What are common sources of randomness in Machine L

问题:

Reproducibility is important. In a closed-source machine learning project I'm currently working on it is hard to achieve it. What are the parts to look at?

回答1:

Setting seeds

Computers have pseudo-random number generators which are initialized with a value called the seed. For machine learning, you might need to do the following:

# I've heard the order here is important
import random
random.seed(0)

import numpy as np
np.random.seed(0)

import tensorflow as tf
tf.set_random_seed(0)
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1,
                              inter_op_parallelism_threads=1)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)

from keras import backend as K
K.set_session(sess)  # tell keras about the seeded session

# now import keras stuff

See also: Keras FAQ: How can I obtain reproducible results using Keras during development?

sklearn

sklearn.model_selection.train_test_split has a random_state parameter.

What to check

1. Am I loading the data in the same order every time?
2. Do I initialize the model the same way?
3. Do you use external data that might change?
4. Do you use external state that might change (e.g. datetime.now)?