Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import tensorflow as tf
- import numpy as np
- # Import training data
- mnist = tf.keras.datasets.mnist
- # Initialize training data
- (x_train, y_train), (x_test, y_test) = mnist.load_data()
- x_train, x_test = x_train / 255.0, x_test / 255.0
- # Create the neural network
- model = tf.keras.models.Sequential([
- tf.keras.layers.Flatten(input_shape=(28, 28)),
- tf.keras.layers.Dense(128, activation='relu'),
- tf.keras.layers.Dropout(0.2),
- tf.keras.layers.Dense(10)
- ])
- loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
- predictions = model(x_train[:1]).numpy()
- loss_fn(y_train[:1], predictions).numpy()
- # Prepare for training the network
- model.compile(optimizer='adam',
- loss=loss_fn,
- metrics=['accuracy'])
- predictions = model(x_train[:1]).numpy()
- # Train the network
- model.fit(x_train, y_train, epochs=5)
- #Evaluate the network
- model.evaluate(x_test, y_test, verbose=2)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement