Deep Learning - "Unknown dataset_type="KITTI_rectangles"

NickPombo

<\/HEAD>

Hola,<\/SPAN><\/P>Actualmente estoy trabajando en entrenar un modelo de deep learning en ArcGIS Pro que detectará imágenes geotérmicas en imágenes Landsat 8. He estado siguiendo este tutorial: Train Deep Learning ModelHelp | Documentation<\/A> .<\/SPAN><\/P>

<\/P>

Actualmente estoy atascado en el último paso del proceso, entrenar el modelo en sí. He creado una carpeta adecuada para todos los datos de entrenamiento exportados y ahora estoy trabajando con Python. Aquí está mi código a continuación:<\/SPAN><\/P><\/P>importar<\/SPAN> <\/SPAN>arcpy <\/SPAN><\/P>desde<\/SPAN> <\/SPAN>arcpy.ia <\/SPAN><\/SPAN>importar<\/SPAN> <\/SPAN>* <\/SPAN><\/P> <\/SPAN><\/P># Verificar la licencia de la extensión ArcGIS Image Analyst<\/SPAN><\/P>arcpy.CheckOutExtension(<\/SPAN>"ImageAnalyst"<\/SPAN>)<\/SPAN><\/P>#Definir parámetros de entrada<\/span>

in_folder = "C:\Users\gphy426\Documents\Geothermal Pombo\training_data_geoproc"

out_folder = "C:\Users\gphy426\Documents\Geothermal Pombo\trained_model"

max_epochs = 20

model_type = "FEATURE_CLASSIFIER"

batch_size = 2

arg = "# #"

learning_rate = None

backbone_model = "RESNET34"

pretrained_model = None

validation_percent = 10

stop_training = “STOP_TRAINING”   # Ejecutar TrainDeepLearningModel(in_folder, out_folder, max_epochs, model_type, <pstyle=”margin”: “...” color=#500050font-weight=

SangeetMathew

Hi Nick, 

The training api and tools use  "transfer learning" to train our models which means your data needs to be 3 Band 8 bit. What I would suggest to make your dataset training capable, is to use a composite band tool/function on your dataset to make it 3 band( Here is some help How To: Convert individual raster bands into a color or multiband image ). If it is not 8 bit you can use the stretch function to make it 8 bit. Then run the Export training tool (using PASCAL VOC Objects option ) and then train your data. Hope this helps.

Thanks

Sangeet