forked from open-mmlab/mmskeleton
-
Notifications
You must be signed in to change notification settings - Fork 0
/
tools.py
200 lines (161 loc) · 6.32 KB
/
tools.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
import numpy as np
import random
def downsample(data_numpy, step, random_sample=True):
# input: C,T,V,M
begin = np.random.randint(step) if random_sample else 0
return data_numpy[:, begin::step, :, :]
def temporal_slice(data_numpy, step):
# input: C,T,V,M
C, T, V, M = data_numpy.shape
return data_numpy.reshape(C, T / step, step, V, M).transpose(
(0, 1, 3, 2, 4)).reshape(C, T / step, V, step * M)
def mean_subtractor(data_numpy, mean):
# input: C,T,V,M
# naive version
if mean == 0:
return
C, T, V, M = data_numpy.shape
valid_frame = (data_numpy != 0).sum(axis=3).sum(axis=2).sum(axis=0) > 0
begin = valid_frame.argmax()
end = len(valid_frame) - valid_frame[::-1].argmax()
data_numpy[:, :end, :, :] = data_numpy[:, :end, :, :] - mean
return data_numpy
def auto_pading(data_numpy, size, random_pad=False):
C, T, V, M = data_numpy.shape
if T < size:
begin = random.randint(0, size - T) if random_pad else 0
data_numpy_paded = np.zeros((C, size, V, M))
data_numpy_paded[:, begin:begin + T, :, :] = data_numpy
return data_numpy_paded
else:
return data_numpy
def random_choose(data_numpy, size, auto_pad=True):
# input: C,T,V,M
C, T, V, M = data_numpy.shape
if T == size:
return data_numpy
elif T < size:
if auto_pad:
return auto_pading(data_numpy, size, random_pad=True)
else:
return data_numpy
else:
begin = random.randint(0, T - size)
return data_numpy[:, begin:begin + size, :, :]
def random_move(data_numpy,
angle_candidate=[-10., -5., 0., 5., 10.],
scale_candidate=[0.9, 1.0, 1.1],
transform_candidate=[-0.2, -0.1, 0.0, 0.1, 0.2],
move_time_candidate=[1]):
# input: C,T,V,M
C, T, V, M = data_numpy.shape
move_time = random.choice(move_time_candidate)
node = np.arange(0, T, T * 1.0 / move_time).round().astype(int)
node = np.append(node, T)
num_node = len(node)
A = np.random.choice(angle_candidate, num_node)
S = np.random.choice(scale_candidate, num_node)
T_x = np.random.choice(transform_candidate, num_node)
T_y = np.random.choice(transform_candidate, num_node)
a = np.zeros(T)
s = np.zeros(T)
t_x = np.zeros(T)
t_y = np.zeros(T)
# linspace
for i in range(num_node - 1):
a[node[i]:node[i + 1]] = np.linspace(
A[i], A[i + 1], node[i + 1] - node[i]) * np.pi / 180
s[node[i]:node[i + 1]] = np.linspace(S[i], S[i + 1],
node[i + 1] - node[i])
t_x[node[i]:node[i + 1]] = np.linspace(T_x[i], T_x[i + 1],
node[i + 1] - node[i])
t_y[node[i]:node[i + 1]] = np.linspace(T_y[i], T_y[i + 1],
node[i + 1] - node[i])
theta = np.array([[np.cos(a) * s, -np.sin(a) * s],
[np.sin(a) * s, np.cos(a) * s]])
# perform transformation
for i_frame in range(T):
xy = data_numpy[0:2, i_frame, :, :]
new_xy = np.dot(theta[:, :, i_frame], xy.reshape(2, -1))
new_xy[0] += t_x[i_frame]
new_xy[1] += t_y[i_frame]
data_numpy[0:2, i_frame, :, :] = new_xy.reshape(2, V, M)
return data_numpy
def random_shift(data_numpy):
# input: C,T,V,M
C, T, V, M = data_numpy.shape
data_shift = np.zeros(data_numpy.shape)
valid_frame = (data_numpy != 0).sum(axis=3).sum(axis=2).sum(axis=0) > 0
begin = valid_frame.argmax()
end = len(valid_frame) - valid_frame[::-1].argmax()
size = end - begin
bias = random.randint(0, T - size)
data_shift[:, bias:bias + size, :, :] = data_numpy[:, begin:end, :, :]
return data_shift
def openpose_match(data_numpy):
C, T, V, M = data_numpy.shape
assert (C == 3)
score = data_numpy[2, :, :, :].sum(axis=1)
# the rank of body confidence in each frame (shape: T-1, M)
rank = (-score[0:T - 1]).argsort(axis=1).reshape(T - 1, M)
# data of frame 1
xy1 = data_numpy[0:2, 0:T - 1, :, :].reshape(2, T - 1, V, M, 1)
# data of frame 2
xy2 = data_numpy[0:2, 1:T, :, :].reshape(2, T - 1, V, 1, M)
# square of distance between frame 1&2 (shape: T-1, M, M)
distance = ((xy2 - xy1)**2).sum(axis=2).sum(axis=0)
# match pose
forward_map = np.zeros((T, M), dtype=int) - 1
forward_map[0] = range(M)
for m in range(M):
choose = (rank == m)
forward = distance[choose].argmin(axis=1)
for t in range(T - 1):
distance[t, :, forward[t]] = np.inf
forward_map[1:][choose] = forward
assert (np.all(forward_map >= 0))
# string data
for t in range(T - 1):
forward_map[t + 1] = forward_map[t + 1][forward_map[t]]
# generate data
new_data_numpy = np.zeros(data_numpy.shape)
for t in range(T):
new_data_numpy[:, t, :, :] = data_numpy[:, t, :, forward_map[
t]].transpose(1, 2, 0)
data_numpy = new_data_numpy
# score sort
trace_score = data_numpy[2, :, :, :].sum(axis=1).sum(axis=0)
rank = (-trace_score).argsort()
data_numpy = data_numpy[:, :, :, rank]
return data_numpy
def top_k_by_category(label, score, top_k):
instance_num, class_num = score.shape
rank = score.argsort()
hit_top_k = [[] for i in range(class_num)]
for i in range(instance_num):
l = label[i]
hit_top_k[l].append(l in rank[i, -top_k:])
accuracy_list = []
for hit_per_category in hit_top_k:
if hit_per_category:
accuracy_list.append(sum(hit_per_category) * 1.0 / len(hit_per_category))
else:
accuracy_list.append(0.0)
return accuracy_list
def calculate_recall_precision(label, score):
instance_num, class_num = score.shape
rank = score.argsort()
confusion_matrix = np.zeros([class_num, class_num])
for i in range(instance_num):
true_l = label[i]
pred_l = rank[i, -1]
confusion_matrix[true_l][pred_l] += 1
precision = []
recall = []
for i in range(class_num):
true_p = confusion_matrix[i][i]
false_n = sum(confusion_matrix[i, :]) - true_p
false_p = sum(confusion_matrix[:, i]) - true_p
precision.append(true_p * 1.0 / (true_p + false_p))
recall.append(true_p * 1.0 / (true_p + false_n))
return precision, recall