Task_0013_decision_planner / decision_test_report.json
Dongkkka's picture
Upload folder using huggingface_hub
71d153a verified
{
"model_path": "/home/ubuntu/groot_workspace/checkpoints/siglip2_decision_4class_state22_woidle_post1chunk/best_model.pt",
"test_episodes": [
4,
5,
14,
19
],
"threshold": 0.5,
"frame_metrics": {
"class_accuracy": 0.9955503512880562,
"switch_macro_f1": 0.9010890266576999,
"per_switch": [
{
"transition": "0->1",
"tp": 48,
"fp": 2,
"fn": 16,
"tn": 4204,
"precision": 0.96,
"recall": 0.75,
"f1": 0.8421052631578947
},
{
"transition": "1->2",
"tp": 64,
"fp": 11,
"fn": 0,
"tn": 4195,
"precision": 0.8533333333333334,
"recall": 1.0,
"f1": 0.9208633093525179
},
{
"transition": "2->3",
"tp": 63,
"fp": 7,
"fn": 1,
"tn": 4199,
"precision": 0.9,
"recall": 0.984375,
"f1": 0.9402985074626866
}
]
},
"episode_metrics": [
{
"episode_index": 4,
"chunk_language_accuracy": 1.0,
"frame_language_accuracy": 0.9742647058823529,
"early_switch_count": 0,
"switch_delays": {
"0->1": 8,
"1->2": 10,
"2->3": 10
},
"sequence_completed": true,
"switch_frames": {
"0->1": 48,
"1->2": 512,
"2->3": 688
},
"boundaries": [
{
"frame": 40,
"from": 0,
"to": 1
},
{
"frame": 502,
"from": 1,
"to": 2
},
{
"frame": 678,
"from": 2,
"to": 3
}
]
},
{
"episode_index": 5,
"chunk_language_accuracy": 1.0,
"frame_language_accuracy": 0.9937722419928826,
"early_switch_count": 0,
"switch_delays": {
"0->1": 5,
"1->2": 1,
"2->3": 1
},
"sequence_completed": true,
"switch_frames": {
"0->1": 48,
"1->2": 544,
"2->3": 720
},
"boundaries": [
{
"frame": 43,
"from": 0,
"to": 1
},
{
"frame": 543,
"from": 1,
"to": 2
},
{
"frame": 719,
"from": 2,
"to": 3
}
]
},
{
"episode_index": 14,
"chunk_language_accuracy": 0.046875,
"frame_language_accuracy": 0.03823529411764706,
"early_switch_count": 0,
"switch_delays": {
"0->1": null,
"1->2": null,
"2->3": null
},
"sequence_completed": false,
"switch_frames": {},
"boundaries": [
{
"frame": 39,
"from": 0,
"to": 1
},
{
"frame": 484,
"from": 1,
"to": 2
},
{
"frame": 663,
"from": 2,
"to": 3
}
]
},
{
"episode_index": 19,
"chunk_language_accuracy": 1.0,
"frame_language_accuracy": 0.9778420038535646,
"early_switch_count": 0,
"switch_delays": {
"0->1": 8,
"1->2": 10,
"2->3": 5
},
"sequence_completed": true,
"switch_frames": {
"0->1": 48,
"1->2": 496,
"2->3": 672
},
"boundaries": [
{
"frame": 40,
"from": 0,
"to": 1
},
{
"frame": 486,
"from": 1,
"to": 2
},
{
"frame": 667,
"from": 2,
"to": 3
}
]
}
],
"summary": {
"early_switch_count": 0,
"sequence_completion_rate": 0.75,
"chunk_language_accuracy": 0.76171875,
"frame_language_accuracy": 0.7460285614616118
}
}