How to tell if tensorflow is using gpu acceleration from inside python shell

TensorFlow is a popular machine learning framework developed by Google. It supports both CPU and GPU acceleration for training and prediction tasks. If you are running TensorFlow on a machine with a GPU, you might wonder how to check if the framework is actually using GPU acceleration. In this article, we will show you how to do that from inside the Python shell.

First, you need to import the TensorFlow library in your Python script:

import tensorflow as tf

Next, you can use the following code snippet to check if TensorFlow is using GPU acceleration:

print("Is GPU available: ", tf.test.is_gpu_available())

This code snippet will output a boolean value indicating whether TensorFlow is using GPU acceleration or not. If the output is True, it means that TensorFlow is using GPU acceleration. If the output is False, it means that TensorFlow is not using GPU acceleration.

Additionally, you can also check the list of available GPUs that TensorFlow can use:

print("Available GPUs: ", tf.config.experimental.list_physical_devices('GPU'))

This code snippet will output a list of available GPUs that TensorFlow can use for acceleration. If you see a list of GPU devices, it means that TensorFlow is using GPU acceleration.

By following these steps, you can easily check if TensorFlow is using GPU acceleration from inside the Python shell. This can be useful for troubleshooting performance issues or verifying that your GPU is being utilized efficiently during machine learning tasks.