When I repeatedly run tf.estimator.LinearRegressor
the results are slightly different each time. I'm guessing that's because of the shuffle=True
here:
input_fn = tf.estimator.inputs.numpy_input_fn(
{"x": x_train}, y_train, batch_size=4, num_epochs=None, shuffle=True)
Which is fine as far as it goes, but when I try to make it deterministic by seeding the random number generators in both np and tf:
np.random.seed(1)
tf.set_random_seed(1)
The results are still slightly different each time. What am I missing?
Aucun commentaire:
Enregistrer un commentaire