TesorflowLearning

Here’s the exact CMD commands for your setup:

REM 1. Navigate to your target directory
cd C:\Users\IAGhe\OneDrive\Documents\Learning\Python

REM 2. Create a virtual environment (call it 'tf_cpu_env')
python -m venv tf_cpu_env

REM 3. Activate the virtual environment
tf_cpu_env\Scripts\activate

REM 4. Upgrade pip to latest
python -m pip install --upgrade pip

REM 5. Install TensorFlow (CPU) and Jupyter Notebook
pip install tensorflow jupyter ipykernel

REM 6. Make this virtual environment available in Jupyter
python -m ipykernel install --user --name=tf_cpu_env --display-name "Python (tf_cpu_env)"

REM 7. (Optional) Install extra common packages for data science
pip install numpy pandas matplotlib seaborn scikit-learn

REM 8. Launch Jupyter Notebook
jupyter notebook

Step 2 — Verify TensorFlow Installation

Inside a notebook:

import tensorflow as tf
print(tf.__version__)
print("Eager execution:", tf.executing_eagerly())

Output:

t = tf.constant([[1, 2], [3, 4]], dtype=tf.float32)
print(t)
print("Shape:", t.shape)
print("Dtype:", t.dtype)

Output:

t = tf.constant([[1, 2], [3, 4]], dtype=tf.float32)
print(t)
print("Shape:", t.shape)
print("Dtype:", t.dtype)

Output:

# Change dtype
t_int = tf.cast(t, dtype=tf.int32)
print(t_int)

Output:

# Reshape
t_reshaped = tf.reshape(t, (4, 1))
print(t_reshaped)

Output:

a = tf.constant([1, 2, 3], dtype=tf.float32)
b = tf.constant([[1], [2], [3]], dtype=tf.float32)
print(a + b)  # Broadcasting

Output:

tf.math Operations in TensorFlow

import tensorflow as tf

# Example tensors
x = tf.constant([1.0, 2.0, 3.0], dtype=tf.float32)
y = tf.constant([4.0, 5.0, 6.0], dtype=tf.float32)

print("x:", x.numpy())
print("y:", y.numpy())

Output:

# --- Basic arithmetic ---
print("\nAddition:", tf.add(x, y).numpy())       # x + y
print("Subtraction:", tf.subtract(x, y).numpy()) # x - y
print("Multiplication:", tf.multiply(x, y).numpy()) # x * y
print("Division:", tf.divide(x, y).numpy())      # x / y

Output:

# --- Reductions ---
print("\nSum of x:", tf.reduce_sum(x).numpy())     # 1.0 + 2.0 + 3.0
print("Mean of y:", tf.reduce_mean(y).numpy())     # average of y

Output:

# --- Mathematical functions ---
print("\nExponent (e^x):", tf.math.exp(x).numpy())
print("Natural log:", tf.math.log(y).numpy())
print("Square root:", tf.math.sqrt(y).numpy())

Output:

# --- Combining operations ---
z = tf.multiply(x, y)  # elementwise product
result = tf.reduce_mean(tf.math.sqrt(z))
print("\nMean of sqrt(x * y):", result.numpy())

Output: