Evaluate multi-IO neural network model
Returns the loss value and the metric values for a multi-input & multi-output model in test mode. Computation is done in batches.
Inputs
-
Model — DynamicObject
The trained model to evaluate.
-
Testing X — DynamicObject
A DynamicObject mapping the input names of the neural network to the correspoding test input data.
-
Testing Y — DynamicObject
A DynamicObject mapping the output names of the neural network to the correspoding test output data.
-
Batch size — Integer
Number of samples per batch of computation.
Outputs
-
Loss — Float
Test loss of the model, taking all outputs into account.
-
Loss of each output — DynamicObject
A DynamicObject mapping the output names to corresponding individual test loss (Float).
-
Metric values — DynamicObject
A DynamicObject mapping metric names to their corresponding value (Float).