View source on GitHub
|
Sets the graph-level random seed for the default graph.
tf.compat.v1.set_random_seed(
seed
)
Migrate to TF2
'tf.compat.v1.set_random_seed' is compatible with eager mode. However, in eager mode this API will set the global seed instead of the graph-level seed of the default graph. In TF2 this API is changed to tf.random.set_seed.
| Used in the tutorials |
|---|
Operations that rely on a random seed actually derive it from two seeds: the graph-level and operation-level seeds. This sets the graph-level seed.
Its interactions with operation-level seeds is as follows:
To illustrate the user-visible effects, consider these examples:
To generate different sequences across sessions, set neither graph-level nor op-level seeds:
a = tf.random.uniform([1])
b = tf.random.normal([1])
print("Session 1")
with tf.compat.v1.Session() as sess1:
print(sess1.run(a)) # generates 'A1'
print(sess1.run(a)) # generates 'A2'
print(sess1.run(b)) # generates 'B1'
print(sess1.run(b)) # generates 'B2'
print("Session 2")
with tf.compat.v1.Session() as sess2:
print(sess2.run(a)) # generates 'A3'
print(sess2.run(a)) # generates 'A4'
print(sess2.run(b)) # generates 'B3'
print(sess2.run(b)) # generates 'B4'
To generate the same repeatable sequence for an op across sessions, set the seed for the op:
a = tf.random.uniform([1], seed=1)
b = tf.random.normal([1])
# Repeatedly running this block with the same graph will generate the same
# sequence of values for 'a', but different sequences of values for 'b'.
print("Session 1")
with tf.compat.v1.Session() as sess1:
print(sess1.run(a)) # generates 'A1'
print(sess1.run(a)) # generates 'A2'
print(sess1.run(b)) # generates 'B1'
print(sess1.run(b)) # generates 'B2'
print("Session 2")
with tf.compat.v1.Session() as sess2:
print(sess2.run(a)) # generates 'A1'
print(sess2.run(a)) # generates 'A2'
print(sess2.run(b)) # generates 'B3'
print(sess2.run(b)) # generates 'B4'
To make the random sequences generated by all ops be repeatable across sessions, set a graph-level seed:
tf.compat.v1.random.set_random_seed(1234)
a = tf.random.uniform([1])
b = tf.random.normal([1])
# Repeatedly running this block with the same graph will generate the same
# sequences of 'a' and 'b'.
print("Session 1")
with tf.compat.v1.Session() as sess1:
print(sess1.run(a)) # generates 'A1'
print(sess1.run(a)) # generates 'A2'
print(sess1.run(b)) # generates 'B1'
print(sess1.run(b)) # generates 'B2'
print("Session 2")
with tf.compat.v1.Session() as sess2:
print(sess2.run(a)) # generates 'A1'
print(sess2.run(a)) # generates 'A2'
print(sess2.run(b)) # generates 'B1'
print(sess2.run(b)) # generates 'B2'
Args |
|---|
seed
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.