Data Api : Valueerror: `y` Argument Is Not Supported When Using Dataset As Input

I have 45000 images of size 224*224, stored as a numpy array. This array, called source_arr has shape 45000,224,224 and it fits in the memory. I divide this array into train, test

Solution 1:

you have source_arr and y_train as numpy array ;so you can do :

data_set = tf.data.Dataset.from_tensor_slices(  (source_arr , y_train) )

if you have source_arr and y_train as tf.dataset :

data_set = tf.data.Dataset.zip( (source_arr , y_train) )