exception when the shape of the label is different from the output of the model
baek2sm opened this issue · comments
Seungbaek Hong commented
When creating an application using MSE Loss, training proceeds even if the shape of the target (label) is different from the shape of the final output of the model.
In this case, it is unlikely to be trained with the correct label values.
If the shape of the label is different from the final output shape of the model,
it would be better to make an exception.