def print_log_probs_by_digit_class(model):
"""Print the average log-probability of images in each digit class."""
X = util.read_mnist_images(TRAIN_IMAGES_FILE)
y = util.read_mnist_labels(TRAIN_LABELS_FILE)
X_test = util.read_mnist_images(TEST_IMAGES_FILE)
y_test = util.read_mnist_labels(TEST_LABELS_FILE)
print('Training set')
for digit in range(10):
X_curr = X[y == digit, :]
loglik = model.log_likelihood(X_curr) / X_curr.shape[0]
print('Average log-probability of a {} image: {:1.3f}'.format(
digit, loglik))
print()
print('Test set')
for digit in range(10):
X_curr = X_test[y_test == digit, :]
loglik = model.log_likelihood(X_curr) / X_curr.shape[0]
print('Average log-probability of a {} image: {:1.3f}'.format(
digit, loglik))
print()
# Call some extra useful things to answer Conceptual Q3
for_q3(model, X, y)
def train_from_labels(prior=None, show=True):
"""Fit the mixture model using the labeled MNIST data. There are 10 mixture components,
one corresponding to each of the digit classes."""
X = util.read_mnist_images(TRAIN_IMAGES_FILE)
y = util.read_mnist_labels(TRAIN_LABELS_FILE)
X_test = util.read_mnist_images(TEST_IMAGES_FILE)
num_data, num_pixels = X.shape
if prior is None:
prior = Prior.default_prior()
model = Model.random_initialization(prior, 10, IMAGE_DIM**2)
R = np.zeros((num_data, 10))
R[np.arange(num_data), y] = 1.
model.params.pi = model.update_pi(R)
model.params.theta = model.update_theta(X, R)
# mask which includes top half of pixels
M = np.zeros(X.shape, dtype=int)
M[:, :M.shape[1] // 2] = 1
if show:
model.visualize_components()
try:
model.visualize_predictions(X[:64, :], M[:64, :])
except:
print('Posterior predictive distribution not implemented yet.')
print('Training log-likelihood:', model.log_likelihood(X) / num_data)
print('Test log-likelihood:',
model.log_likelihood(X_test) / X_test.shape[0])
return model
def print_log_probs_by_digit_class(model):
X = util.read_mnist_images(TRAIN_IMAGES_FILE)
y = util.read_mnist_labels(TRAIN_LABELS_FILE)
X_test = util.read_mnist_images(TEST_IMAGES_FILE)
y_test = util.read_mnist_labels(TEST_LABELS_FILE)
print('Training set')
for digit in range(10):
X_curr = X[y == digit, :]
loglik = model.log_likelihood(X_curr) / X_curr.shape[0]
print('Average log-probability of a {} image: {:1.3f}'.format(
digit, loglik))
print()
print('Test set')
for digit in range(10):
X_curr = X_test[y_test == digit, :]
loglik = model.log_likelihood(X_curr) / X_curr.shape[0]
print('Average log-probability of a {} image: {:1.3f}'.format(
digit, loglik))
print()
def print_part_1_values():
"""Print a set of values that we use to check the correctness of the implementation in Part 1."""
NUM_IMAGES = 50
X = util.read_mnist_images(TRAIN_IMAGES_FILE)
y = util.read_mnist_labels(TRAIN_LABELS_FILE)
X, y = X[:NUM_IMAGES, :], y[:NUM_IMAGES]
num_data, num_pixels = X.shape
prior = Prior(2., 3., 4.)
model = Model.random_initialization(prior, 10, IMAGE_DIM**2)
R = np.zeros((num_data, 10))
R[np.arange(num_data), y] = 0.9
R += 0.01
model.params.pi = model.update_pi(R)
model.params.theta = model.update_theta(X, R)
print('pi[0]', model.params.pi[0])
print('pi[1]', model.params.pi[1])
print('theta[0, 239]', model.params.theta[0, 239])
print('theta[3, 298]', model.params.theta[3, 298])
