تصدير بيانات التدريب للتعلم العميق Export Training Data for Deep Learning

القائمة الرئيسية

الصفحات

تصدير بيانات التدريب للتعلم العميق Export Training Data for Deep Learning

لمتابعة موقعنا ليصلك كل جديد إضغط هنا


Export Training Data for Deep Learning Tool

أداة تصدير بيانات التدريب للتعلم العميق

ArcMap ArcGIS

How to use Export Training Data for Deep Learning Tool in Arc Toolbox??

كيفية استخدام أداة تصدير بيانات التدريب للتعلم العميق ؟؟

كيفية استخدام أداة تصدير بيانات التدريب للتعلم العميق ؟؟

Path to access the toolمسار الوصول الى الأداة

:

Export Training Data for Deep Learning Tool, Segmentation and Classification Toolset, Spatial Analyst Tools Toolbox

Export Training Data for Deep Learning Tool 

Export Training Data for Deep Learning

Uses a remote sensing image to convert labeled vector or raster data into deep learning training datasets. The output is a folder of image chips and a folder of metadata files in the specified format.

يستخدم صورة الاستشعار عن بعد لتحويل البيانات المتجهية أو النقطية إلى مجموعات بيانات تدريب التعلم العميق. الإخراج عبارة عن مجلد من شرائح الصور ومجلد لملفات البيانات الوصفية بالتنسيق المحدد.

1.    Input Raster أدخل البيانات النقطية

The input source imagery, typically multispectral imagery.

Examples of the type of input source imagery include multispectral satellite, drone, aerial, or National Agriculture Imagery Program (NAIP).

صور مصدر الإدخال ، عادةً صور متعددة الأطياف.

تتضمن الأمثلة على نوع صور مصدر الإدخال القمر الصناعي متعدد الأطياف أو الطائرة بدون طيار أو الجوي أو برنامج الصور الزراعية الوطني (NAIP).

Output Folder

The folder where the output image chips and metadata will be stored.

Input Feature Class Or Classified Raster (optional)

The training sample data, in either vector or raster form.

Vector inputs should follow a training sample format as generated by the ArcGIS Desktop Image Classification toolbar. Raster inputs should follow a classified raster format as generated by the Classify Raster tool.

Class Value Field (optional)

The field that contains the class values. If no field is specified, the system searches for a value or classvalue field. If the feature does not contain a class field, the system determines that all records belong to one class.

Buffer Radius (optional)

The radius for a buffer around each training sample to delineate a training sample area. This allows you to create circular polygon training samples from points.

The linear unit of the Input Feature Class Or Classified Raster spatial reference is used.

Image Chip Format (optional)

Specifies the raster format for the image chip outputs.

PNG and JPEG support up to 3 bands.

Tile Size X (optional)

The size of the image chips for the X dimension.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

2.    Output Folder مجلد الإخراج

The folder where the output image chips and metadata will be stored.

المجلد حيث سيتم تخزين شرائح الصور الناتجة والبيانات الوصفية.

Input Feature Class Or Classified Raster (optional)

The training sample data, in either vector or raster form.

Vector inputs should follow a training sample format as generated by the ArcGIS Desktop Image Classification toolbar. Raster inputs should follow a classified raster format as generated by the Classify Raster tool.

Class Value Field (optional)

The field that contains the class values. If no field is specified, the system searches for a value or classvalue field. If the feature does not contain a class field, the system determines that all records belong to one class.

Buffer Radius (optional)

The radius for a buffer around each training sample to delineate a training sample area. This allows you to create circular polygon training samples from points.

The linear unit of the Input Feature Class Or Classified Raster spatial reference is used.

Image Chip Format (optional)

Specifies the raster format for the image chip outputs.

PNG and JPEG support up to 3 bands.

Tile Size X (optional)

The size of the image chips for the X dimension.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

3.    Input Feature Class Or Classified Raster (optional) فئة ميزة الإدخال أو النقطية المصنفة (اختياري)

The training sample data, in either vector or raster form.

Vector inputs should follow a training sample format as generated by the ArcGIS Desktop Image Classification toolbar. Raster inputs should follow a classified raster format as generated by the Classify Raster tool.

بيانات عينة التدريب ، إما في شكل متجه أو نقطي.

يجب أن تتبع مدخلات المتجه تنسيق عينة تدريب كما تم إنشاؤه بواسطة شريط أدوات ArcGIS Desktop Image Classification. يجب أن تتبع مدخلات البيانات النقطية تنسيقًا نقطيًا مصنفًا كما تم إنشاؤه بواسطة أداة Classify Raster.

Class Value Field (optional)

The field that contains the class values. If no field is specified, the system searches for a value or classvalue field. If the feature does not contain a class field, the system determines that all records belong to one class.

Buffer Radius (optional)

The radius for a buffer around each training sample to delineate a training sample area. This allows you to create circular polygon training samples from points.

The linear unit of the Input Feature Class Or Classified Raster spatial reference is used.

Image Chip Format (optional)

Specifies the raster format for the image chip outputs.

PNG and JPEG support up to 3 bands.

Tile Size X (optional)

The size of the image chips for the X dimension.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

4.    Class Value Field (optional) حقل قيمة الفئة (اختياري)

The field that contains the class values. If no field is specified, the system searches for a value or classvalue field. If the feature does not contain a class field, the system determines that all records belong to one class.

الحقل الذي يحتوي على قيم الفئة. إذا لم يتم تحديد أي حقل ، يبحث النظام عن قيمة أو حقل فئة قيمة. إذا كانت الميزة لا تحتوي على حقل فئة ، يحدد النظام أن جميع السجلات تنتمي إلى فئة واحدة.

Buffer Radius (optional)

The radius for a buffer around each training sample to delineate a training sample area. This allows you to create circular polygon training samples from points.

The linear unit of the Input Feature Class Or Classified Raster spatial reference is used.

Image Chip Format (optional)

Specifies the raster format for the image chip outputs.

PNG and JPEG support up to 3 bands.

Tile Size X (optional)

The size of the image chips for the X dimension.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

5.    Buffer Radius (optional) نصف قطر الحرم المكاني (اختياري)

The radius for a buffer around each training sample to delineate a training sample area. This allows you to create circular polygon training samples from points.

The linear unit of the Input Feature Class Or Classified Raster spatial reference is used.

نصف قطر الحرم المكاني حول كل عينة تدريب لتحديد منطقة عينة التدريب. يتيح لك ذلك إنشاء عينات تدريب على شكل مضلع دائري من النقاط.

يتم استخدام الوحدة الخطية لفئة ميزات الإدخال أو الإسناد المكاني النقطي المصنف.

Image Chip Format (optional)

Specifies the raster format for the image chip outputs.

PNG and JPEG support up to 3 bands.

Tile Size X (optional)

The size of the image chips for the X dimension.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

6.    Image Chip Format (optional) تنسيق رقاقة الصورة (اختياري)

Specifies the raster format for the image chip outputs.

PNG and JPEG support up to 3 bands.

· TIFF—TIFF format

· PNG—PNG format

· JPEG—JPEG format

· MRF—MRF (Meta Raster Format)

يحدد التنسيق النقطي لمخرجات شريحة الصورة.

يدعم تنسيق PNG و JPEG ما يصل إلى 3 نطاقات.

TIFF - تنسيق TIFF

PNG - تنسيق PNG

JPEG - تنسيق JPEG

MRF - MRF (تنسيق Meta Raster)

Tile Size X (optional)

The size of the image chips for the X dimension.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

7.    Tile Size X (optional) حجم س (اختياري)

The size of the image chips for the X dimension.

حجم شرائح الصورة للبعد X.

Tile Size Y (optional)

The size of the image chips for the Y dimension.

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

8.    Tile Size Y (optional) حجم ص (اختياري)

The size of the image chips for the Y dimension.

حجم شرائح الصورة للبعد Y.

 

Stride X (optional)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

9.    Stride X (optional) س (اختياري)

The distance to move in the X direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

المسافة للتحرك في الاتجاه X عند إنشاء شرائح الصورة التالية.

عندما تكون الخطوة مساوية لحجم البلاط ، لن يكون هناك تداخل. عندما تكون الخطوة مساوية لنصف حجم البلاط ، سيكون هناك تداخل بنسبة 50 بالمائة.

Stride Y (optional)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

10. Stride Y (optional) ص (اختياري)

The distance to move in the Y direction when creating the next image chips.

When stride is equal to tile size, there will be no overlap. When stride is equal to half the tile size, there will be 50 percent overlap.

مسافة التحرك في الاتجاه Y عند إنشاء شرائح الصورة التالية.

عندما تكون الخطوة مساوية لحجم البلاط ، لن يكون هناك تداخل. عندما تكون الخطوة مساوية لنصف حجم البلاط ، سيكون هناك تداخل بنسبة 50 بالمائة.

Output NoFeature Tiles (optional)

Specifies whether image chips that do not capture training samples will be exported.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

11. Output NoFeature Tiles (optional) المخرج بدون معالم (اختياري)

Specifies whether image chips that do not capture training samples will be exported.

· Checked—All image chips, including those that do not capture training samples, will be exported.

· Unchecked—Only image chips that capture training samples will be exported. This is the default.

If checked, image chips that do not capture labeled data will also be exported; if not checked, they will not be exported.

يحدد ما إذا كان سيتم تصدير شرائح الصور التي لا تلتقط عينات التدريب.

• تم التحديد - سيتم تصدير جميع شرائح الصور ، بما في ذلك تلك التي لا تلتقط عينات التدريب.

• غير محدد - سيتم تصدير شرائح الصور التي تلتقط عينات التدريب فقط. هذا هو الافتراضي.

إذا تم تحديده ، فسيتم أيضًا تصدير شرائح الصور التي لا تلتقط البيانات المصنفة ؛ إذا لم يتم تحديدها ، فلن يتم تصديرها.

Meta Data Format (optional)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

12. Meta Data Format (optional) تنسيق البيانات الوصفية (اختياري)

Specifies the format of the output metadata labels.

The four options for output metadata labels for the training data are KITTI rectangles, PASCAL VOC rectangles, Classified Tiles (a class map), and RCNN Masks. If your input training sample data is a feature class layer, such as a building layer or standard classification training sample file, use the KITTI or PASCAL VOC rectangles option. The output metadata is a .txt file or .xml file containing the training sample data contained in the minimum bounding rectangle. The name of the metadata file matches the input source image name. If your input training sample data is a class map, use the Classified Tiles option as your output metadata format.

· KITTI_rectangles—The metadata follows the same format as the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) Object Detection Evaluation dataset. The KITTI dataset is a vision benchmark suite. This is the default.The label files are plain text files. All values, both numerical and strings, are separated by spaces, and each row corresponds to one object.

· PASCAL_VOC_rectangles—The metadata follows the same format as the Pattern Analysis, Statistical Modeling and Computational Learning, Visual Object Classes (PASCAL_VOC) dataset. The PASCAL VOC dataset is a standardized image dataset for object class recognition.The label files are XML files and contain information about image name, class value, and bounding boxes.

· Classified_Tiles—The output will be one classified image chip per input image chip. No other metadata for each image chip is used. Only the statistics output has more information on the classes, such as class names, class values, and output statistics.

· RCNN_Masks—The output will be image chips that have a mask on the areas where the sample exists. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone in the deep learning framework model.

For the KITTI metadata format, 15 columns are created, but only 5 of them are used in the tool. The first column is the class value. The next 3 columns are skipped. Columns 5-8 define the minimum bounding rectangle, which is comprised of 4 image coordinate locations: left, top, right, and bottom pixels, respectively. The minimum bounding rectangle encompasses the training chip used in the deep learning classifier. The remaining columns are not used.

يحدد تنسيق تسميات البيانات الأولية للمخرجات.

الخيارات الأربعة لتسميات البيانات الوصفية للمخرجات لبيانات التدريب هي مستطيلات KITTI ، ومستطيلات PASCAL VOC ، والبلاط المصنف (خريطة الفصل) ، وأقنعة RCNN. إذا كانت بيانات نموذج تدريب الإدخال عبارة عن طبقة فئة معلم ، مثل طبقة بناء أو ملف عينة تدريب على التصنيف القياسي ، فاستخدم خيار مستطيلات KITTI أو PASCAL VOC. البيانات الوصفية للمخرجات هي ملف .txt أو ملف .xml يحتوي على بيانات عينة التدريب الموجودة في الحد الأدنى لمستطيل الإحاطة. يتطابق اسم ملف البيانات الأولية مع اسم صورة مصدر الإدخال. إذا كانت بيانات عينة تدريب الإدخال الخاصة بك عبارة عن خريطة فصل ، فاستخدم الخيار Classified Tiles كتنسيق بيانات تعريف الإخراج.

KITTI_rectangles - تتبع البيانات الوصفية نفس تنسيق مجموعة بيانات تقييم اكتشاف الكائنات لمعهد كارلسروه للتكنولوجيا ومعهد تويوتا التكنولوجي (KITTI). مجموعة بيانات KITTI هي مجموعة معايير الرؤية. هذا هو الإعداد الافتراضي ، ملفات التسمية هي ملفات نصية عادية. يتم فصل جميع القيم ، العددية والسلاسل ، بمسافات ، ويتوافق كل صف مع كائن واحد.

PASCAL_VOC_rectangles - تتبع البيانات الوصفية نفس تنسيق مجموعة بيانات تحليل الأنماط والنمذجة الإحصائية والتعلم الحسابي وفئات الكائنات المرئية (PASCAL_VOC). مجموعة بيانات PASCAL VOC هي مجموعة بيانات صور قياسية للتعرف على فئة الكائن. ملفات الملصقات هي ملفات XML وتحتوي على معلومات حول اسم الصورة وقيمة الفئة والمربعات المحيطة.

Classified_Tiles - سيكون الإخراج عبارة عن شريحة صورة مصنفة واحدة لكل شريحة صورة إدخال. لا يتم استخدام أي بيانات وصفية أخرى لكل شريحة صورة. يحتوي إخراج الإحصائيات فقط على مزيد من المعلومات حول الفئات ، مثل أسماء الفئات وقيم الفئة وإحصائيات الإخراج.

RCNN_Masks - سيكون الناتج عبارة عن شرائح صور بها قناع على المناطق التي توجد بها العينة. يقوم النموذج بإنشاء مربعات محيط وأقنعة تجزئة لكل مثيل لكائن في الصورة. يعتمد على شبكة هرم الميزات (FPN) والعمود الفقري ResNet101 في نموذج إطار عمل التعلم العميق.

بالنسبة إلى تنسيق البيانات الوصفية لـ KITTI ، يتم إنشاء 15 عمودًا ، ولكن يتم استخدام 5 منهم فقط في الأداة. العمود الأول هو قيمة الفئة. تم تخطي الأعمدة الثلاثة التالية. تحدد الأعمدة 5-8 الحد الأدنى لمستطيل الإحاطة ، والذي يتكون من 4 مواقع إحداثيات للصورة: وحدات بكسل يسار ، وأعلى ، ويمين ، وأسفل ، على التوالي. يشمل الحد الأدنى لمستطيل الإحاطة شريحة التدريب المستخدمة في مصنف التعلم العميق. لم يتم استخدام الأعمدة المتبقية.

Start Index (optional)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

13. Start Index (optional) فهرس البداية (اختياري)

The start index for the sequence of image chips. This allows you to append more image chips to an existing sequence. The default value is 0.

فهرس البداية لتسلسل شرائح الصور. يتيح لك ذلك إلحاق المزيد من شرائح الصور بالتسلسل الحالي. القيمة الافتراضية هي 0.

 اليك صفحه ومجموعة على الفيس بوك لتعلم أكثر بما يخص نظم المعلومات الجغرافية (GIS) و برنامج ArcGIS Pro من خلال هذه الروابط:


مجموعة على الفيس بوك ArcGIS Pro من هنا.
مجموعة على الفيس بوك GIS for WE - ArcGIS Pro من هنا.
صفحة الفيس بوك GIS for WE من هنا.

 

GIS for WE

تعليقات

التنقل السريع
    >