Keras Quick Start Guide 🚀

Welcome to the Keras Quick Start page! Whether you're new to deep learning or just want to get started quickly, Keras provides an intuitive API for building and training neural networks. Here's a concise overview to help you begin:

📦 Installation

To use Keras, ensure you have TensorFlow installed (Keras is integrated with TensorFlow):

pip install tensorflow

📌 Tip: For GPU acceleration, install the tensorflow-gpu version instead.

🧠 Basic Workflow

1. Import Keras

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

2. Build a Model

   model = models.Sequential([
       layers.Dense(64, activation='relu', input_shape=(784,)),
       layers.Dense(10, activation='softmax')
   ])
   

3. Compile the Model

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

4. Train & Evaluate

   model.fit(x_train, y_train, epochs=5)
   model.evaluate(x_test, y_test)
   

📈 Example: MNIST Classification

Here's a simple example using the MNIST dataset:

from tensorflow.keras.datasets import mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(-1, 784).astype('float32') / 255
x_test = x_test.reshape(-1, 784).astype('float32') / 255

model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)

🌐 Expand Your Knowledge

For more advanced tutorials, check out our TensorFlow Quick Start guide. You can also explore Keras documentation for detailed API references.