A structure that holds the output of a tff.learning.Model
.
tff.learning.BatchOutput(
loss, predictions, num_examples
)
Used in the notebooks
Attributes |
loss
|
The scalar mean loss on the examples in the batch. If the model
has multiple losses, it is the sum of all the individual losses.
|
predictions
|
Tensor of predictions on the examples. The first dimension
must be the same size (the size of the batch).
|
num_examples
|
Number of examples seen in the batch.
|
Class Variables |
loss
|
|
num_examples
|
|
predictions
|
|