forked from cwhy/i-raven
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmain.py
257 lines (229 loc) · 12.2 KB
/
main.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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
import argparse
import copy
import os
import random
import numpy as np
from tqdm import trange
from build_tree import (build_center_single, build_distribute_four,
build_distribute_nine,
build_in_center_single_out_center_single,
build_in_distribute_four_out_center_single,
build_left_center_single_right_center_single,
build_up_center_single_down_center_single)
from const import IMAGE_SIZE
from rendering import render_panel
from sampling import sample_attr_avail, sample_rules
from serialize import dom_problem, serialize_aot, serialize_rules
from solver import solve
def merge_component(dst_aot, src_aot, component_idx):
src_component = src_aot.children[0].children[component_idx]
dst_aot.children[0].children[component_idx] = src_component
def separate(args, all_configs):
random.seed(args.seed)
np.random.seed(args.seed)
for key in list(all_configs.keys()):
acc = 0
for k in trange(args.num_samples):
count_num = k % 10
if count_num < (10 - args.val - args.test):
set_name = "train"
elif count_num < (10 - args.test):
set_name = "val"
else:
set_name = "test"
root = all_configs[key]
while True:
rule_groups = sample_rules()
new_root = root.prune(rule_groups)
if new_root is not None:
break
start_node = new_root.sample()
row_1_1 = copy.deepcopy(start_node)
for l in range(len(rule_groups)):
rule_group = rule_groups[l]
rule_num_pos = rule_group[0]
row_1_2 = rule_num_pos.apply_rule(row_1_1)
row_1_3 = rule_num_pos.apply_rule(row_1_2)
for i in range(1, len(rule_group)):
rule = rule_group[i]
row_1_2 = rule.apply_rule(row_1_1, row_1_2)
for i in range(1, len(rule_group)):
rule = rule_group[i]
row_1_3 = rule.apply_rule(row_1_2, row_1_3)
if l == 0:
to_merge = [row_1_1, row_1_2, row_1_3]
else:
merge_component(to_merge[1], row_1_2, l)
merge_component(to_merge[2], row_1_3, l)
row_1_1, row_1_2, row_1_3 = to_merge
row_2_1 = copy.deepcopy(start_node)
row_2_1.resample(True)
for l in range(len(rule_groups)):
rule_group = rule_groups[l]
rule_num_pos = rule_group[0]
row_2_2 = rule_num_pos.apply_rule(row_2_1)
row_2_3 = rule_num_pos.apply_rule(row_2_2)
for i in range(1, len(rule_group)):
rule = rule_group[i]
row_2_2 = rule.apply_rule(row_2_1, row_2_2)
for i in range(1, len(rule_group)):
rule = rule_group[i]
row_2_3 = rule.apply_rule(row_2_2, row_2_3)
if l == 0:
to_merge = [row_2_1, row_2_2, row_2_3]
else:
merge_component(to_merge[1], row_2_2, l)
merge_component(to_merge[2], row_2_3, l)
row_2_1, row_2_2, row_2_3 = to_merge
row_3_1 = copy.deepcopy(start_node)
row_3_1.resample(True)
for l in range(len(rule_groups)):
rule_group = rule_groups[l]
rule_num_pos = rule_group[0]
row_3_2 = rule_num_pos.apply_rule(row_3_1)
row_3_3 = rule_num_pos.apply_rule(row_3_2)
for i in range(1, len(rule_group)):
rule = rule_group[i]
row_3_2 = rule.apply_rule(row_3_1, row_3_2)
for i in range(1, len(rule_group)):
rule = rule_group[i]
row_3_3 = rule.apply_rule(row_3_2, row_3_3)
if l == 0:
to_merge = [row_3_1, row_3_2, row_3_3]
else:
merge_component(to_merge[1], row_3_2, l)
merge_component(to_merge[2], row_3_3, l)
row_3_1, row_3_2, row_3_3 = to_merge
imgs = [render_panel(row_1_1),
render_panel(row_1_2),
render_panel(row_1_3),
render_panel(row_2_1),
render_panel(row_2_2),
render_panel(row_2_3),
render_panel(row_3_1),
render_panel(row_3_2),
np.zeros((IMAGE_SIZE, IMAGE_SIZE), np.uint8)]
context = [row_1_1, row_1_2, row_1_3, row_2_1, row_2_2, row_2_3, row_3_1, row_3_2]
modifiable_attr = sample_attr_avail(rule_groups, row_3_3)
answer_AoT = copy.deepcopy(row_3_3)
candidates = [answer_AoT]
attr_num = 3
if attr_num <= len(modifiable_attr):
idx = np.random.choice(len(modifiable_attr), attr_num, replace=False)
selected_attr = [modifiable_attr[i] for i in idx]
else:
selected_attr = modifiable_attr
mode = None
# switch attribute 'Number' for convenience
pos = [i for i in range(len(selected_attr)) if selected_attr[i][1] == 'Number']
if pos:
pos = pos[0]
selected_attr[pos], selected_attr[-1] = selected_attr[-1], selected_attr[pos]
pos = [i for i in range(len(selected_attr)) if selected_attr[i][1] == 'Position']
if pos:
mode = 'Position-Number'
values = []
if len(selected_attr) >= 3:
mode_3 = None
if mode == 'Position-Number':
mode_3 = '3-Position-Number'
for i in range(attr_num):
component_idx, attr_name, min_level, max_level, attr_uni = selected_attr[i][0], selected_attr[i][1], \
selected_attr[i][3], selected_attr[i][4], \
selected_attr[i][5]
value = answer_AoT.sample_new_value(component_idx, attr_name, min_level, max_level, attr_uni,
mode_3)
values.append(value)
tmp = []
for j in candidates:
new_AoT = copy.deepcopy(j)
new_AoT.apply_new_value(component_idx, attr_name, value)
tmp.append(new_AoT)
candidates += tmp
elif len(selected_attr) == 2:
component_idx, attr_name, min_level, max_level, attr_uni = selected_attr[0][0], selected_attr[0][1], \
selected_attr[0][3], selected_attr[0][4], \
selected_attr[0][5]
value = answer_AoT.sample_new_value(component_idx, attr_name, min_level, max_level, attr_uni, None)
values.append(value)
new_AoT = copy.deepcopy(answer_AoT)
new_AoT.apply_new_value(component_idx, attr_name, value)
candidates.append(new_AoT)
component_idx, attr_name, min_level, max_level, attr_uni = selected_attr[1][0], selected_attr[1][1], \
selected_attr[1][3], selected_attr[1][4], \
selected_attr[1][5]
if mode == 'Position-Number':
ran, qu = 6, 1
else:
ran, qu = 3, 2
for i in range(ran):
value = answer_AoT.sample_new_value(component_idx, attr_name, min_level, max_level, attr_uni, None)
values.append(value)
for j in range(qu):
new_AoT = copy.deepcopy(candidates[j])
new_AoT.apply_new_value(component_idx, attr_name, value)
candidates.append(new_AoT)
elif len(selected_attr) == 1:
component_idx, attr_name, min_level, max_level, attr_uni = selected_attr[0][0], selected_attr[0][1], \
selected_attr[0][3], selected_attr[0][4], \
selected_attr[0][5]
for i in range(7):
value = answer_AoT.sample_new_value(component_idx, attr_name, min_level, max_level, attr_uni, None)
values.append(value)
new_AoT = copy.deepcopy(answer_AoT)
new_AoT.apply_new_value(component_idx, attr_name, value)
candidates.append(new_AoT)
random.shuffle(candidates)
answers = []
for candidate in candidates:
answers.append(render_panel(candidate))
# imsave(generate_matrix_answer(imgs + answers), "/media/dsg3/hs/RAVEN_image/experiments2/{}/{}.jpg".format(key, k))
image = imgs[0:8] + answers
target = candidates.index(answer_AoT)
predicted = solve(rule_groups, context, candidates)
meta_matrix, meta_target = serialize_rules(rule_groups)
structure, meta_structure = serialize_aot(start_node)
np.savez("{}/{}/RAVEN_{}_{}.npz".format(args.save_dir, key, k, set_name), image=image,
target=target,
predict=predicted,
meta_matrix=meta_matrix,
meta_target=meta_target,
structure=structure,
meta_structure=meta_structure)
with open("{}/{}/RAVEN_{}_{}.xml".format(args.save_dir, key, k, set_name), "wb") as f:
dom = dom_problem(context + candidates, rule_groups)
f.write(dom)
if target == predicted:
acc += 1
print(("Accuracy of {}: {}".format(key, float(acc) / args.num_samples)))
def main():
main_arg_parser = argparse.ArgumentParser(description="parser for I-RAVEN")
main_arg_parser.add_argument("--num-samples", type=int, default=10000,
help="number of samples for each component configuration")
main_arg_parser.add_argument("--save-dir", type=str, default="/media/dsg3/datasets/I-RAVEN",
help="path to folder where the generated dataset will be saved.")
main_arg_parser.add_argument("--seed", type=int, default=1234,
help="random seed for dataset generation")
main_arg_parser.add_argument("--fuse", type=int, default=0,
help="whether to fuse different configurations")
main_arg_parser.add_argument("--val", type=float, default=2,
help="the proportion of the size of validation set")
main_arg_parser.add_argument("--test", type=float, default=2,
help="the proportion of the size of test set")
args = main_arg_parser.parse_args()
all_configs = {"center_single": build_center_single(),
"distribute_four": build_distribute_four(),
"distribute_nine": build_distribute_nine(),
"left_center_single_right_center_single": build_left_center_single_right_center_single(),
"up_center_single_down_center_single": build_up_center_single_down_center_single(),
"in_center_single_out_center_single": build_in_center_single_out_center_single(),
"in_distribute_four_out_center_single": build_in_distribute_four_out_center_single()}
if not os.path.exists(args.save_dir):
os.mkdir(args.save_dir)
if not args.fuse:
for key in list(all_configs.keys()):
if not os.path.exists(os.path.join(args.save_dir, key)):
os.mkdir(os.path.join(args.save_dir, key))
separate(args, all_configs)
if __name__ == "__main__":
main()