Welcome to the TensorFlow for Beginners tutorial! Whether you're new to machine learning or just starting with TensorFlow, this guide will walk you through the essentials to build your first model. 🌟

What is TensorFlow? 🧠

TensorFlow is an open-source library developed by Google for machine learning and deep learning. It allows you to create complex neural networks and train them on large datasets. 📚
Learn more about TensorFlow's history and features

Getting Started 🧰

1. Installation

Install TensorFlow using pip:

pip install tensorflow

Or create a virtual environment for isolation:

python -m venv tf_env
source tf_env/bin/activate  # On Windows: tf_env\Scripts\activate

2. Basic Concepts

  • Tensors: Multi-dimensional arrays that flow through the computational graph.
    Tensor Example
  • Graphs: Visual representation of operations and data flow.
    Computational Graph
  • Sessions: Execute the graph operations in a controlled environment.

Your First Model 🧪

Let's build a simple MNIST digit classifier using Keras:

import tensorflow as tf
from tensorflow.keras import layers, models

# Load dataset
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

# Build model
model = models.Sequential([
    layers.Flatten(input_shape=(28, 28)),
    layers.Dense(128, activation='relu'),
    layers.Dropout(0.2),
    layers.Dense(10, activation='softmax')
])

# Compile and train
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)

# Evaluate
model.evaluate(x_test, y_test, verbose=2)

This code demonstrates data preprocessing, model architecture, and training a neural network. 📈

Next Steps 📚

Happy coding! 🌐

TensorFlow Logo