Train Deep Learning Model

(Required)

This is the input location for the training sample data. It can be the path of output location on the file share raster data store or a shared file system path. The training sample data folder needs to be the output of Export Training Data For Deep Learning tool, containing images and labels folders, as well as the JSON model definition file written out together by the tool.

File share raster store path examples:

//File share raster store path examples
in_folder=/rasterStores/yourRasterStoreFolderName/trainingSampleData
in_folder=/fileShares/yourFileShareFolderName/trainingSampleData

//File share path example
in_folder=\\serverName\deepLearning\trainingSampleData

(Required)

A JSON representing the output trained .dlpk name that will be added to your enterprise portal. If the .dlpk item already exists, the portal item Id can be given to the service tool. The output path of the .dlpk file that is generated will be used to update the existing .dlpk item. The output .dlpk file is stored and shared on the hosting server and uploaded to your portal.

output_name={"name": "trainedModel"}
output_name={"name": "trainedModel","folderId":"dfwerfbd3ec25584d0d8f4"}

//String representing the fileshare datastore path to which the dlpk would be written to
output_name=“/fileShares/filesharename/folder”

(Required)

The model type to use for training the deep learning model. The single shot detector (SSD) model type is used for object detection. U-Net (UNET) model types are used to pixel classification. For object classification, the Feature Classifier (FEATURE_CLASSIFIER) model type should be used. The Pyramid Scene Parsing Network (PSPNET) model type is used for pixel classification. Both RetinaNet (RETINANET) and MarkRCNN (MARKRCNN) model types are used for object detection.

Values: SSD | UNET | FEATURE_CLASSIFIER | PSPNET | RETINANET | MASKRCNN

(Optional)

The name of the value pairs of arguments and their values that can be customized by the clients.

arguments={"name1": "value1", "name2": "value2"}

(Optional)

The number of training samples to be processed for training at one time. If the server has a powerful GPU, this number can be increased to 16, 36, 64, and so on.

batch_size=4

(Optional)

The maximum number of epochs for training the model. One epoch means the whole training dataset will be passed forward and backward through the deep neural network once.

max_epochs=20

(Optional)

The rate at which the weights are updated during the training. It is a small positive value in the range between 0.0 and 1.0. If the learning rate is set to 0, it will extract the optimal learning rate from the learning curve during the training process.

learning_rate=0

(Optional)

Specifies the preconfigured neural network to be used as an architecture for training the new model.

Values: DENSENET121 | DENSENET161 | DENSENET169 | DENSENET201 | MOBILENET_V2 | MASKRCNN50_FPN | RESNET18 | RESNET34 | RESNET50 | RESNET101 | RESNET152 | VGG11 | VGG11_BN | VGG13 | VGG13_BN | VGG16 | VGG16_BN | VGG19 | VGG19_BN

backbone_model=RESNET34

(Optional)

The percentage of training sample data that will be used for validating the model.

validation_percent=10

(Optional)

The pretrained model to be used for fine tuning the new model. It is a .dlpk portal item.

pretrained_model={"itemId": "8cfbd3ec25584d0d8fed23b8ff7c43b"}

(Optional)

Specifies whether early stopping will be implemented. If true, the model training will stop when the model is no longer improving, regardless of the maximum epochs specified. This is the default. If false, the model training will continue until the maximum epochs is reached.

Values: true | false

(Optional)

Environment settings that affect task execution. This task has the following settings:

• extent—A bounding box that defines the analysis area.
• cellSize—The output raster will have the resolution specified by cell size.
• processorType—The specified processor (CPU or GPU) will be used for the analysis.

context={"cellSize": "20","processorType": "GPU"}

Specify whether to freeze the backbone layers in the pretrained model, so that the weights and biases in the backbone layers remain unchanged. If true, the predefined weights and biases will not be altered in the backboneModel. This is the default. If false, the weights and biases of the backboneModel may be altered to better fir your training samples. This may take more time to process but usually could get better results.

Values: true | false

The response format. The default response format is html.

Values: html | json | pjson

The preconfigured model will be a dense network trained on the ImageNET Dataset that contains more than a million images and is 121 layers deep. Unlike RESNET, which combines the layer using summation, DenseNet combines the layers using concatenation.

The preconfigured model will be a dense network trained on the ImageNET Dataset that contains more than a million images and is 161 layers deep. Unlike RESNET, which combines the layer using summation, DenseNet combines the layers using concatenation.

The preconfigured model will be a dense network trained on the ImageNET Dataset that contains more than a million images and is 169 layers deep. Unlike RESNET, which combines the layer using summation, DenseNet combines the layers using concatenation.

The preconfigured model will be a dense network trained on the ImageNET Dataset that contains more than a million images and is 201 layers deep. Unlike RESNET, which combines the layer using summation, DenseNet combines the layers using concatenation.

This preconfigured model is trained on the ImageNet Database and is 54 layers deep geared towards Edge device computing, since it uses less memory.

This preconfigured model was trained for object detection with backbone RESNET50 with Feature Pyramid Networks to detect objects at different scales.

The preconfigured model will be a residual network trained on the ImageNET Dataset that contains more than a million images and is 18 layers deep.

The preconfigured model will be a residual network trained on the ImageNET Dataset that contains more than a million images and is 34 layers deep. This is the default.

The preconfigured model will be a residual network trained on the ImageNET Dataset that contains more than a million images and is 50 layers deep.

The preconfigured model will be a residual network trained on the ImageNET Dataset that contains more than a million images and is 101 layers deep.

The preconfigured model will be a residual network trained on the ImageNET Dataset that contains more than a million images and is 152 layers deep.

The preconfigured model will be a convolution neural network trained on the ImageNET Dataset that contains more than a million images to classify images into 1000 object categories and is 11 layers deep.

This preconfigured model is based on the VGG network but with batch normalization, which is each layer in the network in normalized. It trained on the ImageNet dataset and has 11 layers.

The preconfigured model will be a convolution neural network trained on the ImageNET Dataset that contains more than a million images to classify images into 1000 object categories and is 13 layers deep.

This preconfigured model is based on the VGG network but with batch normalization, which is each layer in the network in normalized. It trained on the ImageNet dataset and has 13 layers.

The preconfigured model will be a convolution neural network trained on the ImageNET Dataset that contains more than a million images to classify images into 1000 object categories and is 16 layers deep.

This preconfigured model is based on the VGG network but with batch normalization, which is each layer in the network in normalized. It trained on the ImageNet dataset and has 16 layers.

The preconfigured model will be a convolution neural network trained on the ImageNET Dataset that contains more than a million images to classify images into 1000 object categories and is 19 layers deep.

This preconfigured model is based on the VGG network but with batch normalization, which is each layer in the network in normalized. It trained on the ImageNet dataset and has 19 layers.