summarize M_NODE_MAX_NUMBER_OF_FEATURES +

Inquires the maximum number of features, or a percentage of the maximum number of features that MIL can use to determine how to best split the nodes of the trees.

Note that if Round((Value/100)*NumberOfFeatures) == 0, then NumberOfFeatures = 1 (see M_NODE_MAX_NUMBER_OF_FEATURES_MODE). SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_ALL.
Click to summarize M_ALL

Specifies no maximum.
Click to summarize 0.0 <= MaxNumPercent <= 100.0

Specifies the percentage with which to determine the maximum number of features. INFO
Click to summarize Value >= 1

Specifies the value with which to determine the maximum number of features. INFO
Click to summarize M_NODE_MAX_NUMBER_OF_FEATURES_MODE +

Inquires how to establish the maximum number of features that MIL uses to determine how to best split the nodes of the trees. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_SQUARE_ROOT.
Click to summarize M_ALL

Specifies that all available features are used.
Click to summarize M_LOG2

Specifies to use a base 2 logarithm, determined from the total number of features. INFO
Click to summarize M_SQUARE_ROOT

Specifies to use a square root, determined from the total number of features. INFO
Click to summarize M_USER_DEFINED_PERCENTAGE

Specifies to use a percentage, determined from the total number of features, where the percentage is set by M_NODE_MAX_NUMBER_OF_FEATURES. INFO
Click to summarize M_USER_DEFINED_VALUE

Specifies to use the maximum number of features defined with M_NODE_MAX_NUMBER_OF_FEATURES.
Click to summarize M_SEED_MODE +

Inquires the mode with which to initialize the seeds. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_USER_DEFINED.
Click to summarize M_AUTO

Specifies that the seed is chosen at random, and that MIL generates and uses a new seed each time you call MclassTrain(). INFO
Click to summarize M_USER_DEFINED

Specifies the user-defined seed set with M_SEED_VALUE.
Click to summarize M_SEED_VALUE +

The seed used to generate random numbers needed to train a tree ensemble.

Note that this value will be ignored if M_SEED_MODE = M_AUTO. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value; the default value is 1.
Click to summarize Value >= 1

Specifies the seed value.
Click to summarize M_SPLIT_QUALITY_TYPE +

Inquires the function with which to measure the quality of a node split. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_GINI.
Click to summarize M_ENTROPY

Specifies that MIL uses an Entropy based function to measure the quality of a node split.
Click to summarize M_GINI

Specifies that MIL uses a Gini based function to measure the quality of a node split.
Click to summarize M_TREE_MAX_DEPTH +

Inquires the maximum depth of the trees. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_NONE.
Click to summarize M_NONE

Specifies no maximum depth.
Click to summarize Value >= 0

Specifies the maximum depth.
Click to summarize M_TREE_MAX_NUMBER_OF_LEAF_NODES +

Inquires the maximum number of terminal nodes in the tree. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_NONE.
Click to summarize M_NONE

Specifies no maximum.
Click to summarize Value >= 1

Specifies the maximum number of terminal nodes in the tree.

To inquire about a global setting of a CNN or tree ensemble training context, set the InquireType parameter to one of the value below. In this case, set the ContextOrResultClassId parameter to the identifier of a CNN or tree ensemble training context and set the LabelOrIndex parameter to M_CONTEXT.

function map For a training context (CNN or tree ensemble)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_SUPPORT_MISSING_GROUND_TRUTH +

Inquires whether entries without a ground truth on training and development datasets are supported. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_DISABLE.
Click to summarize M_DISABLE

Specifies that entries without a ground truth are not allowed. INFO
Click to summarize M_ENABLE

Specifies that entries without a ground truth are allowed. INFO

To inquire about a global setting of a classifier or training context, set the InquireType parameter to one of the values below. In this case, set the ContextOrResultClassId parameter to the identifier of a classifier or training context and set the LabelOrIndex parameter to M_CONTEXT.

Note, these values apply to a CNN or tree ensemble classifier or training context, unless otherwise specified.

function map For a classifier or training context (CNN or tree ensemble)
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_NUMBER_OF_TREES +

Inquires the number of trees in the classifier or training context. You can only retrieve this value after calling MclassPreprocess().

Note, this is only available for tree ensemble training or classifier contexts.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Specifies the default value.

For tree ensemble training context, the default value is 10.

Note that you cannot specify this value for tree ensemble classifier contexts.

(summarize)
Click to summarize Value >= 1

Retrieves the number of trees in the classifier or training context.
Click to summarize M_PREPROCESSED +

Inquires whether the classification or training context is preprocessed.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_FALSE

Specifies that the context has not been preprocessed using MclassPreprocess().
Click to summarize M_TRUE

Specifies that the context has been preprocessed using MclassPreprocess().
Click to summarize M_TIMEOUT +

Inquires the maximum calculation time for MclassPredict(), in msec. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT

Same as M_DISABLE.
Click to summarize M_DISABLE

Specifies an infinite amount of time.
Click to summarize Value > 0.0

Specifies the maximum time, in msec.

To inquire about any classification context supported by this function, set the InquireType the value below. In this case, set the ContextOrResultClassId parameter to the identifier of a classifier context, a dataset context, or a training context, and set the LabelOrIndex parameter to M_CONTEXT.

function map For any supported context
Click to summarize
InquireType		 Description
UserVarPtr
- Possible values returned
Click to summarize M_MODIFICATION_COUNT +

Inquires the current value of the modification counter. The modification counter is increased by one each time settings for the context are modified.

Although you cannot identify the modification counter's contents, you can compare them throughout your application to know if the context has been altered. If the modification counter has changed you can, for example, prompt the user to save before closing the application.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize Value

Specifies the current value of the modification counter.
Click to summarize M_OWNER_SYSTEM +

Inquires the identifier of the system on which the context was allocated. SET

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Click to summarize M_DEFAULT_HOST

Specifies the default Host system of the current MIL application.
Click to summarize MIL system identifier

Specifies a valid system identifier, previously allocated using MsysAlloc().
Combination value for M_AUTHOR_NAME; M_CLASS_NAME; M_CNN_TRAIN_ENGINE_USED_DESCRIPTION; M_EXPIRY_DATE_STRING; M_ROOT_PATH.

You can add the following value to the above-mentioned values to get the size of a string.

function map For inquiring the size of a string
Click to summarizeInquireType combination value Description
UserVarPtr
- Possible values returned
Click to summarize M_STRING_SIZE +

Inquires the number of characters in the string. This number accounts for every character, including the terminating null character.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE MORE
Combination value for the values listed in For a classifier context's source layer (predefined CNN); the values listed in For a training context (tree ensemble); and for the following values: M_ACTIVE_AUTHOR_INDEX; M_ACTIVE_AUTHOR_UPDATE; M_CLASS_DRAW_COLOR; M_CLASS_ICON_ID; M_CLASS_WEIGHT; M_CNN_TRAIN_ENGINE; M_INITIAL_LEARNING_RATE; M_LATEST_USED_RESET_TRAINING_VALUES; M_LEARNING_RATE_DECAY; M_MAX_EPOCH; M_MINI_BATCH_SIZE; M_OWNER_SYSTEM; M_SCHEDULER_TYPE; M_TARGET_IMAGE_SIZE_X; M_TARGET_IMAGE_SIZE_Y; M_TIMEOUT.

You can add the following value to the above-mentioned values to determine the default value of an inquire type, regardless of the current value of the inquire type.

function map For inquiring the default value of an inquire type
Click to summarizeInquireType Description
UserVarPtr
- Possible values returned
Click to summarize M_DEFAULT

Inquires the default value of the specified inquire type.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE
Combination value for the values listed in all the parameter association tables.

You can add the following value to the above-mentioned values to determine whether an inquire type is supported.

function map For inquiring whether an inquire type is supported
Click to summarizeInquireType Description
UserVarPtr
- Possible values returned
Click to summarize M_SUPPORTED

Inquires whether the specified inquire type is supported for the classification context.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE
Click to summarize M_NULL

Specifies that the inquire type is not supported.
Click to summarize Value != 0

Specifies that the inquire type is supported.
Combination values for the values listed in For a classifier context's source layer (predefined CNN) (exceptions might exist); the values listed in For a classifier context (tree ensemble) (exceptions might exist); the values listed in For a classifier context (predefined CNN or tree ensemble) (exceptions might exist); the values listed in For a class definition in a classifier or dataset context (any) (exceptions might exist); the values listed in For a training context (CNN) (exceptions might exist); the values listed in For a training context (tree ensemble) (exceptions might exist); the values listed in For a training context (CNN or tree ensemble) (exceptions might exist); the values listed in For a classifier or training context (CNN or tree ensemble) (exceptions might exist); the values listed in For any supported context (exceptions might exist); and for the following values: M_ACTIVE_AUTHOR_INDEX; M_ACTIVE_AUTHOR_UPDATE; M_CLASSIFIER_CNN_PREDEFINED_TYPE; M_NUMBER_OF_AUGMENTED_ENTRIES; M_NUMBER_OF_AUTHORS; M_NUMBER_OF_CLASSES; M_NUMBER_OF_ENTRIES; M_NUMBER_OF_ENTRIES_GROUND_TRUTH; M_NUMBER_OF_ENTRIES_PREDICTED; M_OWNER_SYSTEM; M_PREDICTED_SCORE_AVERAGE; M_PREDICTED_SCORE_MAX; M_PREDICTED_SCORE_MIN; M_PREPROCESSED; M_STRING_SIZE; M_TARGET_IMAGE_SIZE_X; M_TARGET_IMAGE_SIZE_Y; M_TIMEOUT; M_TRAIN_IMAGE_MIN_SIZE_X; M_TRAIN_IMAGE_MIN_SIZE_Y; M_TRAIN_IMAGE_STEP_X; M_TRAIN_IMAGE_STEP_Y; M_TRAINABLE_COMPLETE; M_TRAINABLE_FINE_TUNING; M_TRAINABLE_TRANSFER_LEARNING.

You can add one of the following values to the above-mentioned values to cast the requested information to a required data type.

Note: In C++, when using a standard vector (std::vector) instead of an array, the values listed in this combination table must not be used. If you need to use a specific data type, instantiate the vector with the necessary data type.

function map For specifying the data type
Click to summarizeInquireType Description
UserVarPtr
- Possible values returned
Click to summarize M_TYPE_MIL_DOUBLE

Casts the requested information to a MIL_DOUBLE.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_DOUBLE  |  array of type MIL_DOUBLE [optionally, in C++: a reference to a std::vector<MIL_DOUBLE> ] MORE
Click to summarize M_TYPE_MIL_ID

Casts the requested information to a MIL_ID. Note that M_TYPE_MIL_ID should only be used with M_OWNER_SYSTEM.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_ID  |  array of type MIL_ID [optionally, in C++: a reference to a std::vector<MIL_ID> ] MORE
Click to summarize M_TYPE_MIL_INT

Casts the requested information to a MIL_INT.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_INT  |  array of type MIL_INT [optionally, in C++: a reference to a std::vector<MIL_INT> ] MORE
Click to summarize M_TYPE_MIL_INT32

Casts the requested information to a MIL_INT32.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_INT32  |  array of type MIL_INT32 [optionally, in C++: a reference to a std::vector<MIL_INT32> ] MORE
Click to summarize M_TYPE_MIL_INT64

Casts the requested information to a MIL_INT64.

(summarize)
Expand data type infoCollapse data type info UserVarPtr extra info
Data type info: Data type: address of a MIL_INT64  |  array of type MIL_INT64 [optionally, in C++: a reference to a std::vector<MIL_INT64> ] MORE
Return value
The returned value is the requested information, cast to a MIL_INT. If the requested information does not fit into a MIL_INT, this function will return M_NULL or truncate the information.
Compilation information
Header Include mil.h.
Library Use mil.lib; milclass.lib.
DLL Requires mil.dll; milclass.dll.
DEFAULT NUMBER OF AUTHORS NUMBER OF CLASSES CONTEXT DEFAULT SOURCE LAYER CLASSIFIER CNN PREDEFINED TYPE CUSTOM FCNET COLOR XL FCNET M FCNET MONO XL FCNET S FCNET XL UNDEFINED EXPIRY DATE STRING TARGET IMAGE SIZE X DEFAULT TARGET IMAGE SIZE Y DEFAULT TRAINABLE COMPLETE FALSE TRUE TRAINABLE FINE TUNING FALSE TRUE TRAINABLE TRANSFER LEARNING FALSE TRUE BAND ORDER DEFAULT BGR RGB SIZE BAND SIZE X SIZE Y STEP X STEP Y TRAIN IMAGE MIN SIZE X TRAIN IMAGE MIN SIZE Y TRAIN IMAGE STEP X TRAIN IMAGE STEP Y TYPE FLOAT Depth value SIGNED Depth value UNSIGNED Depth value NUMBER OF FEATURES CLASSIFIER STATUS DEFAULT PRETRAINED UNDEFINED UNTRAINED USER TRAINED NUMBER OF CLASSES ACTIVE AUTHOR INDEX DEFAULT CURRENT USER ACTIVE AUTHOR UPDATE DEFAULT DISABLE ENABLE AUTHOR KEY AUTHOR NAME NUMBER OF AUGMENTED ENTRIES NUMBER OF AUTHORS NUMBER OF ENTRIES NUMBER OF ENTRIES GROUND TRUTH NUMBER OF ENTRIES PREDICTED PREDICTED SCORE AVERAGE PREDICTED SCORE MAX PREDICTED SCORE MIN ROOT PATH CLASS DRAW COLOR CLASS ICON ID NULL PROC CLASS KEY CLASS NAME CLASS WEIGHT DEFAULT CNN TRAIN ENGINE DEFAULT AUTO CPU GPU CNN TRAIN ENGINE IS INSTALLED FALSE TRUE CNN TRAIN ENGINE USED CPU GPU CNN TRAIN ENGINE USED DESCRIPTION CPU TRAIN ENGINE LOAD STATUS FAILURE SUCCESS UNABLE TO FIND CPU TRAIN ENGINE UNABLE TO LOAD CPU TRAIN ENGINE GPU TRAIN ENGINE LOAD STATUS CUDA FAIL FAILURE JIT COMPILATION REQUIRED JIT COMPILER NOT FOUND SUCCESS UNABLE TO FIND GPU TRAIN ENGINE UNABLE TO FIND VALID GPU UNABLE TO LOAD GPU TRAIN ENGINE INITIAL LEARNING RATE DEFAULT LATEST USED RESET TRAINING VALUES DEFAULT COMPLETE FINE TUNING TRANSFER LEARNING LEARNING RATE DECAY DEFAULT MAX EPOCH DEFAULT MINI BATCH SIZE DEFAULT SCHEDULER TYPE DEFAULT CYCLICAL DECAY DECAY BOOTSTRAP DEFAULT DISABLE WITH REPLACEMENT WITHOUT REPLACEMENT CLASS WEIGHT MODE DEFAULT BALANCE NONE USER DEFINED COMPUTE OUT OF BAG RESULTS DEFAULT DISABLE ENABLE COMPUTE PROXIMITY MATRIX DEFAULT DISABLE ENABLE FEATURE IMPORTANCE MODE DEFAULT DISABLE DROP COLUMN MEAN DECREASE IMPURITY PERMUTATION FEATURE IMPORTANCE SET DEFAULT AUTO DEV DATASET OUT OF BAG MIN IMPURITY DECREASE DEFAULT MIN NUMBER OF ENTRIES LEAF DEFAULT MIN NUMBER OF ENTRIES LEAF MODE DEFAULT USER DEFINED PERCENTAGE USER DEFINED VALUE MIN NUMBER OF ENTRIES SPLIT DEFAULT MIN NUMBER OF ENTRIES SPLIT MODE DEFAULT USER DEFINED PERCENTAGE USER DEFINED VALUE MIN WEIGHT FRACTION LEAF DEFAULT NODE MAX NUMBER OF FEATURES DEFAULT ALL NODE MAX NUMBER OF FEATURES MODE DEFAULT ALL LOG2 SQUARE ROOT USER DEFINED PERCENTAGE USER DEFINED VALUE SEED MODE DEFAULT AUTO USER DEFINED SEED VALUE DEFAULT SPLIT QUALITY TYPE DEFAULT ENTROPY GINI TREE MAX DEPTH DEFAULT NONE TREE MAX NUMBER OF LEAF NODES DEFAULT NONE SUPPORT MISSING GROUND TRUTH DEFAULT DISABLE ENABLE NUMBER OF TREES DEFAULT PREPROCESSED FALSE TRUE TIMEOUT DEFAULT DISABLE MODIFICATION COUNT OWNER SYSTEM DEFAULT HOST STRING SIZE DEFAULT SUPPORTED NULL TYPE MIL DOUBLE TYPE MIL ID TYPE MIL INT TYPE MIL INT32 TYPE MIL INT64 CONTEXT DEFAULT DEFAULT SOURCE LAYER CONTEXT DEFAULT CONTEXT DEFAULT CONTEXT DEFAULT CONTEXT DEFAULT CONTEXT DEFAULT M_FLOAT + Depth value M_SIGNED + Depth value M_UNSIGNED + Depth value