DojoGojira DojoGojira - 1 month ago 15
Python Question

TensorFlow: Non-repeatable results

The Problem

I have a Python script that uses TensorFlow to create a multilayer perceptron net (with dropout) in order to do binary classification. Even though I've been careful to set both the Python and TensorFlow seeds, I get non-repeatable results. If I run once and then run again, I get different results. I can even run once, quit Python, restart Python, run again and get different results.

What I've Tried

I know some people posted questions about getting non-repeatable results in TensorFlow (e.g., "How to get stable results...", "set_random_seed not working...", "How to get reproducible result in TensorFlow"), and the answers usually turn out to be an incorrect use/understanding of
. I've made sure to implement the solutions given but that has not solved my problem.

A common mistake is not realizing that
is only a graph-level seed and that running the script multiple times will alter the graph, explaining the non-repeatable results. I used the following statement to print out the entire graph and verified (via diff) that the graph is the same even when the results are different.

print [ for n in tf.get_default_graph().as_graph_def().node]

I've also used function calls like
to avoid any changes to the graph even though this is probably overkill.

The (Relevant) Code

My script is ~360 lines long so here are the relevant lines (with snipped code indicated). Any items that are in ALL_CAPS are constants that are defined in my
block below.

import numpy as np
import tensorflow as tf

from copy import deepcopy
from tqdm import tqdm # Progress bar

# --------------------------------- Parameters ---------------------------------

# --------------------------------- Functions ---------------------------------

# ------------------------------ Obtain Train Data -----------------------------

# ------------------------------ Obtain Test Data -----------------------------



# ------------------------- Build the TensorFlow Graph -------------------------


with tf.Graph().as_default():

x = tf.placeholder("float", shape=[None, N_INPUT])
y_ = tf.placeholder("float", shape=[None, N_CLASSES])

# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([N_INPUT, N_HIDDEN_1])),
'h2': tf.Variable(tf.random_normal([N_HIDDEN_1, N_HIDDEN_2])),
'h3': tf.Variable(tf.random_normal([N_HIDDEN_2, N_HIDDEN_3])),
'out': tf.Variable(tf.random_normal([N_HIDDEN_3, N_CLASSES]))

biases = {
'b1': tf.Variable(tf.random_normal([N_HIDDEN_1])),
'b2': tf.Variable(tf.random_normal([N_HIDDEN_2])),
'b3': tf.Variable(tf.random_normal([N_HIDDEN_3])),
'out': tf.Variable(tf.random_normal([N_CLASSES]))

# Construct model
pred = multilayer_perceptron(x, weights, biases, USE_DROP_LAYERS, DROP_KEEP_PROB)

mean1 = tf.reduce_mean(weights['h1'])
mean2 = tf.reduce_mean(weights['h2'])
mean3 = tf.reduce_mean(weights['h3'])

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y_))

regularizers = (tf.nn.l2_loss(weights['h1']) + tf.nn.l2_loss(biases['b1']) +
tf.nn.l2_loss(weights['h2']) + tf.nn.l2_loss(biases['b2']) +
tf.nn.l2_loss(weights['h3']) + tf.nn.l2_loss(biases['b3']))

cost += COEFF_REGULAR * regularizers

optimizer = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(cost)

out_labels = tf.nn.softmax(pred)

sess = tf.InteractiveSession()

tf.get_default_graph().finalize() # Lock the graph as read-only

#Print the default graph in text form
print [ for n in tf.get_default_graph().as_graph_def().node]

# --------------------------------- Training ----------------------------------

print "Start Training"
pbar = tqdm(total = TRAINING_EPOCHS)
for epoch in range(TRAINING_EPOCHS):
avg_cost = 0.0
batch_iter = 0


while batch_iter < BATCH_SIZE:
train_features = []
train_labels = []
batch_segments = random.sample(train_segments, 20)
for segment in batch_segments:
train_labels.append(segment[1]), feed_dict={x: train_features, y_: train_labels})
line_out = "," + str(batch_iter) + "\n"
line_out = ",," + str(, feed_dict={x: train_features, y_: train_labels}))
line_out += "," + str(, feed_dict={x: train_features, y_: train_labels}))
line_out += "," + str(, feed_dict={x: train_features, y_: train_labels})) + "\n"
avg_cost +=, feed_dict={x: train_features, y_: train_labels})/BATCH_SIZE
batch_iter += 1

line_out = ",,,,," + str(avg_cost) + "\n"
pbar.update(1) # Increment the progress bar by one

print "Completed training"

# ------------------------------ Testing & Output ------------------------------

keep_prob = 1.0 # Do not use dropout when testing

print "now reducing mean"
print(, feed_dict={x: test_features, y_: test_labels}))

pred_labels =, feed_dict={x: test_features})

output_accuracy_results(pred_labels, test_labels)


What's not repeatable

As you can see, I'm outputting results during each epoch to a file and also printing out accuracy numbers at the end. None of these match from run to run, even though I believe I've set the seed(s) correctly. I've used both

Please let me know if I need to provide more information. And thanks in advance for any help.


Set-up details

TensorFlow version 0.8.0 (CPU only)

Enthought Canopy version 1.7.2 (Python 2.7, not 3.+)

Mac OS X version 10.11.3


You need to set operation level seed in addition to graph-level seed, ie

a = tf.constant([1, 1, 1, 1, 1], dtype=tf.float32)
graph_level_seed = 1
operation_level_seed = 1
b = tf.nn.dropout(a, 0.5, seed=operation_level_seed)