Calculating Multi-class Dice coefficient when predicating value are not integer

Question

I'm trying to calculating Multi-class Dice coefficient similar like this: How calculate the dice coefficient for multi-class segmentation task using Python?

However, this will require that the classes be integer. For me, as shown below, in the predication, the result I got, some of classes are double. Did I make a mistake or I could simply round them to the nearest integer class:

My code is below:

def down_block(x, filters, kernel_size=(3, 3), padding="same", strides=1):
    c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(x)
    c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(c)
    p = keras.layers.MaxPool2D((2, 2), (2, 2))(c)
    return c, p

def up_block(x, skip, filters, kernel_size=(3, 3), padding="same", strides=1):
    us = keras.layers.UpSampling2D((2, 2))(x)
    concat = keras.layers.Concatenate()([us, skip])
    c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(concat)
    c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(c)
    return c

def bottleneck(x, filters, kernel_size=(3, 3), padding="same", strides=1):
    c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(x)
    c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(c)
    return c 


def UNet():
    f = [16, 32, 64, 128, 256]
    #inputs = keras.layers.Input((image_size, image_size, 3))
    inputs = keras.layers.Input((image_size, image_size, 1))
    
    p0 = inputs
    c1, p1 = down_block(p0, f[0]) #128 -> 64
    c2, p2 = down_block(p1, f[1]) #64 -> 32
    c3, p3 = down_block(p2, f[2]) #32 -> 16
    c4, p4 = down_block(p3, f[3]) #16->8
    
    bn = bottleneck(p4, f[4])
    
    u1 = up_block(bn, c4, f[3]) #8 -> 16
    u2 = up_block(u1, c3, f[2]) #16 -> 32
    u3 = up_block(u2, c2, f[1]) #32 -> 64
    u4 = up_block(u3, c1, f[0]) #64 -> 128
    
    #outputs = keras.layers.Conv2D(1, (1, 1), padding="same", activation="sigmoid")(u4)
    outputs = keras.layers.Conv2D(4, (1, 1), padding="same", activation="softmax")(u4)
    #outputs = keras.layers.Conv2D(1, (1, 1), padding="same", activation="softmax")(u4)
    
    model = keras.models.Model(inputs, outputs)
    return model


model.compile(optimizer="adam",  loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=["acc"] )#,run_eagerly=True)
model.summary()