dlpy.images.ImageTable.from_table

classmethod ImageTable.from_table(tbl, image_col='_image_', label_col='_label_', path_col=None, columns=None, casout=None, label_level=0)

Create an ImageTable from a CASTable

Parameters:

tbl : CASTable

The CASTable object to use as the source.

image_col : str, optional

Specifies the column name for the image data. Default = ‘_image_’

label_col : str, optional

Specifies the column name for the labels. Default = ‘_label_’

path_col : str, optional

Specifies the column name that stores the path for each image. Default = None, and the unique image ID will be generated from the labels.

columns : list of str, optional

Specifies the extra columns in the image table. Default = None

casout : dict

Specifies the output CASTable parameters. Default = None. Note : the options of replace=True, blocksize=32 will be automatically added to the casout option.

label_level : optional

Specifies which path level should be used to generate the class labels for each image. For instance, label_level = 1 means the first directory and label_level = -2 means the last directory. This internally use the SAS scan function (check https://www.sascrunch.com/scan-function.html for more details). In default, no class labels are generated. If the label column already exists, this option will be ignored.
Default: 0

Returns:

ImageTable

Examples

>>> from swat import CAS
>>> from dlpy.images import ImageTable
>>> s=CAS("cloud.example.com", 5570)
>>> s.loadactionset("images")
>>> s.images.loadImages(casout="images",path="path/to/images")
>>> cas_table = s.CASTable("images")
>>> img_table=ImageTable.from_table(cas_table)
>>> img_table.show()

For details about the loadImages action, see images.loadImages