Output Dimension Of Keras Model

I use ImageDataGenerator to load my training data train_generator = train_datagen.flow_from_directory( directory= TRAIN_PATH, target_size=(224, 224), color_mode='rgb',

Solution 1:

you can solve simply changing the loss from sparse_categorical_crossentropy to categorical_crossentropy.

"categorical" mode in a generator will one-hot encode labels and this not suits with sparse_categorical_crossentropy