In this Python tutorial, we will learn how to find the shape of a TensorFlow in Python. Also, we will cover the following topics.
- TensorFlow get shape of tensor
- TensorFlow get shape of dataset
- TensorFlow get shape as list
- TensorFlow get shape none
- TensorFlow get shape of placeholder
- Tensorflow x.get_shape().as_list()
TensorFlow get shape
- In this section, we will learn how to get the shape in TensorFlow Python.
- To get the shape of a tensor, you can easily use the tf.shape() function. This method will help the user to return the shape of the given tensor. For example, suppose you have a tensor filled with integer numbers and you want to check the shape of the given input tensor.
- To do this task we can easily use the tf.shape() function and it returns the shape property as a scaler input value.
Syntax:
Let’s have a look at the Syntax and understand the working of the tf.shape() function.
tf.shape
(
input,
out_type=tf.dtypes.int32,
name=None
)
- It consists of a few parameters
- input: This parameter indicates the input tensor which we want to operate
- out_type= By default it takes tf.dtypes.int32 value. This is an optional parameter and defines the output type.
- name: This parameter indicates the name of the operation.
Example:
Let’s take an example and check how to get the shape in TensorFlow Python.
Source Code:
#Tensor
import tensorflow as tf
tensor = tf.constant([[[15, 67, 89], [34, 27, 89]],
[[45, 89, 189], [68, 91, 46]]])
result=tf.shape(tensor)
result
In the above code, first, we imported the TensorFlow library and then use the tf.constant() function for creating a tensor. After that, we have declared a variable ‘result’ and assigned the tf.shape() function for getting the shape of a given tensor.
Here is the Screenshot of the following given code.
Also, check: Python TensorFlow reduce_sum
TensorFlow get shape of tensor
- Let us see how to get the shape of the tensor in TensorFlow Python.
- To perform this particular task we are going to use the tf.shape() function for getting the shape of the tensor.
- Next, we will use the tf.compat.v1.disable_eager_execution() for running the session and it will display the array size.
Example:
Let’s take an example and check how to get the shape of Tensor in TensorFlow Python.
Source Code:
#Tensor
import tensorflow as tf
tf.compat.v1.disable_eager_execution()
tensor = tf.constant([[18, 29], [34, 78]])
result = tf.shape(tensor)
print(result) #shape of tensor
with tf.compat.v1.Session() as val:
new_output=val.run(result)
new_output #Display rows and columns dimension
In the following given code, we have created a tensor by using the tf.constant() function, and forgetting the shape of the tensor we have applied the tf.shape() function.
And within this method, we passed tensor as an argument. Once you will execute this code, the output displays the shape of a tensor. After that, we have applied the function tf.compat.v1.disable_eager_execution().
Here is the implementation of the following given code.
Read: Python TensorFlow reduce_mean
TensorFlow get shape of dataset
- In this section, we will learn how to get the shape of dataset in TensorFlow Python.
- To do this task we are going to use the concept of tfds datasets and it specifies the collection of datasets in TensorFlow.
- In Python, tfds is basically used with machine learning and the TensorFlow framework.
- To install this package in your machine, use the pip install tfds-nightly command.
Example:
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds
tensor=tfds.list_builders()
print(tensor)
result=tf.shape(tensor)
result
In the above code first, we imported the tfds library by using tensorflow_datasets as tfds. After that, we have used the datasets named ‘list_builders and it will display the list of available builders. Now, we want to get the shape of given datasets to do this task we have used the tf.shape() function.
Here is the Screenshot of the following given code.
Read: Python TensorFlow one_hot
TensorFlow get shape as list
- Here we will see how to get the TensorFlow tensor shape as a list in Python.
- To perform this particular task, we are going to use the shape.as_list() function.
- This method returns a list of integer values that indicates the shape and the dimension of an array.
Syntax:
Here is the Syntax of the as_list() function in TensorFlow Python.
as_list()
Example:
import tensorflow as tf
tensor = tf.constant([[[15, 67, 89], [34, 27, 89]],
[[45, 89, 189], [68, 91, 46]]])
new_output = tensor.shape.as_list()
new_output
In the following given code, we have imported the TensorFlow library and then create a tensor by using the tf.constant() function. After that, we have used the shape.as_list() function for displaying the shape of tensor in a list.
Here is the implementation of the following given code.
Read: TensorFlow next_batch + Examples
TensorFlow get shape none
- In this section, we will learn how to get the none shape in TensorFlow Python.
- To do this task, we are going to use the tf.keras.layers.Input() function and this method is a tensor object from the underlying backend.
Syntax:
Here is the Syntax of tf.Keras.layers.input() method.
tf.keras.layer.Input
(
shape=None,
batch_size=None,
name=None,
dtype=None,
sparse=False,
tensor=None,
**kwargs
)
Example:
import tensorflow as tf
var = tf.keras.layers.Input((None,None))
var.shape
Also, you can refer to the below screenshot.
Read: Tensorflow get static value
TensorFlow get shape of placeholder
- In this Program, we will learn how to get the shape of placeholder in TensorFlow Python.
- To do this task, we are going to use the tf.compat.v1.placeholder() method and this method allows us to declare our operation and it always fed the data.
Syntax:
Let’s have a look at the Syntax and understand the working of tf.comapt.v1.placeholder().
tf.compat.v1.placeholder
(
dtype,
shape=None,
name=None
)
Example:
import tensorflow as tf
tf.compat.v1.disable_eager_execution()
tens=tf.compat.v1.placeholder(dtype=tf.int32,shape=(300,300))
tens
In the above code, we imported the numpy library and then use the tf.compat.v1.disable_eager_execution() function. After that, we have used tf.compat.v1.placeholder and within this function, we have passed the shape=(300,300)) as an argument.
Here is the execution of the following given code.
Read: TensorFlow Sparse Tensor
Tensorflow x.get_shape().as_list()
- Let us see how to get the shape of TensorFlow by using the x.get_shape().as_list() function in Python.
- To perform this particular task, we are going to use the tensor.get_shape.as_list() function. This method returns a list of integer values that indicates the shape and the dimension of an array.
Example:
import tensorflow as tf
new_tens = tf.constant([[[78, 92, 167], [98, 178, 94]],
[[178, 236, 345], [109, 256, 345]]])
new_result = new_tens.get_shape().as_list()
new_result
Here is the Screenshot of the following given code.
Also, take a look at some more tutorials related to Python.
- What is Scikit Learn in Python
- What is Matplotlib in Python
- What is Pandas in Python
- TensorFlow Tensor to numpy
- Machine Learning using Python
In this tutorial, we have learned how to find the shape of a TensorFlow in Python. Also, we have covered the following topics.
- TensorFlow get shape of tensor
- TensorFlow get shape of dataset
- TensorFlow get shape as list
- TensorFlow get shape none
- TensorFlow get shape of placeholder
- Tensorflow x.get_shape().as_list()
Python is one of the most popular languages in the United States of America. I have been working with Python for a long time and I have expertise in working with various libraries on Tkinter, Pandas, NumPy, Turtle, Django, Matplotlib, Tensorflow, Scipy, Scikit-Learn, etc… I have experience in working with various clients in countries like United States, Canada, United Kingdom, Australia, New Zealand, etc. Check out my profile.