How to do point-wise categorical crossentropy loss in Keras?

Question

I have a network that produces a 4D output tensor where the value at each position in spatial dimensions (~pixel) is to be interpreted as the class probabilities for that po

Answer 1

You could also not reshape anything and define both softmax and loss on your own. Here is softmax which is applied to the last input dimension (like in tf backend):

def image_softmax(input):
    label_dim = -1
    d = K.exp(input - K.max(input, axis=label_dim, keepdims=True))
    return d / K.sum(d, axis=label_dim, keepdims=True)

and here you have loss (there is no need to reshape anything):

__EPS = 1e-5
def image_categorical_crossentropy(y_true, y_pred):
    y_pred = K.clip(y_pred, __EPS, 1 - __EPS)
    return -K.mean(y_true * K.log(y_pred) + (1 - y_true) * K.log(1 - y_pred))

No further reshapes need.