how about if we have more than 3 classes and how to predict if we have more than 3 classes? about u-net-with-multiple-classification HOT 1 OPEN

i have trained the model for 5 classes
but the prdiction shape is like (1,512,512,5)

`
c1 = [0,0,255] #red
c2 = [0,250,0] #green
c3 = [0,250,255]
c4 = [255,250,0]
c5= [128,128,0]
c6 = [55,55,0]
Unlabelled = [0,0,0]

COLOR_DICT = np.array([ c1, c2,c3,c4,c5,c6, Unlabelled])
class_name = [ 'c1', 'c2', 'c3','c4','c5','c6', 'None'] # You must define by yourself

def labelVisualize(num_class, color_dict, img):
img_out = np.zeros(img[:,:,0].shape + (3,))
for i in range(img.shape[0]):
for j in range(img.shape[1]):
index_of_class = np.argmax(img[i,j])
#print(index_of_class)
img_out[i,j] = color_dict[index_of_class]
return img_out

after this im getting ouput as only one color is filled to entire image
please suggest how to solve this problem ?

from u-net-with-multiple-classification.