Welcome to the TensorFlow introduction! 🚀
TensorFlow is an open-source library for machine learning and deep learning developed by Google. It allows you to create complex neural networks and train models efficiently. Let's dive into the basics!

Getting Started 📦

  1. Install TensorFlow

    TensorFlow Logo

  2. Verify Installation
    Run a simple script to check if TensorFlow is working correctly: 

    import tensorflow as tf
print(tf.__version__)
    Python Logo

Core Concepts 🧠

  • Tensors: The fundamental data structure in TensorFlow, similar to arrays or matrices.
  • Graphs: Represent computations as a series of operations (nodes) and data (edges).
  • Sessions: Execute the graph and manage resources.
Neural Network

Example Code 📜

Here's a basic example using TensorFlow to train a model on the MNIST dataset: 

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

# Load and preprocess data
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train = x_train.reshape(-1, 28*28).astype('float32')/255
x_test = x_test.reshape(-1, 28*28).astype('float32')/255

# Build model
model = models.Sequential([
    layers.Dense(512, activation='relu', input_shape=(28*28,)),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# Train model
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)
Code Sample

Expand Your Knowledge 📘

For deeper insights, check out our TensorFlow Advanced Tutorial or explore Keras documentation.

TensorFlow Workflow