Image
Image Classification. Multi-class image classification is used when an image is classified with only a single label from a set of classes - e.g. each image is classified as either an image of a 'cat' or a 'dog' or a 'duck'.
Constructors
Properties
Required Limit settings for the AutoML job.
Log verbosity for the job.
Settings used for training the model.
Primary metric to optimize for this task.
Search space for sampling different combinations of models and their hyperparameters.
Model sweeping and hyperparameter sweeping related settings.
Target column name: This is prediction values column. Also known as label column name in context of classification tasks.
Required Training data input.
Validation data inputs.
The fraction of training dataset that needs to be set aside for validation purpose. Values between (0.0 , 1.0) Applied when validation dataset is not provided.