⏱️ 50 min
TensorFlow Basics
Get started with Google's deep learning framework
Introduction to TensorFlow
TensorFlow is an end-to-end platform for machine learning. It provides tools for building and deploying ML models at scale. **Key Features:** - Eager execution for intuitive development - Keras API for easy model building - Production deployment with TensorFlow Serving - Multi-platform support (CPU, GPU, TPU)
Building a Neural Network in TensorFlow
Create models with Keras:
python
import tensorflow as tf
from tensorflow import keras
import numpy as np
# Create synthetic data
np.random.seed(42)
X_train = np.random.randn(1000, 20)
y_train = (X_train[:, 0] + X_train[:, 1] > 0).astype(int)
X_test = np.random.randn(200, 20)
y_test = (X_test[:, 0] + X_test[:, 1] > 0).astype(int)
# Build model with Keras Sequential API
model = keras.Sequential([
keras.layers.Dense(64, activation='relu', input_shape=(20,)),
keras.layers.Dropout(0.2),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.2),
keras.layers.Dense(1, activation='sigmoid')
])
# Compile model
model.compile(
optimizer=keras.optimizers.Adam(learning_rate=0.001),
loss='binary_crossentropy',
metrics=['accuracy']
)
# Print model architecture
print("Model Architecture:")
model.summary()
# Train model
history = model.fit(
X_train, y_train,
epochs=20,
batch_size=32,
validation_split=0.2,
verbose=0
)
# Evaluate
test_loss, test_acc = model.evaluate(X_test, y_test, verbose=0)
print(f"\nTest Accuracy: {test_acc * 100:.2f}%")
print(f"Test Loss: {test_loss:.4f}")
# Make predictions
sample_predictions = model.predict(X_test[:5], verbose=0)
print("\nSample Predictions:")
for i, pred in enumerate(sample_predictions):
print(f" Sample {i+1}: {pred[0]:.4f} -> Class {int(pred[0] > 0.5)}")Output:
Model Architecture: _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= dense (Dense) (None, 64) 1344 dropout (Dropout) (None, 64) 0 dense_1 (Dense) (None, 32) 2080 dropout_1 (Dropout) (None, 32) 0 dense_2 (Dense) (None, 1) 33 ================================================================= Total params: 3,457 Trainable params: 3,457 Non-trainable params: 0 Test Accuracy: 99.50% Test Loss: 0.0287 Sample Predictions: Sample 1: 0.9834 -> Class 1 Sample 2: 0.0156 -> Class 0 Sample 3: 0.9921 -> Class 1 Sample 4: 0.0089 -> Class 0 Sample 5: 0.9876 -> Class 1
Custom Training Loop
Advanced TensorFlow usage:
python
import tensorflow as tf
# Create a simple model
class SimpleModel(tf.keras.Model):
def __init__(self):
super().__init__()
self.dense1 = tf.keras.layers.Dense(64, activation='relu')
self.dense2 = tf.keras.layers.Dense(1, activation='sigmoid')
def call(self, inputs):
x = self.dense1(inputs)
return self.dense2(x)
# Initialize
model = SimpleModel()
optimizer = tf.keras.optimizers.Adam(0.001)
loss_fn = tf.keras.losses.BinaryCrossentropy()
# Custom training step
@tf.function
def train_step(x, y):
with tf.GradientTape() as tape:
predictions = model(x, training=True)
loss = loss_fn(y, predictions)
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
return loss
# Training loop
print("Custom Training Loop:")
for epoch in range(10):
epoch_loss = 0
for i in range(0, len(X_train), 32):
batch_x = X_train[i:i+32]
batch_y = y_train[i:i+32]
loss = train_step(batch_x, batch_y)
epoch_loss += loss
print(f"Epoch {epoch + 1}: Loss = {epoch_loss / (len(X_train) / 32):.4f}")Output:
Custom Training Loop: Epoch 1: Loss = 0.6234 Epoch 2: Loss = 0.3891 Epoch 3: Loss = 0.2567 Epoch 4: Loss = 0.1823 Epoch 5: Loss = 0.1345 Epoch 6: Loss = 0.1024 Epoch 7: Loss = 0.0812 Epoch 8: Loss = 0.0661 Epoch 9: Loss = 0.0553 Epoch 10: Loss = 0.0472