Statistics View
The Statistics View is displayed when training begins, and provides a number of stats about how the model is performing during training:
The following are the key Statistic View controls in the tool bar:
Back to Model: Returns to the Modeling Tool.
Pause: pauses training.
Stop: stops training.
Note
The top of the Statistics view represents what the Training component used in the model is showing (i.e., it will be a unique view for each Training component).
The Statistics View is divided into a number of tabs and panes as described below. Most of these contain a download button that generates a screenshot of that tab's/pane's data:
This can be useful for grabbing snapshots of different statistics (e.g., when you pause training at a certain point).
Input Tab
The Input tab displays a visualization of the current data sample. In the screenshot below, this is a visualization of an image depicting a hand-written digit for the number 5:
Target Tab
The Target tab shows a number of panes with vital statistics including loss and accuracy over all epochs, prediction versus ground truth (for the current data sample), and the predictions made so far for each classification (you want to strive for a single color per category):
Tip: You can toggle display of an element within a graph by clicking on the respective item in the graph's legend.
Map and View Box
At the bottom of the Statistics View are the Map and View Box areas:
The Map displays the model and the View Box displays a view of statistics about the training. When you click on individual components in the Map, the View Box displays statistics for the selected component, allowing you to analyze your model on a more granular level during training.
The View Box contains three tabs described in the following sub sections.
Weights & Output Tab
The Weights & Output tab displays the Component's output on the right, and the weights used to create that output on the left. When training models, watch out for weights that are 0 or not changing.
Bias Tab
The Bias tab displays the bias for the current data sample:
Gradients Tab
The Gradients tab displays the gradient descent for the model:
Tip: Check out the following video for a brief introduction on the importance of gradients during debugging:
Last updated
