jacklangerman
commited on
Commit
•
91b350c
1
Parent(s):
a842b44
refactor cv + fix calc
Browse files- hoho/wed.py +12 -10
hoho/wed.py
CHANGED
@@ -28,13 +28,13 @@ def preregister_mean_std(verts_to_transform, target_verts, single_scale=True):
|
|
28 |
return transformed_verts
|
29 |
|
30 |
|
31 |
-
def compute_WED(pd_vertices, pd_edges, gt_vertices, gt_edges, cv=-1, ce=1.0, normalized=True, preregister=True, single_scale=True):
|
32 |
'''The function computes the Wireframe Edge Distance (WED) between two graphs.
|
33 |
pd_vertices: list of predicted vertices
|
34 |
pd_edges: list of predicted edges
|
35 |
gt_vertices: list of ground truth vertices
|
36 |
gt_edges: list of ground truth edges
|
37 |
-
cv: vertex cost
|
38 |
ce: edge cost (multiplier of the edge length for edge deletion and insertion, default is 1.0)
|
39 |
normalized: if True, the WED is normalized by the total length of the ground truth edges
|
40 |
preregister: if True, the predicted vertices have their mean and scale matched to the ground truth vertices
|
@@ -43,21 +43,23 @@ def compute_WED(pd_vertices, pd_edges, gt_vertices, gt_edges, cv=-1, ce=1.0, nor
|
|
43 |
# Vertex coordinates are in centimeters. When cv and ce are set to 100.0 and 1.0 respectively,
|
44 |
# missing a vertex is equivanlent predicting it 1 meter away from the ground truth vertex.
|
45 |
# This is equivalent to setting cv=1 and ce=1 when the vertex coordinates are in meters.
|
46 |
-
# When a negative cv value is set (the default behavior), cv is reset to 1/
|
47 |
|
48 |
pd_vertices = np.array(pd_vertices)
|
49 |
gt_vertices = np.array(gt_vertices)
|
50 |
|
51 |
-
diameter = cdist(gt_vertices, gt_vertices).max()
|
52 |
-
|
53 |
-
if cv < 0:
|
54 |
-
cv = diameter / 4.0
|
55 |
-
# Cost of addining or deleting a vertex is set to 1/4 of the diameter of the ground truth mesh
|
56 |
-
|
57 |
-
# Step 0: Prenormalize / preregister
|
58 |
if preregister:
|
59 |
pd_vertices = preregister_mean_std(pd_vertices, gt_vertices, single_scale=single_scale)
|
60 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
pd_edges = np.array(pd_edges)
|
63 |
gt_edges = np.array(gt_edges)
|
|
|
28 |
return transformed_verts
|
29 |
|
30 |
|
31 |
+
def compute_WED(pd_vertices, pd_edges, gt_vertices, gt_edges, cv=-1/4, ce=1.0, normalized=True, preregister=True, single_scale=True):
|
32 |
'''The function computes the Wireframe Edge Distance (WED) between two graphs.
|
33 |
pd_vertices: list of predicted vertices
|
34 |
pd_edges: list of predicted edges
|
35 |
gt_vertices: list of ground truth vertices
|
36 |
gt_edges: list of ground truth edges
|
37 |
+
cv: vertex cost: if positive, the cost in centimeters of missing a vertex, if negative, multiplies diameter to compute cost (default is -1/2)
|
38 |
ce: edge cost (multiplier of the edge length for edge deletion and insertion, default is 1.0)
|
39 |
normalized: if True, the WED is normalized by the total length of the ground truth edges
|
40 |
preregister: if True, the predicted vertices have their mean and scale matched to the ground truth vertices
|
|
|
43 |
# Vertex coordinates are in centimeters. When cv and ce are set to 100.0 and 1.0 respectively,
|
44 |
# missing a vertex is equivanlent predicting it 1 meter away from the ground truth vertex.
|
45 |
# This is equivalent to setting cv=1 and ce=1 when the vertex coordinates are in meters.
|
46 |
+
# When a negative cv value is set (the default behavior), cv is reset to 1/2 of the diameter of the ground truth wireframe.
|
47 |
|
48 |
pd_vertices = np.array(pd_vertices)
|
49 |
gt_vertices = np.array(gt_vertices)
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
if preregister:
|
52 |
pd_vertices = preregister_mean_std(pd_vertices, gt_vertices, single_scale=single_scale)
|
53 |
|
54 |
+
if cv < 0:
|
55 |
+
diameter = cdist(gt_vertices, gt_vertices).max()
|
56 |
+
# Cost of adding or deleting a vertex is set to -cv times the diameter of the ground truth wireframe
|
57 |
+
cv = -cv * diameter
|
58 |
+
elif cv == 0:
|
59 |
+
# Cost of adding or deleting a vertex is set to the average distance of the ground truth vertices from their mean
|
60 |
+
cv = np.linalg.norm(np.mean(gt_vertices, axis=0) - gt_vertices, axis=1).mean()
|
61 |
+
# Step 0: Prenormalize / preregister
|
62 |
+
|
63 |
|
64 |
pd_edges = np.array(pd_edges)
|
65 |
gt_edges = np.array(gt_edges)
|