Error when checking target: expected dense_3 to have shape (3,) but got array with shape (1,)

Question

I am working on training a VGG16-like model in Keras, on a 3 classes subset from Places205, and encountered the following error:

ValueError: Error when chec         


        

Answer 1

For me, this worked.

from keras.utils import to_categorical

num_labels=10 #for my case

train_labels=to_categorical(train_labels,10)
test_labels=to_categorical(test_labels,10)

Specifying the number of labels as an argument while categorically encoding my labels helped train effectively on my training set.