9951 explained code solutions for 126 technologies

python-tensorflowHow can I install and use TensorFlow on a Windows machine using Python?

  1. Install Python: First, you need to install Python 3.6 or above from the Python website.

  2. Install TensorFlow: After Python is installed, you can install TensorFlow with the command pip install tensorflow in the command line.

  3. Test Installation: To test the installation, you can run the following code block:

import tensorflow as tf


Output example


  1. Create a Graph: After the installation is verified, you can create a graph in TensorFlow using code such as the following:
# Create a graph
g = tf.Graph()

# Establish the graph as the default one
with g.as_default():
  # Assemble a graph consisting of the following three operations:
  #   * Two tf.constant operations to create the operands.
  #   * One tf.add operation to add the two operands.
  x = tf.constant(8, name="x_const")
  y = tf.constant(5, name="y_const")
  my_sum = tf.add(x, y, name="x_y_sum")
  1. Run the Graph: To run the graph, you can use the following code:
# Create a session
with tf.Session() as sess:
  # Run the graph and store the output
  output = sess.run(my_sum)

Output example


  1. Clean Up: Finally, you can close the session and the graph by running the following code:
  1. Additional Resources: For more information, you can refer to the TensorFlow documentation.

Edit this code on GitHub