[CF]提交文件

2025-06-06 15:44:52 +08:00 · 2025-06-06 15:44:52 +08:00 · 421ef71e66
commit 421ef71e66
parent 74acac6b03
36 changed files with 101 additions and 4 deletions
--- a/runs/detect/predict51/4.avi
+++ b/runs/detect/predict51/4.avi
--- a/runs/detect/predict52/3.avi
+++ b/runs/detect/predict52/3.avi
--- a/runs/detect/predict53/5.avi
+++ b/runs/detect/predict53/5.avi
--- a/runs/detect/train40/F1_curve.png
+++ b/runs/detect/train40/F1_curve.png
--- a/runs/detect/train40/PR_curve.png
+++ b/runs/detect/train40/PR_curve.png
--- a/runs/detect/train40/P_curve.png
+++ b/runs/detect/train40/P_curve.png
--- a/runs/detect/train40/R_curve.png
+++ b/runs/detect/train40/R_curve.png
--- a/runs/detect/train40/confusion_matrix.png
+++ b/runs/detect/train40/confusion_matrix.png
--- a/runs/detect/train40/confusion_matrix_normalized.png
+++ b/runs/detect/train40/confusion_matrix_normalized.png
--- a/runs/detect/train40/results.csv
+++ b/runs/detect/train40/results.csv
@ -4,3 +4,98 @@ epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),met
 3,50.8526,0.84409,2.14524,0.93347,0.01141,0.97872,0.95462,0.65143,0.72545,2.96458,0.86384,0.000509704,0.000509704,0.000509704
 4,68.8891,0.92823,1.93303,0.99896,1,0.17404,0.8576,0.66888,0.93772,3.1365,0.99018,0.00067921,0.00067921,0.00067921
 5,88.2008,0.86695,1.72383,0.99086,1,0.14981,0.89164,0.65259,0.85707,3.08949,0.94664,0.000845152,0.000845152,0.000845152
 6,108.889,0.9233,1.64537,0.99611,0.00313,0.97872,0.22074,0.15359,1.19903,3.67627,1.40338,0.00100753,0.00100753,0.00100753
 7,126.63,0.92474,1.74874,1.01005,1,0.22478,0.9398,0.74549,0.6995,3.02254,1.07775,0.00116634,0.00116634,0.00116634
 8,143.386,0.89439,1.541,1.01516,0.96934,0.67287,0.93016,0.70384,0.84448,2.79319,1.07622,0.00132159,0.00132159,0.00132159
 9,160.154,1.01923,1.37768,1.04767,0.95661,0.42553,0.84458,0.65549,1.14153,3.14578,1.50441,0.00147328,0.00147328,0.00147328
 10,176.531,0.85462,1.4615,1.00649,0.82488,0.401,0.59884,0.42863,0.95452,3.05086,1.07771,0.0016214,0.0016214,0.0016214
 11,193.027,0.88501,1.53296,0.99892,0.91788,0.95141,0.96457,0.73447,1.01148,1.98069,1.07153,0.00176596,0.00176596,0.00176596
 12,209.352,0.936,1.39373,1.03826,0.86628,0.82979,0.90199,0.67733,1.08629,1.81286,1.03771,0.0017822,0.0017822,0.0017822
 13,225.621,0.95074,1.5498,1.01222,0.94283,0.61702,0.78999,0.61324,0.93039,2.10289,0.96341,0.0017624,0.0017624,0.0017624
 14,241.911,0.87627,1.35058,0.98415,0.82171,0.82979,0.89473,0.66946,0.96415,1.78842,0.98676,0.0017426,0.0017426,0.0017426
 15,258.455,0.89969,1.26147,0.99252,0.88159,0.85106,0.92253,0.6623,1.0348,1.97623,1.03837,0.0017228,0.0017228,0.0017228
 16,274.784,0.9107,1.19701,1.04842,0.81433,0.87234,0.91067,0.64013,1.07749,2.33723,1.13321,0.001703,0.001703,0.001703
 17,291.033,0.8797,1.19339,1.01255,0.90187,0.93617,0.95235,0.72838,1.0545,1.88516,1.22758,0.0016832,0.0016832,0.0016832
 18,307.447,0.86492,1.23953,1.00577,0.9374,0.95587,0.93494,0.6668,0.94737,1.63386,0.95875,0.0016634,0.0016634,0.0016634
 19,323.927,0.81989,1.14224,0.9353,0.97176,0.97872,0.96568,0.74768,0.79084,2.04213,0.91647,0.0016436,0.0016436,0.0016436
 20,340.644,0.82661,1.05057,1.01933,0.86772,0.97701,0.89158,0.69948,0.80194,2.04703,0.98656,0.0016238,0.0016238,0.0016238
 21,356.877,0.82623,1.07653,0.95122,0.91797,0.97872,0.93621,0.74577,0.87056,1.6536,1.23575,0.001604,0.001604,0.001604
 22,373.893,0.93091,1.1046,1.00084,0.99713,0.97872,0.97504,0.81712,0.88174,1.24998,1.43402,0.0015842,0.0015842,0.0015842
 23,390.374,0.79185,0.97892,0.98414,1,0.9766,0.97504,0.83856,0.85541,1.15924,1.39651,0.0015644,0.0015644,0.0015644
 24,406.837,0.77858,0.96501,0.9412,1,0.97516,0.97504,0.82906,0.8962,1.0739,1.39967,0.0015446,0.0015446,0.0015446
 25,423.408,0.69471,0.8921,0.92449,0.97863,0.97449,0.97462,0.80796,0.8924,1.12536,1.39023,0.0015248,0.0015248,0.0015248
 26,439.924,0.79448,0.94583,1.01777,0.94546,0.97872,0.97254,0.83029,0.85951,1.08172,1.27858,0.001505,0.001505,0.001505
 27,456.303,0.75574,0.89269,0.95814,0.99662,0.97872,0.97504,0.8358,0.64848,1.03876,1.01015,0.0014852,0.0014852,0.0014852
 28,472.56,0.71507,0.83409,0.94143,0.99683,0.97872,0.97504,0.87181,0.57235,0.98598,0.99489,0.0014654,0.0014654,0.0014654
 29,489.005,0.78166,0.86555,0.98982,0.97822,0.97872,0.97504,0.83676,0.78144,1.05176,1.13006,0.0014456,0.0014456,0.0014456
 30,505.365,0.74249,0.86108,0.95286,0.9974,0.97872,0.97504,0.84753,0.83641,1.0551,1.25554,0.0014258,0.0014258,0.0014258
 31,521.68,0.70916,0.87682,0.97448,0.9963,0.95745,0.97421,0.82212,0.93208,0.98694,1.32275,0.001406,0.001406,0.001406
 32,538.031,0.77631,0.87153,0.97965,0.97698,0.97872,0.97462,0.81106,0.89517,0.93599,1.31376,0.0013862,0.0013862,0.0013862
 33,554.543,0.74973,0.83324,0.96358,0.99792,0.97872,0.97504,0.84652,0.77113,0.83692,1.18537,0.0013664,0.0013664,0.0013664
 34,570.984,0.80141,0.80779,0.97662,0.99646,0.97872,0.97504,0.84518,0.76637,0.95064,1.21416,0.0013466,0.0013466,0.0013466
 35,587.277,0.85547,0.88575,1.08871,0.99951,0.97872,0.97504,0.83551,0.76647,1.01295,1.15899,0.0013268,0.0013268,0.0013268
 36,604.325,0.767,0.7671,0.95181,1,0.97769,0.97504,0.85141,0.67728,0.95316,1.06362,0.001307,0.001307,0.001307
 37,621.429,0.71542,0.79484,0.98779,0.9981,0.95745,0.97421,0.84222,0.73423,0.93986,1.13184,0.0012872,0.0012872,0.0012872
 38,637.85,0.76685,0.74774,0.94989,0.99776,0.95745,0.97274,0.80365,0.81724,0.92326,1.21423,0.0012674,0.0012674,0.0012674
 39,654.193,0.71727,0.77154,0.93576,1,0.97778,0.97504,0.81219,0.79632,0.79607,1.241,0.0012476,0.0012476,0.0012476
 40,670.47,0.73679,0.76367,0.96723,0.9987,0.97872,0.97505,0.82224,0.66771,0.84454,1.02726,0.0012278,0.0012278,0.0012278
 41,687.289,0.69753,0.70766,0.93616,0.99866,0.97872,0.97505,0.84836,0.58592,0.78201,0.95605,0.001208,0.001208,0.001208
 42,703.805,0.69078,0.75505,0.94243,0.99862,0.97872,0.97505,0.86063,0.55282,0.76261,0.93304,0.0011882,0.0011882,0.0011882
 43,720.098,0.69355,0.6699,0.94703,0.99818,0.97872,0.97505,0.87101,0.53047,0.81548,0.94703,0.0011684,0.0011684,0.0011684
 44,736.487,0.61083,0.66366,0.89841,0.99775,0.97872,0.97505,0.86761,0.51186,0.74653,0.95031,0.0011486,0.0011486,0.0011486
 45,752.747,0.70031,0.70279,0.98732,0.99804,0.97872,0.97505,0.8701,0.50757,0.70518,0.94971,0.0011288,0.0011288,0.0011288
 46,769.296,0.62004,0.65034,0.90191,0.99812,0.97872,0.97505,0.8481,0.49729,0.65358,0.95067,0.001109,0.001109,0.001109
 47,785.564,0.69383,0.66827,0.93709,0.99739,0.97872,0.97505,0.87732,0.48397,0.63065,0.94863,0.0010892,0.0010892,0.0010892
 48,801.985,0.59658,0.59829,0.90597,0.99596,0.97872,0.97505,0.85898,0.51329,0.64556,0.93802,0.0010694,0.0010694,0.0010694
 49,818.235,0.62114,0.61166,0.90013,0.99836,0.97872,0.97505,0.87547,0.51048,0.70061,0.93659,0.0010496,0.0010496,0.0010496
 50,834.536,0.62591,0.62487,0.9242,0.9987,0.97872,0.97505,0.86005,0.52268,0.71765,0.93612,0.0010298,0.0010298,0.0010298
 51,850.84,0.60417,0.59436,0.89844,0.99859,0.97872,0.97505,0.88784,0.50296,0.68031,0.9205,0.00101,0.00101,0.00101
 52,867.235,0.67345,0.68685,0.95226,0.99746,0.97872,0.97505,0.87982,0.48112,0.64511,0.9015,0.0009902,0.0009902,0.0009902
 53,883.477,0.65875,0.63211,0.89805,0.99761,0.97872,0.97505,0.8855,0.44319,0.64272,0.88555,0.0009704,0.0009704,0.0009704
 54,899.777,0.61886,0.64051,0.92091,0.99779,0.97872,0.97505,0.89959,0.39967,0.62697,0.87383,0.0009506,0.0009506,0.0009506
 55,916.129,0.58662,0.57316,0.8766,0.99787,0.97872,0.97505,0.90367,0.40999,0.58972,0.87969,0.0009308,0.0009308,0.0009308
 56,932.473,0.56885,0.55402,0.86806,0.99816,0.97872,0.97505,0.88802,0.43791,0.56277,0.88202,0.000911,0.000911,0.000911
 57,948.702,0.61308,0.631,0.94614,0.99754,0.97872,0.97505,0.86903,0.51987,0.59688,0.89673,0.0008912,0.0008912,0.0008912
 58,965.014,0.62221,0.62787,0.93053,0.99653,0.97872,0.97505,0.86344,0.53093,0.6724,0.92493,0.0008714,0.0008714,0.0008714
 59,981.468,0.59869,0.61537,0.91599,0.99832,0.97872,0.97505,0.88686,0.53637,0.6404,0.94102,0.0008516,0.0008516,0.0008516
 60,997.948,0.67699,0.64553,0.93616,0.99839,0.97872,0.97505,0.89016,0.53426,0.60405,0.93235,0.0008318,0.0008318,0.0008318
 61,1014.54,0.54223,0.54748,0.86316,0.99856,0.97872,0.97506,0.9013,0.54016,0.60719,0.93491,0.000812,0.000812,0.000812
 62,1030.81,0.57035,0.56477,0.90542,0.99863,0.97872,0.97506,0.87968,0.51468,0.61519,0.90362,0.0007922,0.0007922,0.0007922
 63,1047.14,0.56914,0.5558,0.91865,0.99866,0.97872,0.97506,0.88691,0.51397,0.54698,0.90837,0.0007724,0.0007724,0.0007724
 64,1063.47,0.55618,0.54987,0.88579,0.99865,0.97872,0.97506,0.90335,0.49993,0.51709,0.89065,0.0007526,0.0007526,0.0007526
 65,1079.7,0.53892,0.53695,0.90014,0.99861,0.97872,0.97506,0.90518,0.53615,0.51287,0.90089,0.0007328,0.0007328,0.0007328
 66,1096.03,0.52733,0.51237,0.87921,0.99753,0.97872,0.97506,0.89833,0.54082,0.5022,0.90117,0.000713,0.000713,0.000713
 67,1112.36,0.51289,0.51338,0.8675,0.99761,0.97872,0.97507,0.91082,0.4392,0.50289,0.87438,0.0006932,0.0006932,0.0006932
 68,1129.26,0.51701,0.50177,0.90627,0.99755,0.97872,0.97507,0.90628,0.43663,0.50467,0.87736,0.0006734,0.0006734,0.0006734
 69,1145.59,0.55644,0.53077,0.89669,0.99734,0.97872,0.97507,0.9091,0.44588,0.54371,0.88767,0.0006536,0.0006536,0.0006536
 70,1162.7,0.5669,0.52751,0.90383,0.99726,0.97872,0.97507,0.91448,0.43112,0.53961,0.88243,0.0006338,0.0006338,0.0006338
 71,1179.38,0.52945,0.53576,0.91008,0.99701,0.97872,0.97507,0.91338,0.40923,0.50713,0.86706,0.000614,0.000614,0.000614
 72,1195.76,0.5045,0.5,0.83861,0.99672,0.97872,0.97507,0.92336,0.39388,0.45782,0.85291,0.0005942,0.0005942,0.0005942
 73,1212.84,0.52684,0.5122,0.86863,0.99873,0.97872,0.97507,0.92278,0.40641,0.50211,0.8596,0.0005744,0.0005744,0.0005744
 74,1229.11,0.55294,0.54271,0.88696,0.99862,0.97872,0.97507,0.90759,0.47393,0.51367,0.88525,0.0005546,0.0005546,0.0005546
 75,1245.48,0.51732,0.50029,0.85483,0.99845,0.97872,0.97506,0.91187,0.53175,0.48527,0.94813,0.0005348,0.0005348,0.0005348
 76,1261.78,0.5022,0.51302,0.8886,0.99847,0.97872,0.97506,0.90642,0.53595,0.47371,0.96317,0.000515,0.000515,0.000515
 77,1277.95,0.50634,0.52206,0.87813,0.99855,0.97872,0.97506,0.91129,0.53131,0.4618,0.96477,0.0004952,0.0004952,0.0004952
 78,1294.36,0.52087,0.47526,0.84153,0.9986,0.97872,0.97507,0.91053,0.54476,0.44952,0.97,0.0004754,0.0004754,0.0004754
 79,1310.72,0.50821,0.45477,0.87197,0.99864,0.97872,0.97507,0.90609,0.53997,0.44403,0.96696,0.0004556,0.0004556,0.0004556
 80,1326.99,0.47979,0.47719,0.84969,0.99869,0.97872,0.97507,0.91254,0.51575,0.4359,0.95256,0.0004358,0.0004358,0.0004358
 81,1343.24,0.48129,0.44147,0.86231,0.99872,0.97872,0.97507,0.91279,0.48954,0.41942,0.93704,0.000416,0.000416,0.000416
 82,1359.76,0.49291,0.45548,0.9074,0.99874,0.97872,0.97507,0.90741,0.48763,0.41879,0.92965,0.0003962,0.0003962,0.0003962
 83,1376.02,0.47079,0.46955,0.86087,0.99879,0.97872,0.97507,0.90904,0.50732,0.44106,0.91512,0.0003764,0.0003764,0.0003764
 84,1392.31,0.4745,0.45542,0.84629,0.99879,0.97872,0.97507,0.92615,0.49742,0.45247,0.9043,0.0003566,0.0003566,0.0003566
 85,1408.71,0.49559,0.46153,0.88865,0.99879,0.97872,0.97507,0.91666,0.48863,0.45425,0.8999,0.0003368,0.0003368,0.0003368
 86,1426.04,0.456,0.45025,0.84546,0.99879,0.97872,0.97507,0.9125,0.47711,0.45384,0.89409,0.000317,0.000317,0.000317
 87,1446.38,0.49383,0.47862,0.89165,0.9988,0.97872,0.97507,0.91593,0.46283,0.44674,0.88744,0.0002972,0.0002972,0.0002972
 88,1466.22,0.44404,0.44401,0.87019,0.9988,0.97872,0.97507,0.91409,0.46104,0.44208,0.88486,0.0002774,0.0002774,0.0002774
 89,1483.27,0.46838,0.44705,0.87652,0.99879,0.97872,0.97507,0.91786,0.45794,0.43956,0.88153,0.0002576,0.0002576,0.0002576
 90,1499.55,0.47186,0.45836,0.88991,0.99877,0.97872,0.97507,0.91223,0.43885,0.43136,0.87476,0.0002378,0.0002378,0.0002378
 91,1515.78,0.41417,0.49508,0.85674,0.99878,0.97872,0.97506,0.91813,0.39452,0.42742,0.86201,0.000218,0.000218,0.000218
 92,1531.92,0.37769,0.462,0.83662,0.99877,0.97872,0.97506,0.91767,0.38334,0.43829,0.85263,0.0001982,0.0001982,0.0001982
 93,1548.32,0.3924,0.45598,0.82236,0.99877,0.97872,0.97506,0.9216,0.37609,0.43095,0.84625,0.0001784,0.0001784,0.0001784
 94,1564.44,0.39674,0.46733,0.83448,0.99875,0.97872,0.97506,0.93113,0.38405,0.42572,0.84928,0.0001586,0.0001586,0.0001586
 95,1580.61,0.38629,0.47264,0.87183,0.99876,0.97872,0.97506,0.92702,0.38576,0.43328,0.85016,0.0001388,0.0001388,0.0001388
 96,1596.73,0.36293,0.45807,0.83221,0.99876,0.97872,0.97506,0.93093,0.38964,0.44193,0.85438,0.000119,0.000119,0.000119
 97,1612.83,0.36518,0.46312,0.85978,0.99875,0.97872,0.97506,0.93213,0.38821,0.44448,0.85668,9.92e-05,9.92e-05,9.92e-05
 98,1628.96,0.37402,0.4537,0.8557,0.99877,0.97872,0.97506,0.93936,0.38717,0.44483,0.85828,7.94e-05,7.94e-05,7.94e-05
 99,1645.2,0.38499,0.46885,0.83431,0.99875,0.97872,0.97506,0.93932,0.37754,0.43566,0.855,5.96e-05,5.96e-05,5.96e-05
 100,1661.36,0.3862,0.45546,0.86118,0.99876,0.97872,0.97506,0.93925,0.37097,0.43227,0.85101,3.98e-05,3.98e-05,3.98e-05
--- a/runs/detect/train40/results.png
+++ b/runs/detect/train40/results.png
--- a/runs/detect/train40/train_batch810.jpg
+++ b/runs/detect/train40/train_batch810.jpg
--- a/runs/detect/train40/train_batch811.jpg
+++ b/runs/detect/train40/train_batch811.jpg
--- a/runs/detect/train40/train_batch812.jpg
+++ b/runs/detect/train40/train_batch812.jpg
--- a/runs/detect/train40/val_batch0_labels.jpg
+++ b/runs/detect/train40/val_batch0_labels.jpg
--- a/runs/detect/train40/val_batch0_pred.jpg
+++ b/runs/detect/train40/val_batch0_pred.jpg
--- a/runs/detect/train40/val_batch1_labels.jpg
+++ b/runs/detect/train40/val_batch1_labels.jpg
--- a/runs/detect/train40/val_batch1_pred.jpg
+++ b/runs/detect/train40/val_batch1_pred.jpg
--- a/runs/detect/train40/val_batch2_labels.jpg
+++ b/runs/detect/train40/val_batch2_labels.jpg
--- a/runs/detect/train40/val_batch2_pred.jpg
+++ b/runs/detect/train40/val_batch2_pred.jpg
--- a/runs/detect/train40/weights/best.pt
+++ b/runs/detect/train40/weights/best.pt
--- a/runs/detect/train40/weights/last.pt
+++ b/runs/detect/train40/weights/last.pt
--- a/runs/detect/train402/F1_curve.png
+++ b/runs/detect/train402/F1_curve.png
--- a/runs/detect/train402/PR_curve.png
+++ b/runs/detect/train402/PR_curve.png
--- a/runs/detect/train402/P_curve.png
+++ b/runs/detect/train402/P_curve.png
--- a/runs/detect/train402/R_curve.png
+++ b/runs/detect/train402/R_curve.png
--- a/runs/detect/train402/confusion_matrix.png
+++ b/runs/detect/train402/confusion_matrix.png
--- a/runs/detect/train402/confusion_matrix_normalized.png
+++ b/runs/detect/train402/confusion_matrix_normalized.png
--- a/runs/detect/train402/val_batch0_labels.jpg
+++ b/runs/detect/train402/val_batch0_labels.jpg
--- a/runs/detect/train402/val_batch0_pred.jpg
+++ b/runs/detect/train402/val_batch0_pred.jpg
--- a/runs/detect/train402/val_batch1_labels.jpg
+++ b/runs/detect/train402/val_batch1_labels.jpg
--- a/runs/detect/train402/val_batch1_pred.jpg
+++ b/runs/detect/train402/val_batch1_pred.jpg
--- a/runs/detect/train402/val_batch2_labels.jpg
+++ b/runs/detect/train402/val_batch2_labels.jpg
--- a/runs/detect/train402/val_batch2_pred.jpg
+++ b/runs/detect/train402/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\train39\weights\best.pt")
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train40\weights\best.pt")
-results = model.predict("../res/4.mp4", show=True, save=True)
+results = model.predict("../res/5.mp4", show=True, save=True)
--- a/src/train.py
+++ b/src/train.py
@ -1,10 +1,12 @@
 from ultralytics import YOLO
 import time
 start_time = time.time()
-model = YOLO("yolov8n.pt")
+# model = YOLO("yolov8n.pt")
 model = YOLO(r"C:\workspace\le-yolo\runs\detect\train40\weights\last.pt")
 model.train(data="data.yaml", epochs=100,  batch=8, device='cpu',  imgsz=640, augment = True)
 model.val()
 print('训练完成')
 end_time  = time.time()
 run_time = end_time - start_time
-print('运行时间：', run_time, '秒')
+min = run_time // 60
 print('运行时间：', min, '分钟')