TensorFlow is an open-source machine learning framework developed by Google that allows you to build and train machine learning models. In this tutorial, we will cover the basics of TensorFlow in 100 seconds.

1. Installation:
   To get started with TensorFlow, you need to install it on your machine. You can install it using pip by running the following command:

   pip install tensorflow

2. Creating a TensorFlow graph:
   In TensorFlow, you define your model using a computational graph. This graph represents the operations that will be performed on the data to generate the output. Here’s an example of creating a simple graph that adds two numbers:

   
   import tensorflow as tf

Define the input nodes

a = tf.constant(2)
b = tf.constant(3)

Define the operation node

c = a + b

Create a session and run the graph

with tf.Session() as sess:
result = sess.run(c)
print(result)

3. Running the graph:
To run the graph and get the output of the operations, you need to create a session and run it. The `sess.run()` method is used to run a specific node in the graph and get its output.

4. Building a model:
To build a machine learning model using TensorFlow, you need to define the input nodes, the model architecture, the loss function, and the optimizer. Here's an example of building a simple neural network model:
```python
import tensorflow as tf

# Define the input node (a placeholder for the input data)
x = tf.placeholder(tf.float32, shape=[None, 784])
y_true = tf.placeholder(tf.float32, shape=[None, 10])

# Define the model architecture
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y_pred = tf.nn.softmax(tf.matmul(x, W) + b)

# Define the loss function
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_true * tf.log(y_pred), reduction_indices=[1]))

# Define the optimizer
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

1. Training the model:
   To train the model, you need to iterate over the training data and update the model parameters using the optimizer. Here’s an example of training the model:

   
   import tensorflow as tf

Define the training data

x_train, y_train = …

with tf.Session() as sess:
sess.run(tf.global_variables_initializer())

for i in range(1000):
    sess.run(optimizer, feed_dict={x: x_train, y_true: y_train})

# Evaluate the model
correct_prediction = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y_true, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: x_train, y_true: y_train}))

6. Conclusion:
In this tutorial, we covered the basics of TensorFlow, including how to create a graph, run it, build a model, and train it. TensorFlow is a powerful tool for building and training machine learning models, and it offers a wide range of functionalities for deep learning and other machine learning tasks.