PYTHON

ValueError: Shapes (None, 1) and (None, 11) are incompatible keras

#Sam Ayo answers .. linkedin.com/in/sam-ayo
If you use one-hot-encoded for the label/classes like [0, 0, 0, 0, 0, 0, 1]
you need to use categorical_crossentropy
but if you use sparse label/classes like [1, 2, 3, 4, 5, 6, 7]
you need to use sparse_categorical_crossentropy.

shapes (none, 1) and (none, 5) are incompatible

Change Categorical Cross Entropy to Binary Cross Entropy since your output label is binary. Also Change Softmax to Sigmoid since Sigmoid is the proper activation function for binary data

ValueError: Shapes (None, 1) and (None, 3) are incompatible

y_train = to_categorical(y_train, 3)
y_test = to_categorical(y_test, 3)