(TF2) NN Classification with TF

02. NN Classification with TF

(참고) udemy - TF Developer in 2022

Contents

1. Non-linear activation function
2. Multi-class Classification
3. Learning rate scheduler

1과 거의 동일.

차이점? loss function & output layer

tf.random.set_seed(42)

model = tf.keras.Sequential([
  tf.keras.layers.Dense(100),
  tf.keras.layers.Dense(10),
  tf.keras.layers.Dense(1)
])

# Binary Classification
### loss="binary_crossentropy" 도 OK
model.compile(loss=tf.keras.losses.BinaryCrossentropy(), 
                optimizer=tf.keras.optimizers.SGD(),
                metrics=['accuracy'])

# 3. Fit the model
model.fit(X, y, epochs=5)

(1) Non linear activation function

model = tf.keras.Sequential([
  tf.keras.layers.Dense(4, activation="relu"),
  tf.keras.layers.Dense(4, activation="relu"),
  tf.keras.layers.Dense(1, activation="sigmoid")
])

(2) Multi-class Classification

• input : 28x28 image

model = tf.keras.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(4, activation="relu"),
  tf.keras.layers.Dense(4, activation="relu"),
  tf.keras.layers.Dense(10, activation="softmax") 
])

model.compile(loss = tf.keras.losses.SparseCategoricalCrossentropy(),
                 optimizer=tf.keras.optimizers.Adam(),
                 metrics=["accuracy"])

(3) Learning rate scheduler

• tf.keras.callbacks.LearningRateScheduler
• fit 안의 callbacks argument에 넣는다

lr_scheduler = tf.keras.callbacks.LearningRateScheduler(lambda epoch: 1e-3 * 10**(epoch/20))

# Fit the model
find_lr_history = model_13.fit(train_data,
                               train_labels,
                               epochs=40, 
                               validation_data=(test_data, test_labels),
                               callbacks=[lr_scheduler])