The Peltarion Platform keeps improving, functionality by functionality. Let's see what happened to the platform in February!
Explore our new Knowledge center
Support for multi-class classification models
Support for multi-class classification models with higher dimensionality targets is now on the platform. Previously, each row in the dataset had to correspond to exactly one class. We now allow targets of higher dimensionality (e.g., a target that is a vector of different classes, or a target that is an image with one class per pixel). This unlocks use cases such as multi-class semantic segmentation of images.
To train a multi-class target model, the target data can be represented by a numpy array, where the last axis is interpreted as the class label and needs to be one-hot-encoded before importing into the platform.
Visualizations for higher dimensionality targets
Visualizations for higher dimensionality targets on the Evaluation page are now available. Previously, the metrics under Model evaluation were only computed when the target corresponded to exactly one class or to exactly one numeric value. We now also provide the graphs for multi-dimensional targets (e.g., a vector of numeric values or a target image with one class per pixel).
In the case of a classification problem with a multi-dimensional target, the confusion matrix is sampled to a maximum of 500,000 values. For a multi-dimensional target, each value in the confusion matrix corresponds to a vector element, or to a pixel in the target image. This means that the total number of values in the confusion matrix will be many more than the number of samples in the dataset.
In the case of a regression problem with a multi-dimensional target, each dot in the scatter plot represents an element in the target vector or a pixel value in the target image. For visibility reasons, the scatter plot is sampled to show a maximum of 500 data points. The error distribution plot is based on 5,000 sampled values.