experiment run details:
  dataset: hoi
  path: /gpfs/mariana/home/envomp/bongard/big_hake/
  prompt method: direct
  prompt structure: labeled

---------------------------------------
  test split name: test_seen_obj_seen_act
---------------------------------------

0 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
1 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
2 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
3 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
4 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
5 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
6 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
7 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
8 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
9 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
10 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
11 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
12 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
13 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
14 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
15 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
16 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
17 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
18 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
19 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
20 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
21 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
22 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
23 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
24 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
25 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
26 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
27 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
28 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
29 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
30 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
31 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
32 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
33 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
34 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
35 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
36 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
37 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
38 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
39 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
40 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
41 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
42 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
43 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
44 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
45 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
46 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
47 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
48 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
49 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
50 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
51 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
52 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
53 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
54 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
55 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
56 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
57 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
58 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
59 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
60 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
61 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
62 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
63 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
64 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
65 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
66 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
67 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
68 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
69 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
70 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
71 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
72 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
73 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
74 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
75 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
76 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
77 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
78 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
79 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
80 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
81 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
82 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
83 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
84 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
85 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
86 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
87 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
88 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
89 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
90 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
91 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
92 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
93 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
94 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
95 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
96 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
97 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
98 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
99 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
100 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
101 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
102 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
103 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
104 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
105 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
106 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
107 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
108 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
109 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
110 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
111 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
112 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
113 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
114 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
115 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
116 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
117 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
118 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
119 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
120 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
121 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
122 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
123 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
124 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
125 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
126 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
127 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
128 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
129 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
130 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
131 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
132 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
133 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
134 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
135 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
136 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
137 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
138 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
139 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
140 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
141 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
142 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
143 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
144 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
145 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
146 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
147 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
148 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
149 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
150 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
151 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
152 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
153 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
154 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n```']'
155 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
156 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
157 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
158 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
159 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
160 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
161 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
162 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
163 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
164 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
165 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
166 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
167 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
168 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
169 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
170 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
171 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
172 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
173 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
174 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
175 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
176 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
177 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
178 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
179 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
180 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
181 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
182 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
183 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
184 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
185 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
186 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
187 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
188 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
189 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
190 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
191 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
192 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
193 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
194 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
195 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
196 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
197 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
198 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
199 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
---------------------------------------
Summary for Split 'test_seen_obj_seen_act':
 results: {'correct': {'cat_1': 40, 'cat_2': 89}, 'incorrect': {'cat_1': 60, 'cat_2': 11}}
 accuracy: 64.50%

---------------------------------------
  test split name: test_seen_obj_unseen_act
---------------------------------------

0 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
1 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
2 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
3 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
4 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
5 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
6 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
7 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
8 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
9 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
10 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
11 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
12 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
13 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
14 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
15 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
16 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
17 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
18 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
19 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
20 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
21 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
22 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
23 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
24 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
25 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
26 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
27 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
28 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
29 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
30 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
31 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
32 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
33 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
34 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
35 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
36 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
37 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
38 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
39 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
40 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
41 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
42 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
43 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
44 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
45 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
46 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
47 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
48 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
49 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
50 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
51 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
52 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
53 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
54 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
55 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
56 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
57 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
58 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
59 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
60 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
61 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
62 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
63 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
64 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
65 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
66 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
67 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
68 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
69 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
70 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
71 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
72 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
73 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
74 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
75 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
76 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
77 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
78 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
79 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
80 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
81 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
82 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
83 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
84 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
85 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
86 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
87 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
88 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
89 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
90 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
91 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
92 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
93 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
94 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
95 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
96 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
97 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
98 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
99 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
100 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
101 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
102 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
103 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
104 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
105 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
106 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
107 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
108 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
109 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
110 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
111 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
112 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
113 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
114 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
115 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
116 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
117 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
118 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
119 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
120 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
121 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
122 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
123 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
124 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
125 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
126 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
127 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
128 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
129 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
130 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
131 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
132 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
133 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
134 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
135 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
136 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
137 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
138 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
139 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
140 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
141 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
142 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
143 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
144 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
145 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
146 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
147 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
148 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
149 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
150 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
151 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
152 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
153 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
154 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
155 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
156 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
157 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
158 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
159 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
160 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
161 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
162 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
163 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
164 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
165 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
166 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
167 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
168 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
169 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
170 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
171 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
172 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
173 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
174 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
175 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
176 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
177 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
178 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
179 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
180 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
181 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
182 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
183 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
184 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
185 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
186 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
187 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
188 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
189 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
190 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
191 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
192 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
193 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
194 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
195 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
196 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
197 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
198 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
199 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
---------------------------------------
Summary for Split 'test_seen_obj_unseen_act':
 results: {'correct': {'cat_1': 46, 'cat_2': 81}, 'incorrect': {'cat_1': 54, 'cat_2': 19}}
 accuracy: 63.50%

---------------------------------------
  test split name: test_unseen_obj_seen_act
---------------------------------------

0 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
1 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
2 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
3 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
4 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
5 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
6 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
7 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
8 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
9 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
10 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
11 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
12 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
13 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
14 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
15 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
16 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
17 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
18 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
19 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
20 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
21 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
22 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
23 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
24 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
25 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
26 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
27 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
28 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
29 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
30 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
31 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
32 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
33 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
34 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
35 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
36 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
37 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
38 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
39 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
40 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
41 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
42 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
43 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
44 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
45 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
46 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
47 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
48 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
49 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
50 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
51 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
52 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
53 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
54 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
55 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
56 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
57 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
58 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
59 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
60 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
61 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
62 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
63 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
64 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
65 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
66 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
67 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
68 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
69 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
70 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
71 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
72 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
73 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
74 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
75 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
76 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
77 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
78 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
79 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
80 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
81 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
82 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
83 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
84 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
85 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
86 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
87 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
88 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
89 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
90 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
91 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
92 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
93 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
94 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
95 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
96 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
97 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
98 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
99 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
100 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
101 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
102 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
103 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
104 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
105 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
106 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
107 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
108 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
109 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
110 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
111 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
112 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
113 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
114 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
115 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
116 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
117 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
118 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
119 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
120 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
121 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
122 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
123 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
124 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
125 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
126 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
127 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
128 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
129 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
130 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
131 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
132 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
133 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
134 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
135 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
136 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
137 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
138 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
139 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
140 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
141 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
142 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
143 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
144 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
145 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
146 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
147 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
148 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
149 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
150 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
151 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
152 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
153 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
154 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
155 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
156 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
157 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
158 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
159 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
160 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
161 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
162 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
163 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
164 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
165 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
166 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
167 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
168 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
169 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
170 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
171 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
172 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
173 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
174 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
175 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
176 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
177 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
178 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
179 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
180 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
181 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
182 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
183 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
184 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
185 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
186 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
187 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
188 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
189 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
190 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
191 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
192 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
193 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
194 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
195 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
196 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
197 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
198 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
199 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
---------------------------------------
Summary for Split 'test_unseen_obj_seen_act':
 results: {'correct': {'cat_1': 31, 'cat_2': 83}, 'incorrect': {'cat_1': 69, 'cat_2': 17}}
 accuracy: 57.00%

---------------------------------------
  test split name: test_unseen_obj_unseen_act
---------------------------------------

0 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
1 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
2 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
3 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
4 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
5 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
6 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
7 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
8 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
9 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
10 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
11 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
12 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
13 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
14 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
15 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
16 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
17 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
18 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
19 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
20 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
21 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
22 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
23 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
24 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
25 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
26 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
27 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
28 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
29 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
30 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
31 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
32 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
33 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
34 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
35 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
36 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
37 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
38 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
39 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
40 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
41 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
42 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
43 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
44 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
45 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
46 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
47 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
48 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
49 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
50 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
51 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
52 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
53 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
54 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
55 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
56 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
57 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
58 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
59 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
60 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
61 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
62 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
63 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
64 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
65 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
66 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
67 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
68 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
69 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
70 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
71 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
72 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
73 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
74 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
75 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
76 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
77 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
78 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
79 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
80 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
81 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
82 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
83 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
84 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
85 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
86 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
87 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
88 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
89 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
90 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
91 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
92 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
93 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
94 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
95 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
96 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
97 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
98 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
99 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
100 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
101 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
102 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
103 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
104 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
105 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
106 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
107 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
108 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
109 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
110 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
111 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
112 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
113 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
114 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
115 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
116 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
117 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
118 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
119 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
120 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
121 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
122 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
123 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
124 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
125 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
126 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
127 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
128 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
129 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
130 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
131 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
132 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
133 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
134 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
135 | expected:'cat_1' | got='cat_1 | full: [' cat_1\nThe test image shows a bench in an urban setting with no people sitting on it, which aligns with the cat_1 images where benches are either empty or have only one person sitting alone.\n']'
136 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
137 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
138 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
139 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
140 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
141 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
142 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
143 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
144 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
145 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
146 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
147 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
148 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
149 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
150 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
151 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
152 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
153 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
154 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
155 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
156 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
157 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
158 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
159 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
160 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
161 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
162 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
163 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
164 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n']'
165 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
166 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
167 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
168 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
169 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
170 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
171 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
172 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
173 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
174 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
175 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
176 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
177 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
178 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
179 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
180 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
181 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
182 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
183 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
184 | expected:'cat_2' | got='cat_1 | full: [' cat_1\n```']'
185 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
186 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
187 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
188 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
189 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
190 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
191 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
192 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
193 | expected:'cat_1' | got='cat_2 | full: [' cat_2\n']'
194 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
195 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n']'
196 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
197 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
198 | expected:'cat_2' | got='cat_2 | full: [' cat_2\n']'
199 | expected:'cat_1' | got='cat_1 | full: [' cat_1\n```']'
---------------------------------------
Summary for Split 'test_unseen_obj_unseen_act':
 results: {'correct': {'cat_1': 38, 'cat_2': 77}, 'incorrect': {'cat_1': 62, 'cat_2': 23}}
 accuracy: 57.50%

---------------------------------------
