Creates a new set of image classifier parameters with validation data represented by a dictionary.
- macOS 10.14–10.15Deprecated
- Xcode 10.0–11.0Deprecated
- Create ML
A versioned feature extractor.
Data to be used for validation stored as a dictionary using labels for keys, and arrays of image URLs as the corresponding values. If your data is stored in an
Classifier .Data Source
Extractor: validation Data: max Iterations: augmentation Options:)
Set this parameter to
nilto tell the classifier to set aside a small, random subset of your training data to be used as validation data.
The maximum number of iterations to use during training.
The variations that the training process uses to generate more data from the training data you provide. For example, you can tell the training process to supplement your training data set with rotated versions of your original images using the
The example below shows how to create a model with the
crop augmentation option that trains for 20 iterations, and that relies on explicit validation data stored in a
Validation directory within your
Provide the resulting
parameters structure to either the
init(training method (if your training data is represented by a
MLImage) or the
init(training method (if your training data is represented by a dictionary) when creating your model.