-
Notifications
You must be signed in to change notification settings - Fork 1
Description
-
When using Docker for evaluation, the WARNING shown in the above image appeared: 2025-12-24 05:48:49,034 - compute_metrics_parallel - Error evaluating constraint is_visible. Is this normal?
-
The evaluation metrics we finally obtained have a large gap compared to those in the paper(
). Is there something wrong with our configuration? The evaluation results are as follows:
{
"language_adherence_success": 15.171428571428573,
"global_constraint_accuracy": 45.08521418701059,
"complete_placement_success": 8.542857142857143,
"subgroup_metrics": {
"spatial": 0.5661352865144335,
"rotational": 0.17298735861610112,
"visibility": 0.0,
"physical": 0.5731428571428572
},
"per_constraint_metrics": {
"on": {
"accuracy": 0.9378238341968912,
"satisfied": 1267,
"total": 1351
},
"below": {
"accuracy": 0.2553191489361702,
"satisfied": 48,
"total": 188
},
"is_visible": {
"accuracy": 0.0,
"satisfied": 0,
"total": 996
},
"near": {
"accuracy": 0.49556650246305417,
"satisfied": 1006,
"total": 2030
},
"above": {
"accuracy": 0.16822429906542055,
"satisfied": 18,
"total": 107
},
"not_visible": {
"accuracy": 0.0,
"satisfied": 0,
"total": 214
},
"plausible": {
"accuracy": 0.5731428571428572,
"satisfied": 2006,
"total": 3500
},
"facing": {
"accuracy": 0.17298735861610112,
"satisfied": 260,
"total": 1503
},
"adjacent": {
"accuracy": 0.4088397790055249,
"satisfied": 74,
"total": 181
},
"between": {
"accuracy": 0.27388535031847133,
"satisfied": 215,
"total": 785
}
},
"metrics_by_constraint_count": {
"2": {
"total_placements": 1481,
"at_least_one_correct": 944,
"all_correct": 203
},
"1": {
"total_placements": 878,
"at_least_one_correct": 258,
"all_correct": 258
},
"3": {
"total_placements": 1049,
"at_least_one_correct": 848,
"all_correct": 70
},
"4": {
"total_placements": 92,
"at_least_one_correct": 89,
"all_correct": 0
}
}
}