[CF]提交文件

2025-06-05 15:36:42 +08:00 · 2025-06-05 15:36:42 +08:00 · ce8f840299
commit ce8f840299
parent 6357eb5e74
36 changed files with 38 additions and 2 deletions
--- a/runs/detect/predict29/1.avi
+++ b/runs/detect/predict29/1.avi
--- a/runs/detect/predict30/2.avi
+++ b/runs/detect/predict30/2.avi
--- a/runs/detect/predict31/1.avi
+++ b/runs/detect/predict31/1.avi
--- a/runs/detect/predict32/3.avi
+++ b/runs/detect/predict32/3.avi
--- a/runs/detect/train26/F1_curve.png
+++ b/runs/detect/train26/F1_curve.png
--- a/runs/detect/train26/PR_curve.png
+++ b/runs/detect/train26/PR_curve.png
--- a/runs/detect/train26/P_curve.png
+++ b/runs/detect/train26/P_curve.png
--- a/runs/detect/train26/R_curve.png
+++ b/runs/detect/train26/R_curve.png
--- a/runs/detect/train26/confusion_matrix.png
+++ b/runs/detect/train26/confusion_matrix.png
--- a/runs/detect/train26/confusion_matrix_normalized.png
+++ b/runs/detect/train26/confusion_matrix_normalized.png
--- a/runs/detect/train26/results.csv
+++ b/runs/detect/train26/results.csv
@ -63,3 +63,39 @@ epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),met
 62,768.657,0.48072,0.56784,0.88594,0.99859,0.97872,0.97504,0.87932,0.49053,0.75084,0.9037,0.0007922,0.0007922,0.0007922
 63,780.841,0.55917,0.60833,0.90572,0.99866,0.97872,0.97504,0.8848,0.483,0.75222,0.90783,0.0007724,0.0007724,0.0007724
 64,794.139,0.49627,0.63279,0.93568,0.99871,0.97872,0.97504,0.88849,0.46154,0.71729,0.89663,0.0007526,0.0007526,0.0007526
+65,809.183,0.5422,0.61979,0.91826,0.99831,0.97872,0.97504,0.88894,0.44554,0.69579,0.88535,0.0007328,0.0007328,0.0007328
+66,826.529,0.52536,0.61141,0.88808,0.97735,0.97872,0.97504,0.88483,0.44802,0.71624,0.8918,0.000713,0.000713,0.000713
+67,843.231,0.52884,0.60849,0.91693,0.97751,0.97872,0.97462,0.90006,0.49765,0.72076,0.9078,0.0006932,0.0006932,0.0006932
+68,858.217,0.52012,0.60488,0.88413,0.9973,0.97872,0.97504,0.89056,0.47557,0.70697,0.89253,0.0006734,0.0006734,0.0006734
+69,870.633,0.54421,0.60111,0.92961,0.99869,0.97872,0.97505,0.88974,0.43279,0.6473,0.89538,0.0006536,0.0006536,0.0006536
+70,882.802,0.6041,0.62523,0.90733,0.99869,0.97872,0.97505,0.88974,0.43279,0.6473,0.89538,0.0006338,0.0006338,0.0006338
+71,895.113,0.62387,0.5822,0.97853,0.99839,0.97872,0.97505,0.90479,0.44454,0.64819,0.89868,0.000614,0.000614,0.000614
+72,907.536,0.49362,0.6171,0.86569,0.99867,0.97872,0.97505,0.908,0.43185,0.64718,0.89272,0.0005942,0.0005942,0.0005942
+73,919.806,0.65596,0.65639,1.00239,0.99867,0.97872,0.97505,0.90561,0.4217,0.60938,0.87813,0.0005744,0.0005744,0.0005744
+74,931.995,0.58737,0.58898,0.95303,0.99867,0.97872,0.97505,0.9173,0.40121,0.60192,0.86613,0.0005546,0.0005546,0.0005546
+75,944.212,0.49581,0.5332,0.87874,0.99868,0.97872,0.97505,0.91972,0.39378,0.58595,0.86223,0.0005348,0.0005348,0.0005348
+76,956.684,0.41264,0.74594,0.7891,0.99868,0.97872,0.97505,0.91334,0.38024,0.56515,0.86336,0.000515,0.000515,0.000515
+77,969.06,0.5148,0.56391,0.91987,0.99873,0.97872,0.97505,0.90574,0.36714,0.55898,0.86153,0.0004952,0.0004952,0.0004952
+78,981.215,0.44345,0.56514,0.87102,0.99873,0.97872,0.97505,0.90574,0.36714,0.55898,0.86153,0.0004754,0.0004754,0.0004754
+79,993.389,0.75259,0.88922,1.01904,0.99874,0.97872,0.97505,0.91994,0.35244,0.55994,0.85823,0.0004556,0.0004556,0.0004556
+80,1005.69,0.56094,0.56148,0.91332,0.99871,0.97872,0.97505,0.93219,0.33951,0.54825,0.85353,0.0004358,0.0004358,0.0004358
+81,1017.91,0.39504,0.7493,0.75912,0.99867,0.97872,0.97505,0.93406,0.32041,0.529,0.85223,0.000416,0.000416,0.000416
+82,1030.32,0.42973,0.50872,0.82449,0.99864,0.97872,0.97505,0.9367,0.31864,0.50679,0.85244,0.0003962,0.0003962,0.0003962
+83,1042.68,0.4585,0.47919,0.87823,0.99861,0.97872,0.97505,0.93873,0.32757,0.50275,0.85269,0.0003764,0.0003764,0.0003764
+84,1055.16,0.4396,0.48395,0.86594,0.99859,0.97872,0.97505,0.93946,0.3301,0.50185,0.84862,0.0003566,0.0003566,0.0003566
+85,1067.4,0.41895,0.48022,0.90105,0.99855,0.97872,0.97505,0.93956,0.32873,0.49971,0.83915,0.0003368,0.0003368,0.0003368
+86,1079.79,0.37891,0.66838,0.73848,0.99855,0.97872,0.97505,0.93956,0.32873,0.49971,0.83915,0.000317,0.000317,0.000317
+87,1092.18,0.48218,0.51309,0.89898,0.99852,0.97872,0.97505,0.94983,0.32133,0.49896,0.83179,0.0002972,0.0002972,0.0002972
+88,1104.32,0.60411,0.59325,0.91111,0.99854,0.97872,0.97505,0.94761,0.3237,0.49831,0.82918,0.0002774,0.0002774,0.0002774
+89,1116.51,0.37718,0.66303,0.7512,0.99852,0.97872,0.97505,0.9397,0.33159,0.50139,0.82825,0.0002576,0.0002576,0.0002576
+90,1128.76,0.45675,0.54511,0.86681,0.99856,0.97872,0.97505,0.93146,0.33433,0.49946,0.82797,0.0002378,0.0002378,0.0002378
+91,1140.95,0.42183,0.5796,0.93932,0.99855,0.97872,0.97505,0.93484,0.32953,0.49049,0.82598,0.000218,0.000218,0.000218
+92,1153.16,0.3751,0.55246,0.84782,0.99855,0.97872,0.97505,0.933,0.326,0.49124,0.82383,0.0001982,0.0001982,0.0001982
+93,1165.39,0.38557,0.5376,0.85563,0.99852,0.97872,0.97505,0.93231,0.32707,0.5014,0.82325,0.0001784,0.0001784,0.0001784
+94,1177.82,0.35373,0.53711,0.85211,0.99852,0.97872,0.97505,0.93231,0.32707,0.5014,0.82325,0.0001586,0.0001586,0.0001586
+95,1189.92,0.35459,0.52475,0.81646,0.99853,0.97872,0.97505,0.9336,0.32132,0.51149,0.82209,0.0001388,0.0001388,0.0001388
+96,1202.11,0.38726,0.54125,0.87,0.99854,0.97872,0.97505,0.93324,0.31827,0.51172,0.82195,0.000119,0.000119,0.000119
+97,1214.35,0.34727,0.53959,0.81035,0.99853,0.97872,0.97505,0.93164,0.30842,0.51247,0.82357,9.92e-05,9.92e-05,9.92e-05
+98,1226.46,0.30893,0.69202,0.74366,0.99854,0.97872,0.97505,0.92958,0.30333,0.5146,0.82441,7.94e-05,7.94e-05,7.94e-05
+99,1238.62,0.33106,0.53769,0.80986,0.99855,0.97872,0.97505,0.93077,0.29757,0.51586,0.82436,5.96e-05,5.96e-05,5.96e-05
+100,1250.83,0.33754,0.50732,0.85718,0.99856,0.97872,0.97505,0.9327,0.29568,0.50961,0.82457,3.98e-05,3.98e-05,3.98e-05
--- a/runs/detect/train26/results.png
+++ b/runs/detect/train26/results.png
--- a/runs/detect/train26/train_batch630.jpg
+++ b/runs/detect/train26/train_batch630.jpg
--- a/runs/detect/train26/train_batch631.jpg
+++ b/runs/detect/train26/train_batch631.jpg
--- a/runs/detect/train26/train_batch632.jpg
+++ b/runs/detect/train26/train_batch632.jpg
--- a/runs/detect/train26/val_batch0_labels.jpg
+++ b/runs/detect/train26/val_batch0_labels.jpg
--- a/runs/detect/train26/val_batch0_pred.jpg
+++ b/runs/detect/train26/val_batch0_pred.jpg
--- a/runs/detect/train26/val_batch1_labels.jpg
+++ b/runs/detect/train26/val_batch1_labels.jpg
--- a/runs/detect/train26/val_batch1_pred.jpg
+++ b/runs/detect/train26/val_batch1_pred.jpg
--- a/runs/detect/train26/val_batch2_labels.jpg
+++ b/runs/detect/train26/val_batch2_labels.jpg
--- a/runs/detect/train26/val_batch2_pred.jpg
+++ b/runs/detect/train26/val_batch2_pred.jpg
--- a/runs/detect/train26/weights/best.pt
+++ b/runs/detect/train26/weights/best.pt
--- a/runs/detect/train26/weights/last.pt
+++ b/runs/detect/train26/weights/last.pt
--- a/runs/detect/train262/F1_curve.png
+++ b/runs/detect/train262/F1_curve.png
--- a/runs/detect/train262/PR_curve.png
+++ b/runs/detect/train262/PR_curve.png
--- a/runs/detect/train262/P_curve.png
+++ b/runs/detect/train262/P_curve.png
--- a/runs/detect/train262/R_curve.png
+++ b/runs/detect/train262/R_curve.png
--- a/runs/detect/train262/confusion_matrix.png
+++ b/runs/detect/train262/confusion_matrix.png
--- a/runs/detect/train262/confusion_matrix_normalized.png
+++ b/runs/detect/train262/confusion_matrix_normalized.png
--- a/runs/detect/train262/val_batch0_labels.jpg
+++ b/runs/detect/train262/val_batch0_labels.jpg
--- a/runs/detect/train262/val_batch0_pred.jpg
+++ b/runs/detect/train262/val_batch0_pred.jpg
--- a/runs/detect/train262/val_batch1_labels.jpg
+++ b/runs/detect/train262/val_batch1_labels.jpg
--- a/runs/detect/train262/val_batch1_pred.jpg
+++ b/runs/detect/train262/val_batch1_pred.jpg
--- a/runs/detect/train262/val_batch2_labels.jpg
+++ b/runs/detect/train262/val_batch2_labels.jpg
--- a/runs/detect/train262/val_batch2_pred.jpg
+++ b/runs/detect/train262/val_batch2_pred.jpg
--- a/src/test.py
+++ b/src/test.py
@ -1,3 +1,3 @@
 from ultralytics import YOLO
-model = YOLO(r"C:\workspace\le-yolo\runs\detect\train22\weights\best.pt")
-results = model.predict("../res/1.mp4", show=True, save=True)
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train26\weights\best.pt")
+results = model.predict("../res/2.mp4", show=True, save=True)