crosstyan/RapidPoseTriangulation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reset with index jumps.

Browse Source
This commit is contained in:
Daniel
2024-10-10 12:47:41 +02:00
parent b80ad139e5
commit b958bc8bcf
2 changed files with 99 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

188
media/RESULTS.md
View File

@ -6006,48 +6006,48 @@ Results of the model in various experiments on different datasets.
"person_nums": {
"total_frames": 121,
"total_labels": 484,
"total_preds": 634,
"total_preds": 638,
"considered_empty": 0,
"valid_preds": 483,
"invalid_preds": 151,
"invalid_preds": 155,
"missing": 1,
"invalid_fraction": 0.23817,
"precision": 0.76183,
"invalid_fraction": 0.24295,
"precision": 0.75705,
"recall": 0.99793,
"f1": 0.86404,
"non_empty": 634
"f1": 0.86096,
"non_empty": 638
},
"mpjpe": {
"count": 483,
"mean": 0.03745,
"median": 0.035063,
"std": 0.014194,
"sem": 0.000647,
"mean": 0.037486,
"median": 0.034783,
"std": 0.014406,
"sem": 0.000656,
"min": 0.01794,
"max": 0.136715,
"recall-0.025": 0.163223,
"recall-0.05": 0.842975,
"recall-0.025": 0.165289,
"recall-0.05": 0.840909,
"recall-0.1": 0.991736,
"recall-0.15": 0.997934,
"recall-0.25": 0.997934,
"recall-0.5": 0.997934,
"num_labels": 484,
"ap-0.025": 0.023957,
"ap-0.05": 0.580664,
"ap-0.1": 0.79534,
"ap-0.15": 0.804355,
"ap-0.25": 0.804355,
"ap-0.5": 0.804355
"ap-0.025": 0.024574,
"ap-0.05": 0.576818,
"ap-0.1": 0.794001,
"ap-0.15": 0.803006,
"ap-0.25": 0.803006,
"ap-0.5": 0.803006
},
"head": {
"count": 483,
"mean": 0.037576,
"median": 0.030619,
"std": 0.023474,
"sem": 0.001069,
"mean": 0.037728,
"median": 0.030655,
"std": 0.023551,
"sem": 0.001073,
"min": 0.004382,
"max": 0.136584,
"recall-0.025": 0.378099,
"recall-0.025": 0.371901,
"recall-0.05": 0.721074,
"recall-0.1": 0.977273,
"recall-0.15": 0.997934,
@ -6057,13 +6057,13 @@ Results of the model in various experiments on different datasets.
},
"shoulder_left": {
"count": 483,
"mean": 0.039129,
"median": 0.032213,
"std": 0.022975,
"sem": 0.001047,
"mean": 0.039183,
"median": 0.032414,
"std": 0.022945,
"sem": 0.001045,
"min": 0.004214,
"max": 0.142662,
"recall-0.025": 0.31405,
"recall-0.025": 0.311983,
"recall-0.05": 0.745868,
"recall-0.1": 0.979339,
"recall-0.15": 0.997934,
@ -6073,13 +6073,13 @@ Results of the model in various experiments on different datasets.
},
"shoulder_right": {
"count": 483,
"mean": 0.035508,
"median": 0.030929,
"std": 0.021175,
"sem": 0.000965,
"mean": 0.035627,
"median": 0.031518,
"std": 0.021128,
"sem": 0.000962,
"min": 0.003681,
"max": 0.180338,
"recall-0.025": 0.384298,
"recall-0.025": 0.378099,
"recall-0.05": 0.778926,
"recall-0.1": 0.987603,
"recall-0.15": 0.995868,
@ -6089,14 +6089,14 @@ Results of the model in various experiments on different datasets.
},
"elbow_left": {
"count": 483,
"mean": 0.039093,
"median": 0.031479,
"std": 0.027871,
"sem": 0.001269,
"mean": 0.039216,
"median": 0.031488,
"std": 0.027873,
"sem": 0.00127,
"min": 0.005996,
"max": 0.237523,
"recall-0.025": 0.347107,
"recall-0.05": 0.737603,
"recall-0.025": 0.345041,
"recall-0.05": 0.735537,
"recall-0.1": 0.966942,
"recall-0.15": 0.987603,
"recall-0.25": 0.997934,
@ -6105,13 +6105,13 @@ Results of the model in various experiments on different datasets.
},
"elbow_right": {
"count": 483,
"mean": 0.041455,
"median": 0.033784,
"std": 0.038189,
"sem": 0.001739,
"mean": 0.041639,
"median": 0.033826,
"std": 0.038231,
"sem": 0.001741,
"min": 0.003944,
"max": 0.443462,
"recall-0.025": 0.367769,
"recall-0.025": 0.363636,
"recall-0.05": 0.741736,
"recall-0.1": 0.954545,
"recall-0.15": 0.979339,
@ -6121,47 +6121,47 @@ Results of the model in various experiments on different datasets.
},
"wrist_left": {
"count": 483,
"mean": 0.04895,
"median": 0.039104,
"std": 0.036788,
"sem": 0.001676,
"mean": 0.048731,
"median": 0.038931,
"std": 0.036668,
"sem": 0.00167,
"min": 0.002618,
"max": 0.309556,
"recall-0.025": 0.258264,
"recall-0.05": 0.650826,
"recall-0.025": 0.262397,
"recall-0.05": 0.654959,
"recall-0.1": 0.913223,
"recall-0.15": 0.977273,
"recall-0.15": 0.979339,
"recall-0.25": 0.995868,
"recall-0.5": 0.997934,
"num_labels": 484
},
"wrist_right": {
"count": 481,
"mean": 0.050009,
"median": 0.040081,
"std": 0.040668,
"sem": 0.001856,
"mean": 0.050653,
"median": 0.039122,
"std": 0.044513,
"sem": 0.002032,
"min": 0.003069,
"max": 0.35488,
"recall-0.025": 0.262397,
"max": 0.445609,
"recall-0.025": 0.268595,
"recall-0.05": 0.63843,
"recall-0.1": 0.900826,
"recall-0.15": 0.964876,
"recall-0.25": 0.987603,
"recall-0.15": 0.96281,
"recall-0.25": 0.985537,
"recall-0.5": 0.993802,
"num_labels": 484
},
"hip_left": {
"count": 483,
"mean": 0.040026,
"mean": 0.039765,
"median": 0.036626,
"std": 0.021724,
"sem": 0.00099,
"std": 0.02136,
"sem": 0.000973,
"min": 0.004385,
"max": 0.191835,
"recall-0.025": 0.231405,
"recall-0.05": 0.756198,
"recall-0.1": 0.979339,
"recall-0.025": 0.235537,
"recall-0.05": 0.758264,
"recall-0.1": 0.981405,
"recall-0.15": 0.995868,
"recall-0.25": 0.997934,
"recall-0.5": 0.997934,
@ -6169,15 +6169,15 @@ Results of the model in various experiments on different datasets.
},
"hip_right": {
"count": 483,
"mean": 0.042645,
"median": 0.034828,
"std": 0.027596,
"sem": 0.001257,
"mean": 0.042641,
"median": 0.03475,
"std": 0.027897,
"sem": 0.001271,
"min": 0.004215,
"max": 0.149838,
"recall-0.025": 0.27686,
"recall-0.05": 0.71281,
"recall-0.1": 0.948347,
"recall-0.025": 0.28719,
"recall-0.05": 0.714876,
"recall-0.1": 0.946281,
"recall-0.15": 0.997934,
"recall-0.25": 0.997934,
"recall-0.5": 0.997934,
@ -6185,9 +6185,9 @@ Results of the model in various experiments on different datasets.
},
"knee_left": {
"count": 483,
"mean": 0.025053,
"median": 0.021076,
"std": 0.018987,
"mean": 0.024984,
"median": 0.020915,
"std": 0.018998,
"sem": 0.000865,
"min": 0.001403,
"max": 0.27912,
@ -6201,14 +6201,14 @@ Results of the model in various experiments on different datasets.
},
"knee_right": {
"count": 483,
"mean": 0.026099,
"median": 0.022868,
"std": 0.015211,
"sem": 0.000693,
"mean": 0.026066,
"median": 0.022746,
"std": 0.015356,
"sem": 0.000699,
"min": 0.001415,
"max": 0.094234,
"recall-0.025": 0.557851,
"recall-0.05": 0.919421,
"recall-0.025": 0.559917,
"recall-0.05": 0.917355,
"recall-0.1": 0.997934,
"recall-0.15": 0.997934,
"recall-0.25": 0.997934,
@ -6217,9 +6217,9 @@ Results of the model in various experiments on different datasets.
},
"ankle_left": {
"count": 483,
"mean": 0.029784,
"mean": 0.029662,
"median": 0.023999,
"std": 0.034378,
"std": 0.034381,
"sem": 0.001566,
"min": 0.002215,
"max": 0.497796,
@ -6233,14 +6233,14 @@ Results of the model in various experiments on different datasets.
},
"ankle_right": {
"count": 483,
"mean": 0.029202,
"mean": 0.029111,
"median": 0.026139,
"std": 0.017443,
"sem": 0.000795,
"std": 0.017356,
"sem": 0.000791,
"min": 0.001964,
"max": 0.103825,
"recall-0.025": 0.464876,
"recall-0.05": 0.880165,
"recall-0.025": 0.466942,
"recall-0.05": 0.882231,
"recall-0.1": 0.993802,
"recall-0.15": 0.997934,
"recall-0.25": 0.997934,
@ -6250,17 +6250,17 @@ Results of the model in various experiments on different datasets.
"joint_recalls": {
"num_labels": 6292,
"recall-0.025": 0.38207,
"recall-0.05": 0.77718,
"recall-0.1": 0.96615,
"recall-0.15": 0.99031,
"recall-0.25": 0.99603,
"recall-0.05": 0.77765,
"recall-0.1": 0.96631,
"recall-0.15": 0.99046,
"recall-0.25": 0.99587,
"recall-0.5": 0.99762
}
}
{
"total_parts": 6776,
"correct_parts": 6729,
"pcp": 0.993064
"correct_parts": 6727,
"pcp": 0.992769
}
```

6
scripts/test_skelda_dataset.py
View File

@ -277,10 +277,13 @@ def main():
times = []
triangulator = spt.Triangulator(min_score=minscore, min_group_size=min_group_size)
old_scene = ""
old_index = -1
for label in tqdm.tqdm(labels):
images_2d = []
if old_scene != label.get("scene", "") or dataset_use == "human36m_wb":
if old_scene != label.get("scene", "") or (
old_index + datasets[dataset_use]["take_interval"] < label["index"]
):
# Reset last poses if scene changes
old_scene = label.get("scene", "")
triangulator.reset()
@ -328,6 +331,7 @@ def main():
time_3d = time.time() - start
print("3D time:", time_3d)
old_index = label["index"]
all_poses.append(np.array(poses3D))
all_ids.append(label["id"])
all_paths.append(label["imgpaths"])