Sequential Model

A sequential model in TensorFlow is a linear stack of layers, allowing for easy and straightforward building of deep learning models by adding one layer at a time.

fmnist = tf.keras.datasets.fashion_mnist

(training_images, training_labels) ,  (test_images, test_labels) = fmnist.load_data()

training_images = training_images/255.0
test_images = test_images/255.0

model = tf.keras.models.Sequential([tf.keras.layers.Flatten(),
                                    tf.keras.layers.Dense(512, activation=tf.nn.relu), # Try experimenting with this layer
                                    tf.keras.layers.Dense(10, activation=tf.nn.softmax)])

model.compile(optimizer = 'adam',
              loss = 'sparse_categorical_crossentropy')

model.fit(training_images, training_labels, epochs=5)

model.evaluate(test_images, test_labels)

classifications = model.predict(test_images)

print(classifications[0])
print(test_labels[0])

Callbacks

• Callbacks in TensorFlow are functions or objects used to customize and enhance the training process by performing specific actions during or after each training epoch.
• They are commonly employed for tasks like model checkpointing, early stopping, and logging training metrics.

class myCallback(tf.keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if(logs.get('accuracy') >= 0.6): # Experiment with changing this value
      print("\\nReached 60% accuracy so cancelling training!")
      self.model.stop_training = True

callbacks = myCallback()

fmnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels) ,  (test_images, test_labels) = fmnist.load_data()

training_images=training_images/255.0
test_images=test_images/255.0
model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(512, activation=tf.nn.relu),
  tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(training_images, training_labels, epochs=5, callbacks=[callbacks])