Prediction

Each model graph has at least one prediction output. The prediction type is set to each prediction, and defines the associated labels.
Use the leap_binder.add_prediction function to add a prediction type to the list or prediction types. From this list, a type can be assigned to each prediction output.
Example of usage:
leap_binder.add_prediction(
    name='toxicity',
    labels=['non-toxic','toxic']
)
For more info, see leap_binder.add_prediction.
In the Network view, each prediction (output) node can be pointed to its corresponding Prediction Type in the Layer Details panel.
Guides
Full examples can be found at the Dataset Integration section of the following guides:
​MNIST Guide​
​IMDB Guide​
Visualizer Function
Custom Metrics
Last modified 11d ago