ValueError: Shapes (10, 1) and (10, 66) are incompatible code example

Example 1: 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

Example 2: ValueError: Shapes (None, 1) and (None, 3) are incompatible

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