[Python] Arguments `target` and `output` must have the same rank (ndim)

i'm working with a multioutput tensorflow model, just for learning purposes, that should output 1 numerical and 1 categorical data (6 classes).

everything seems to be fine, well-defined, but when i fit the model it errors saying "ValueError: Arguments target and output must have the same rank (ndim). Received: target.shape=(None,), output.shape=(None, 6)"

for simplicity, on output layers I have:

layers.Dense(1, activation='relu', name="output_numerical")(x)
layers.Dense(6, activation='softmax', name="output_categorical")(x)


model is compiled as:

losses = {'output_numerical': 'mse', 'output_categorical': 'categorical_crossentropy'}
loss_weights = {'output_numerical': 1.0, 'output_categorical': 1.0}
model.compile(optimizer=optimizer, loss=losses, loss_weights=loss_weights)


and finally, a sample of features x and labels y:

input_numerical | input_categorical
1.0 | 1
1.1 | 0
1.2 | 3
1.5 | 5
....


output_numerical| output_categorical
2.0 | 5
1.1 | 4
3.2 | 3
4.5 | 2
....


Can anyone help me to fix the problem?

I expect that softmax outputs just 1 number, the expected category, but I suspect that is outputing the probs for each class.

Continue reading...