class ImageLSH(object):
def __init__(self, input_dir, get_node=default_get_node):
self.last_time = time.time()
self.get_node = get_node
self._create_from_dir_recur(input_dir)
def record(self):
last = self.last_time
self.last_time = time.time()
print "Spent:",self.last_time - last
def _create_from_dir_recur(self, input_dir):
print "Start searching for mat files in", input_dir
matches = []
for root, dirnames, filenames in os.walk(input_dir):
for filename in fnmatch.filter(filenames, '*.mat'):
matches.append(os.path.join(root, filename))
print "Found %d files."
self.record()
self.lsh = LSHash(8, 784)
for f in matches:
n = self.get_node(f)
self.lsh.index(n.feature, extra_data=n.path)
print "Done constructing tree."
self.record()
def get_nearest_neighbors(self, mat_file, k):
node = self.get_node(mat_file)
return self.lsh.query(node.feature, num_results=k)
print "Done searching. Elapsed: %s" % (time.time() - self.start_time)
def _create_from_dir_recur(self, input_dir):
print "Start searching for mat files in", input_dir
matches = []
for root, dirnames, filenames in os.walk(input_dir):
for filename in fnmatch.filter(filenames, '*.mat'):
matches.append(os.path.join(root, filename))
print "Found %d files."
self.record()
self.lsh = LSHash(8, 784)
for f in matches:
n = self.get_node(f)
self.lsh.index(n.feature, extra_data=n.path)
print "Done constructing tree."
self.record()
return np.linalg.norm(x-y)
def brute_force(train_points, test_point, k):
distances = [(p, l2(test_point, p)) for p in train_points]
sorted_distances = sorted(distances, key=lambda x: x[1])
return sorted_distances[:k]
if __name__ == "__main__":
num_dimension = 2000
num_samples = 100000
num_test = 10
k = 5
X = np.random.uniform(0, 100, size=(num_samples, num_dimension))
Y = np.random.uniform(0, 100, size=(num_test, num_dimension))
train_points = [X[i,:] for i in range(num_samples)]
lsh = LSHash(8, num_dimension)
start_cons = time.time()
for i in range(num_samples):
lsh.index(X[i,:])
print "done construction in", time.time() - start_cons
for i in range(num_test):
test_point = Y[i,:]
start_time = time.time()
lsh_neighbors = lsh.query(test_point, num_results=k, distance_func='true_euclidean')
done_lsh = time.time()
brute_force_neighbors = brute_force(train_points, test_point, k)
done_brute_force = time.time()
print "lsh in:", done_lsh-start_time
print "brute-force in:", done_brute_force-done_lsh
assert len(lsh_neighbors) == k
assert len(brute_force_neighbors) == k
