The key topics discussed in this course are summarized below. The overview material is available for download at the end of this page.

Tensorflow Set Up

Instalation

pip install tensorflow

Import

# Import the TensorFlow library with the alias tf
import tensorflow as tf

Tensor Types

Simple Tensor Creation

# Create a 1D tensor
tensor_1D = tf.constant([1, 2, 3])

# Create a 2D tensor
tensor_2D = tf.constant([[1, 2, 3], [4, 5, 6]])

# Create a 3D tensor
tensor_3D = tf.constant([[[1, 2], [3, 4]], [[5, 6],[7, 8]]])

Tensor Properties

• Rank: it tells you the number of dimensions present in the tensor. For instance, a matrix has a rank of 2. You can get the rank of the tensor using the .ndim attribute:

print(f'Rank of a tensor: {tensor.ndim}')

• Shape: this describes how many values exist in each dimension. A 2x3 matrix has a shape of (2, 3). The length of the shape parameter matches the tensor's rank (its number of dimensions). You can get the the shape of the tensor by the .shape attribute:

print(f'Shape of a tensor: {tensor.shape}')

• Types: Tensors come in various data types. While there are many, some common ones include float32, int32, and string. You can get the the data type of the tensor by the .dtype attribute:

print(f'Data type of a tensor: {tensor.dtype}')

Tensor Axes

Applications of Tensors

• Table Data

• Text Sequences

• Numerical Sequences

• Image Processing

• Video Processing

Batches

Tensor Creation Methods

# Create a 2x2 constant tensor
tensor_const = tf.constant([[1, 2], [3, 4]])

# Create a variable tensor
tensor_var = tf.Variable([[1, 2], [3, 4]])

# Zero tensor of shape (3, 3)
tensor_zeros = tf.zeros((3, 3))

# Ones tensor of shape (2, 2)
tensor_ones = tf.ones((2, 2))

# Tensor of shape (2, 2) filled with 6
tensor_fill = tf.fill((2, 2), 6)

# Generate a sequence of numbers starting from 0, ending at 9
tensor_range = tf.range(10)

# Create 5 equally spaced values between 0 and 10
tensor_linspace = tf.linspace(0, 10, 5)

# Tensor of shape (2, 2) with random values normally distributed 
tensor_random = tf.random.normal((2, 2), mean=4, stddev=0.5)

# Tensor of shape (2, 2) with random values uniformly distributed 
tensor_random = tf.random.uniform((2, 2), minval=-2, maxval=2)

Convertions

• NumPy to Tensor

# Create a NumPy array based on a Python list
numpy_array = np.array([[1, 2], [3, 4]])

# Convert a NumPy array to a tensor
tensor_from_np = tf.convert_to_tensor(numpy_array)

• Pandas to Tensor

# Create a DataFrame based on dictionary
df = pd.DataFrame({'A': [1, 2], 'B': [3, 4]})

# Convert a DataFrame to a tensor
tensor_from_df = tf.convert_to_tensor(df.values)

• Constant Tensor to a Variable Tensor

# Create a variable from a tensor
tensor = tf.random.normal((2, 3))
variable_1 = tf.Variable(tensor)

# Create a variable based on other generator
variable_2 = tf.Variable(tf.zeros((2, 2)))

Data Types

# Creating a tensor of type float16
tensor_float = tf.constant([1.2, 2.3, 3.4], dtype=tf.float16)

# Convert tensor_float from float32 to int32
tensor_int = tf.cast(tensor_float, dtype=tf.int32)

Arithmetic

• Addition

c1 = tf.add(a, b)  
c2 = a + b

# Changes the object inplace without creating a new one
a.assign_add(b)

• Subtraction

c1 = tf.subtract(a, b)  
c2 = a - b 

# Inplace substraction
a.assign_sub(b)

• Element-wise Multiplication

c1 = tf.multiply(a, b)  
c2 = a * b

• Division

c1 = tf.divide(a, b)  
c2 = a / b 

Broadcasting

Linear Algebra

• Matrix Multiplication

product1 = tf.matmul(matrix1, matrix2)
product2 = matrix1 @ matrix2

• Matrix Inversion

inverse_mat = tf.linalg.inv(matrix)

• Transpose

transposed = tf.transpose(matrix)

• Dot Product

# Dot product along axes
dot_product_axes1 = tf.tensordot(matrix1, matrix2, axes=1)
dot_product_axes0 = tf.tensordot(matrix1, matrix2, axes=0)

Reshape

# Create a tensor with shape (3, 2)
tensor = tf.constant([[1, 2], [3, 4], [5, 6]])

# Reshape the tensor to shape (2, 3)
reshaped_tensor = tf.reshape(tensor, (2, 3))

Slicing

# Create a tensor
tensor = tf.constant([[1, 2, 3], [4, 5, 6], [7, 8, 9]])

# Slice tensor to extract sub-tensor from index (0, 1) of size (1, 2)
sliced_tensor = tf.slice(tensor, begin=(0, 1), size=(1, 2))

# Slice tensor to extract sub-tensor from index (1, 0) of size (2, 2)
sliced_tensor = tf.slice(tensor, (1, 0), (2, 2))

Modifying with Slicing

# Create a tensor
tensor = tf.Variable([[1, 2, 3], [4, 5, 6], [7, 8, 9]])

# Change the entire first row 
tensor[0, :].assign([0, 0, 0])

# Modify the second and the third columns 
tensor[:, 1:3].assign(tf.fill((3,2), 1))

Concatenating

# Create two tensors
tensor1 = tf.constant([[1, 2, 3], [4, 5, 6]])
tensor2 = tf.constant([[7, 8, 9]])

# Concatenate tensors vertically (along rows)
concatenated_tensor = tf.concat([tensor1, tensor2], axis=0)

# Concatenate tensors horizontally (along columns)
concatenated_tensor = tf.concat([tensor3, tensor4], axis=1)

Reduction Operations

# Calculate sum of all elements
total_sum = tf.reduce_sum(tensor)

# Calculate mean of all elements
mean_val = tf.reduce_mean(tensor)

# Determine the maximum value
max_val = tf.reduce_max(tensor)

# Find the minimum value
min_val = tf.reduce_min(tensor)

Gradient Tape

# Define input variables
x = tf.Variable(tf.fill((2, 3), 3.0))
z = tf.Variable(5.0)

# Start recording the operations
with tf.GradientTape() as tape:
    # Define the calculations
    y = tf.reduce_sum(x * x + 2 * z)
    
# Extract the gradient for the specific inputs (x and z)
grad = tape.gradient(y, [x, z])

print(f"The gradient of y with respect to x is:\n{grad[0].numpy()}")
print(f"The gradient of y with respect to z is: {grad[1].numpy()}")

@tf.function

@tf.function
def compute_gradient_conditional(x):
    with tf.GradientTape() as tape:
        if tf.reduce_sum(x) > 0:
            y = x * x
        else:
            y = x * x * x
    return tape.gradient(y, x)

x = tf.constant([-2.0, 2.0])
grad = compute_gradient_conditional(x)
print(f"The gradient at x = {x.numpy()} is {grad.numpy()}")