InitializeENVINet5MultiModel Task

This task initializes an untrained multiclass TensorFlow mask-based model.

Example

; Start the application

e = ENVI(/HEADLESS)

 

; Get the task from the catalog of ENVITasks

Task = ENVITask('InitializeENVINet5MultiModel')

 

; Define inputs

Task.MODEL_DESCRIPTION = 'My model description'

Task.NCLASSES = 4

 

; Specify the number of bands in the training rasters,

; not including the mask band

Task.NBANDS = 3

 

; Run the task

Task.Execute

Print, Task.OUTPUT_MODEL, /IMPLIED_PRINT

Syntax

Result = ENVITask('InitializeENVINet5MultiModel')

Input properties (Set, Get): MODEL_ARCHITECTURE, MODEL_DESCRIPTION, MODEL_NAME, NBANDS, NCLASSES, OUTPUT_MODEL_URI, PATCH_SIZE

Output properties (Get only): OUTPUT_MODEL

Properties marked as "Set" are those that you can set to specific values. You can also retrieve their current values any time. Properties marked as "Get" are those whose values you can retrieve but not set.

Methods

This task inherits the following methods from ENVITask. See the ENVITask topic in ENVI Help.

Properties

This task inherits the following properties from ENVITask:

COMMUTE_ON_DOWNSAMPLE

COMMUTE_ON_SUBSET

DESCRIPTION

DISPLAY_NAME

NAME

REVISION

See the ENVITask topic in ENVI Help for details.

This task also contains the following properties:

MODEL_ARCHITECTURE (optional)

Specify a model architecture to use during training. The options are:

MODEL_DESCRIPTION (optional)

Specify a description of the model's capabilities.

MODEL_NAME (optional)

Specify the name of the model. The default value is ENVI Deep Learning.

The default value is ENVI Deep Learning.

NBANDS (required)

Specify the number of bands in the training rasters that will be used to train this model (minus the mask band).

NCLASSES (required)

Specify the number of classes (excluding the background class).

OUTPUT_MODEL

This is a reference to the initialized ENVITensorFlowModel.

OUTPUT_MODEL_URI (required)

Specify a string with the fully qualified filename and path for the HDF5 (.h5) model file to be written.

PATCH_SIZE (optional)

Specify the edge length in pixels of the square patches used for training. The choices are: 208, 224, 240, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512, 528, 544, 560, 576, 592, 608, 624, 640, 656, 672, 688, 704, 720, 736, 752, 768, 784. The default is 464.

Version History

Deep Learning 1.1

Introduced

Deep Learning 2.1 Added MODEL_ARCHITECTURE property

See Also

ENVITensorFlowModel, TrainTensorFlowMaskModel Task