This function restores an ENVITensorFlowGridModel object, which specifies the TensorFlow model used for deep learning.

This routine is part of ENVI Deep Learning, which requires a separate license and installation.

Example


Sample data files are available on our ENVI Tutorials web page. Click the "Deep Learning" link in the ENVI Tutorial Data section to download a .zip file containing the data. Extract the contents to a local directory. The file TrainedGridModel.h5 is in the Grid_Tutorial_Data\Classification\Models directory.

; Start the application
e = ENVI(/HEADLESS)
 
; Update the following line with the correct path
; to the tutorial data files
ModelFile = 'C:\MyTutorialFiles\TrainedGridModel.h5'
 
; Reopen a model
Model = ENVITensorFlowGridModel(ModelFile)
Metrics = Model.Metrics
Print, Model, /IMPLIED_PRINT

Syntax


Result = ENVITensorFlowGridModel(Input_File [, Properties=value] [, ERROR=value])

Return Value


This routine returns a reference to an ENVITensorFlowGridModel object.

Arguments


Input_File

Specify a fully qualified filename and path to an ENVITensorFlowGridModel file in HDF5 format.

Methods


Close

Dehydrate

Hydrate

Properties


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.

BACKGROUND_PATCH_RATIO (Get)

The ratio of background to foreground patches.

CLASS_COLORS (Get)

An array of RGB class colors per class.

CLASS_NAMES (Get)

A string array of class label names.

EPOCHS (Get, Set)

An epoch is a full pass of the entire training dataset through the algorithm's learning process. Specify the number of Epochs to run. Training inputs are adjusted at the end of each epoch.

FEATURE_PATCH_PERCENTAGE (Get)

The percentage of data to use that contains features.

GRID_SIZE (Get)

The squared value of the grid. For example, GRID_SIZE=224 is (224x224)

METRICS (Get)

A Hash of model training and validation metrics produced by TensorFlow which provides an estimation of the performance of the trained TensorFlow model. The values of the metrics hash keys are arrays that provide a metric for each epoch. The index value plus 1 of the array represents the value for that epoch. Arrays are 0-based, so epoch 0 is the first epoch. The best model, referenced as the OUTPUT_MODEL training property, provides metrics starting at epoch 1 through the best epoch. If the best epoch is 3 and total epochs is 10, metrics for epochs 1, 2, and 3 will be provided. The last model, referenced as the OUTPUT_LAST_MODEL training property, provides a metric for every epoch.

MODEL_ARCHITECTURE (Get)

A string with the model architecture; for example:

  • ResNet50

  • ResNet101

MODEL_TYPE (Get)

A string with the model type. The value is Grid.

NBANDS (Get)

The number of bands in the training rasters (minus the mask band).

NCLASSES (Get)

The number of classes (minus the background class).

URI (Get)

A string that is a fully qualified raster file path.

Keywords


ERROR (optional)

Set this keyword to a named variable that will contain any error message issued during execution of this routine. If no error occurs, the ERROR variable will be set to a null string (''). If an error occurs and the routine is a function, then the function result will be undefined.

When this keyword is not set and an error occurs, ENVI returns to the caller and execution halts. In this case, the error message is contained within !ERROR_STATE and can be caught using IDL's CATCH routine. See IDL Help for more information on !ERROR_STATE and CATCH.

See the Manage Errors topic in ENVI Help for more information on error handling.

Version History


Deep Learning 3.0

Introduced

See Also


TrainTensorFlowGridModel Task, TensorFlowGridClassification Task, TensorFlowOptimizedObjectClassification Task, TensorFlowOptimizedPixelClassification Task