when trying to train a CNN with randomly selected small subsets (each same size) of the training data set, I get different results in accuracy (the accuracy varies from 0.75 to 0.85).
I determine the subsets by the following method by varying the value for
random_state = 0, 7, 42,.....
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.1, random_state=..., stratify=y)
Would it be correct to calculate the average of the different accuracies (with standard deviation) in order to get a real estimation? Would this be a correct scientific approach?
I hope and look forward for any help and would be very grateful.