def test_feature_matching_speed():
"""
Test how long feature matching takes to execute on the Notre Dame pair.
"""
start = time.time()
image1 = load_image(f'{ROOT}/data/1a_notredame.jpg')
image2 = load_image(f'{ROOT}/data/1b_notredame.jpg')
eval_file = f'{ROOT}/ground_truth/notredame.pkl'
scale_factor = 0.5
image1 = PIL_resize(image1, (int(
image1.shape[1] * scale_factor), int(image1.shape[0] * scale_factor)))
image2 = PIL_resize(image2, (int(
image2.shape[1] * scale_factor), int(image2.shape[0] * scale_factor)))
image1_bw = rgb2gray(image1)
image2_bw = rgb2gray(image2)
tensor_type = torch.FloatTensor
torch.set_default_tensor_type(tensor_type)
to_tensor = transforms.ToTensor()
image_input1 = to_tensor(image1_bw).unsqueeze(0)
image_input2 = to_tensor(image2_bw).unsqueeze(0)
x1, y1, _ = get_interest_points(image_input1)
x2, y2, _ = get_interest_points(image_input2)
x1, x2 = x1.detach().numpy(), x2.detach().numpy()
y1, y2 = y1.detach().numpy(), y2.detach().numpy()
image1_features = get_siftnet_features(image_input1, x1, y1)
image2_features = get_siftnet_features(image_input2, x2, y2)
matches, confidences = match_features(image1_features, image2_features, x1,
y1, x2, y2)
print('{:d} matches from {:d} corners'.format(len(matches), len(x1)))
# num_pts_to_evaluate = len(matches)
num_pts_to_evaluate = 100
_, c = evaluate_correspondence(image1, image2, eval_file, scale_factor,
x1[matches[:num_pts_to_evaluate, 0]],
y1[matches[:num_pts_to_evaluate, 0]],
x2[matches[:num_pts_to_evaluate, 1]],
y2[matches[:num_pts_to_evaluate, 1]])
end = time.time()
duration = end - start
print(
f'Your Feature matching pipeline takes {duration} seconds to run on Notre Dame'
)
def test_get_siftnet_features(): """ """ x = np.array([8,8,7,9]) # numpy array y = np.array([7,9,8,8]) # numpy array img_bw = np.arange(256).reshape(16,16) # numpy array img_bw = torch.from_numpy(img_bw) img_bw = img_bw.unsqueeze(0).unsqueeze(0) img_bw = img_bw.type(torch.FloatTensor) features = get_siftnet_features(img_bw, x, y) assert np.allclose(features.sum(), 22.039, atol=1) assert features.shape == (4, 128)
def test_get_siftnet_features():
"""
"""
x = np.array([8, 8, 7, 9]) # numpy array
y = np.array([7, 9, 8, 8]) # numpy array
img_bw = np.arange(256).reshape(16, 16) # numpy array
img_bw = torch.from_numpy(img_bw)
img_bw = img_bw.unsqueeze(0).unsqueeze(0)
img_bw = img_bw.type(torch.FloatTensor)
features = get_siftnet_features(img_bw, x, y)
assert np.allclose(features.sum(), 22.039, atol=1)
assert features.shape == (4, 128)
gt_feat_crop = np.array([[0.28135952,
0.20184263], [0.28796558, 0.17183169],
[0.27522191, 0.12444288], [0., 0.23030874]])
assert np.allclose(features[:, 64:66], gt_feat_crop)