# In[ ]: y_test_pred = classifier.predict_labels(dists, k=5) num_correct = np.sum(y_test_pred == y_test) accuracy = float(num_correct) / num_test print 'Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy) # You should expect to see a slightly better performance than with `k = 1`. # In[ ]: # Now lets speed up distance matrix computation by using partial vectorization # with one loop. Implement the function compute_distances_one_loop and run the # code below: dists_one = classifier.compute_distances_one_loop(X_test) # To ensure that our vectorized implementation is correct, we make sure that it # agrees with the naive implementation. There are many ways to decide whether # two matrices are similar; one of the simplest is the Frobenius norm. In case # you haven't seen it before, the Frobenius norm of two matrices is the square # root of the squared sum of differences of all elements; in other words, reshape # the matrices into vectors and compute the Euclidean distance between them. difference = np.linalg.norm(dists - dists_one, ord='fro') print 'Difference was: %f' % (difference, ) if difference < 0.001: print 'Good! The distance matrices are the same' else: print 'Uh-oh! The distance matrices are different'
plt.show()
print("set k=1 and test the data......")
# Now implement the function predict_labels and run the code below:
# We use k = 1 (which is Nearest Neighbor).
y_test_pred = classifier.predict_labels(dists, k=1)
# Compute and print the fraction of correctly predicted examples
num_correct = np.sum(y_test_pred == y_test)
accuracy = float(num_correct) / num_test
print('Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy))
print("use compute_distances_one_loop to calculate the dists.....")
# Now lets speed up distance matrix computation by using partial vectorization
# with one loop. Implement the function compute_distances_one_loop and run the
# code below:
dists_one = classifier.compute_distances_one_loop(X_test)
# To ensure that our vectorized implementation is correct, we make sure that it
# agrees with the naive implementation. There are many ways to decide whether
# two matrices are similar; one of the simplest is the Frobenius norm. In case
# you haven't seen it before, the Frobenius norm of two matrices is the square
# root of the squared sum of differences of all elements; in other words, reshape
# the matrices into vectors and compute the Euclidean distance between them.
print("test the difference between two loop and one loop........")
difference = np.linalg.norm(dists - dists_one, ord='fro')
print('Difference was: %f' % (difference, ))
if difference < 0.001:
print('Good! The distance matrices are the same')
else:
print('Uh-oh! The distance matrices are different')
print("use compute_distances_no_loop to calculate the dists.....")
y_train = y_train[mask]
num_test = 500
mask = list(range(num_test))
x_test = x_test[mask]
y_test = y_test[mask]
x_train = np.reshape(x_train,
(x_train.shape[0], -1)) #reshape the image data into rows
x_test = np.reshape(x_test, (x_test.shape[0], -1))
from classifiers import KNearestNeighbor
classifier = KNearestNeighbor()
classifier.train(x_train, y_train)
dists = classifier.compute_distances_one_loop(x_test)
num_folds = 5
k_choices = [1, 3, 5, 8, 10, 12, 15, 20, 50, 100]
x_train_folds = []
y_train_folds = []
x_train_folds = np.array_split(x_train, num_folds)
y_train_folds = np.array_split(y_train, num_folds)
k_to_accuracies = {}
for i in k_choices:
k_to_accuracies[i] = []
# y_test_pred = classifier.predict_labels(dists, k = 5)
# num_correct = np.sum(y_test == y_test_pred)