Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
43 views

Introduction To Variables - TensorFlow Core

This document introduces TensorFlow variables. Variables are created using tf.Variable and represent shared, persistent state that can be updated in a program. Variables behave similarly to tensors but represent values that can be changed by running ops on them. The document covers how to create, assign, name, place and manage variables.

Uploaded by

zwd.slmn
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
43 views

Introduction To Variables - TensorFlow Core

This document introduces TensorFlow variables. Variables are created using tf.Variable and represent shared, persistent state that can be updated in a program. Variables behave similarly to tensors but represent values that can be changed by running ops on them. The document covers how to create, assign, name, place and manage variables.

Uploaded by

zwd.slmn
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Introduction to Variables

Run in
Google (https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/guide/variab
Colab

A TensorFlow variable is the recommended way to represent shared, persistent state your
program manipulates. This guide covers how to create, update, and manage instances of
tf.Variable (https://www.tensorflow.org/api_docs/python/tf/Variable) in TensorFlow.

Variables are created and tracked via the tf.Variable


 (https://www.tensorflow.org/api_docs/python/tf/Variable) class. A tf.Variable
 (https://www.tensorflow.org/api_docs/python/tf/Variable) represents a tensor whose value can be
changed by running ops on it. Specific ops allow you to read and modify the values of this
tensor. Higher level libraries like tf.keras (https://www.tensorflow.org/api_docs/python/tf/keras)
use tf.Variable (https://www.tensorflow.org/api_docs/python/tf/Variable) to store model
parameters.

Setup
This notebook discusses variable placement. If you want to see on what device your variables
are placed, uncomment this line.

import tensorflow as tf

# Uncomment to see where your variables get placed (see below)


# tf.debugging.set_log_device_placement(True)

2022-12-14 03:58:16.819989: W tensorflow/compiler/xla/stream_executor/platform/d


2022-12-14 03:58:16.820083: W tensorflow/compiler/xla/stream_executor/platform/d
2022-12-14 03:58:16.820092: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:
Create a variable
To create a variable, provide an initial value. The tf.Variable
 (https://www.tensorflow.org/api_docs/python/tf/Variable) will have the same dtype as the
initialization value.

my_tensor = tf.constant([[1.0, 2.0], [3.0, 4.0]])


my_variable = tf.Variable(my_tensor)

# Variables can be all kinds of types, just like tensors


bool_variable = tf.Variable([False, False, False, True])
complex_variable = tf.Variable([5 + 4j, 6 + 1j])

A variable looks and acts like a tensor, and, in fact, is a data structure backed by a tf.Tensor
 (https://www.tensorflow.org/api_docs/python/tf/Tensor). Like tensors, they have a dtype and a
shape, and can be exported to NumPy.

print("Shape: ", my_variable.shape)


print("DType: ", my_variable.dtype)
print("As NumPy: ", my_variable.numpy())

Shape: (2, 2)
DType: <dtype: 'float32'>
As NumPy: [[1. 2.]
[3. 4.]]

Most tensor operations work on variables as expected, although variables cannot be reshaped.

print("A variable:", my_variable)


print("\nViewed as a tensor:", tf.convert_to_tensor(my_variable))
print("\nIndex of highest value:", tf.math.argmax(my_variable))

# This creates a new tensor; it does not reshape the variable.


print("\nCopying and reshaping: ", tf.reshape(my_variable, [1,4]))
A variable: <tf.Variable 'Variable:0' shape=(2, 2) dtype=float32, numpy=
array([[1., 2.],
[3., 4.]], dtype=float32)>

Viewed as a tensor: tf.Tensor(


[[1. 2.]
[3. 4.]], shape=(2, 2), dtype=float32)

Index of highest value: tf.Tensor([1 1], shape=(2,), dtype=int64)

Copying and reshaping: tf.Tensor([[1. 2. 3. 4.]], shape=(1, 4), dtype=float32)

As noted above, variables are backed by tensors. You can reassign the tensor using
tf.Variable.assign (https://www.tensorflow.org/api_docs/python/tf/Variable#assign). Calling
assign does not (usually) allocate a new tensor; instead, the existing tensor's memory is
reused.

a = tf.Variable([2.0, 3.0])
# This will keep the same dtype, float32
a.assign([1, 2])
# Not allowed as it resizes the variable:
try:
  a.assign([1.0, 2.0, 3.0])
except Exception as e:
print(f"{type(e).__name__}: {e}")

ValueError: Cannot assign value to variable ' Variable:0': Shape mismatch.The va

If you use a variable like a tensor in operations, you will usually operate on the backing tensor.

Creating new variables from existing variables duplicates the backing tensors. Two variables
will not share the same memory.

a = tf.Variable([2.0, 3.0])
# Create b based on the value of a
b = tf.Variable(a)
a.assign([5, 6])

# a and b are different


print(a.numpy())
print(b.numpy())

# There are other versions of assign


print(a.assign_add([2,3]).numpy()) # [7. 9.]
print(a.assign_sub([7,9]).numpy()) # [0. 0.]

[5. 6.]
[2. 3.]
[7. 9.]
[0. 0.]

Lifecycles, naming, and watching


In Python-based TensorFlow, tf.Variable (https://www.tensorflow.org/api_docs/python/tf/Variable)
instance have the same lifecycle as other Python objects. When there are no references to a
variable it is automatically deallocated.

Variables can also be named which can help you track and debug them. You can give two
variables the same name.

# Create a and b; they will have the same name but will be backed by
# different tensors.
a = tf.Variable(my_tensor, name="Mark")
# A new variable with the same name, but different value
# Note that the scalar add is broadcast
b = tf.Variable(my_tensor + 1, name="Mark")

# These are elementwise-unequal, despite having the same name


print(a == b)
tf.Tensor(
[[False False]
[False False]], shape=(2, 2), dtype=bool)

Variable names are preserved when saving and loading models. By default, variables in models
will acquire unique variable names automatically, so you don't need to assign them yourself
unless you want to.

Although variables are important for differentiation, some variables will not need to be
differentiated. You can turn off gradients for a variable by setting trainable to false at
creation. An example of a variable that would not need gradients is a training step counter.

step_counter = tf.Variable(1, trainable=False)

Placing variables and tensors


For better performance, TensorFlow will attempt to place tensors and variables on the fastest
device compatible with its dtype. This means most variables are placed on a GPU if one is
available.

However, you can override this. In this snippet, place a float tensor and a variable on the CPU,
even if a GPU is available. By turning on device placement logging (see Setup
 (#scrollTo=xZoJJ4vdvTrD)), you can see where the variable is placed.

Note: Although manual placement works, using distribution strategies (/guide/distributed_training) can be a


more convenient and scalable way to optimize your computation.

If you run this notebook on different backends with and without a GPU you will see different
logging. Note that logging device placement must be turned on at the start of the session.

with tf.device('CPU:0'):

# Create some tensors


  a = tf.Variable([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
  b = tf.constant([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]])
  c = tf.matmul(a, b)

print(c)

tf.Tensor(
[[22. 28.]
[49. 64.]], shape=(2, 2), dtype=float32)

It's possible to set the location of a variable or tensor on one device and do the computation on
another device. This will introduce delay, as data needs to be copied between the devices.

You might do this, however, if you had multiple GPU workers but only want one copy of the
variables.

with tf.device('CPU:0'):
  a = tf.Variable([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
  b = tf.Variable([[1.0, 2.0, 3.0]])

with tf.device('GPU:0'):
# Element-wise multiply
  k = a * b

print(k)

tf.Tensor(
[[ 1. 4. 9.]
[ 4. 10. 18.]], shape=(2, 3), dtype=float32)

Note: Because tf.config.set_soft_device_placement


 (https://www.tensorflow.org/api_docs/python/tf/config/set_soft_device_placement) is turned on by default,
even if you run this code on a device without a GPU, it will still run. The multiplication step will happen on the
CPU.
For more on distributed training, refer to the guide (/guide/distributed_training).

Next steps
To understand how variables are typically used, see our guide on automatic differentiation
 (/guide/autodiff).

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License
 (https://creativecommons.org/licenses/by/4.0/), and code samples are licensed under the Apache 2.0 License
 (https://www.apache.org/licenses/LICENSE-2.0). For details, see the Google Developers Site Policies
 (https://developers.google.com/site-policies). Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2022-12-15 UTC.

You might also like