Consider the following code that we used to classify the income of adults in the US$.$ inputs tf$.$keras.layers.Dense $($units$32,$ activationrelu, input$\_$shape$[$len $($features$.$columns$))$ hidden tf$.$keras.layers.Dense $($units$32,$ activationrelu$)$ outputs tf$.$keras.layers.Dense $($unitsTO BE FILLED, activation$=$softmax$)$ model tf$.$keras.Sequential $([$inputs $,$ hidden, outputs $)$ loss sparse$\_$categorical$\_$crossentropy optimizer tf$.$keras.optimizers $.$ RMSprop $(0\mathrm{.}001)$ model.compile $($lossloss $,$ optimizer optimizer $,$ metrics accuracy $)$ What was the number of units in the output layer of this deep neural network $?$