[CF]提交文件

runs/detect/train37/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: C:\workspace\le-yolo\runs\detect\train36\weights\last.pt
+data: data.yaml
+epochs: 100
+time: null
+patience: 100
+batch: 8
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: cpu
+workers: 8
+project: null
+name: train37
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: C:\workspace\le-yolo\runs\detect\train37

runs/detect/train37/results.csv

@@ -0,0 +1,101 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,7.95003,0.32567,0.27777,0.79257,0.88657,0.7234,0.82101,0.6098,1.92023,0.87522,3.23242,4e-05,4e-05,4e-05
+2,16.1421,0.298,0.29603,0.80742,0.88495,0.7234,0.8161,0.60972,1.92263,0.87913,3.25563,9.901e-05,9.901e-05,9.901e-05
+3,24.1688,0.22903,0.22469,0.75252,0.88161,0.7234,0.80324,0.61488,1.92853,0.90744,3.28161,0.000156832,0.000156832,0.000156832
+4,32.4691,0.25837,0.24291,0.79318,0.88974,0.7234,0.80293,0.61598,1.91826,0.93174,3.30049,0.000213466,0.000213466,0.000213466
+5,40.8701,0.28754,0.25707,0.78676,0.90964,0.70213,0.80073,0.62254,1.9134,0.94797,3.30921,0.000268912,0.000268912,0.000268912
+6,49.6888,0.32976,0.26174,0.80378,0.89457,0.72212,0.79847,0.62741,1.89663,0.94518,3.3256,0.00032317,0.00032317,0.00032317
+7,58.1908,0.31591,0.27325,0.81393,0.88547,0.70213,0.79742,0.63205,1.88941,0.95148,3.3211,0.00037624,0.00037624,0.00037624
+8,66.1901,0.30959,0.27278,0.79872,0.88404,0.70213,0.79665,0.62815,1.88318,0.97469,3.30226,0.000428122,0.000428122,0.000428122
+9,74.9494,0.32794,0.28353,0.76875,0.8805,0.70213,0.79703,0.61929,1.89461,0.99689,3.29722,0.000478816,0.000478816,0.000478816
+10,83.7561,0.41777,0.32964,0.85058,0.88959,0.68583,0.792,0.60892,1.92052,1.0204,3.29607,0.000528322,0.000528322,0.000528322
+11,92.5414,0.42902,0.29881,0.79612,0.88943,0.68471,0.79414,0.60328,1.93297,1.0152,3.28387,0.00057664,0.00057664,0.00057664
+12,101.307,0.36603,0.29384,0.79091,0.96866,0.6577,0.80156,0.60383,1.94505,1.01638,3.30972,0.00062377,0.00062377,0.00062377
+13,109.807,0.36668,0.28502,0.82007,0.96867,0.65792,0.79437,0.61116,1.94965,1.04174,3.32294,0.000669712,0.000669712,0.000669712
+14,117.815,0.37939,0.2927,0.80572,0.99745,0.6383,0.79695,0.60948,1.94903,1.078,3.2921,0.000714466,0.000714466,0.000714466
+15,125.622,0.42569,0.32305,0.81924,0.99745,0.6383,0.79695,0.60948,1.94903,1.078,3.2921,0.000758032,0.000758032,0.000758032
+16,133.801,0.34179,0.26023,0.7933,1,0.65216,0.78839,0.60195,1.95945,1.07991,3.26403,0.00080041,0.00080041,0.00080041
+17,141.762,0.37896,0.3058,0.79081,1,0.65715,0.79269,0.59973,2.00033,1.07287,3.25905,0.0008416,0.0008416,0.0008416
+18,149.618,0.42143,0.32108,0.81327,1,0.65715,0.79269,0.59973,2.00033,1.07287,3.25905,0.000881602,0.000881602,0.000881602
+19,157.401,0.32438,0.28121,0.75125,0.89045,0.6919,0.79613,0.59565,2.00422,1.02167,3.2725,0.000920416,0.000920416,0.000920416
+20,165.29,0.41612,0.30103,0.85153,0.91395,0.67798,0.79922,0.59839,1.98777,0.98635,3.31369,0.000958042,0.000958042,0.000958042
+21,173.049,0.51577,0.34504,0.84247,0.91395,0.67798,0.79922,0.59839,1.98777,0.98635,3.31369,0.00099448,0.00099448,0.00099448
+22,181.52,0.44192,0.3316,0.78953,0.86732,0.69553,0.77428,0.60264,1.96689,0.97545,3.36356,0.00102973,0.00102973,0.00102973
+23,189.452,0.48591,0.3374,0.84494,0.86732,0.69553,0.77428,0.60264,1.96689,0.97545,3.36356,0.00106379,0.00106379,0.00106379
+24,197.633,0.41566,0.3272,0.81965,0.86734,0.69568,0.76622,0.59901,1.94725,0.98899,3.40959,0.00109667,0.00109667,0.00109667
+25,205.774,0.42805,0.31737,0.79383,0.86734,0.69568,0.76622,0.59901,1.94725,0.98899,3.40959,0.00112835,0.00112835,0.00112835
+26,213.942,0.49699,0.34957,0.86716,0.84262,0.70213,0.76329,0.60383,1.955,1.00586,3.42118,0.00115885,0.00115885,0.00115885
+27,221.861,0.52854,0.34679,0.83192,0.84262,0.70213,0.76329,0.60383,1.955,1.00586,3.42118,0.00118816,0.00118816,0.00118816
+28,229.756,0.47508,0.33628,0.78094,0.96667,0.6383,0.76729,0.59988,1.97006,1.00027,3.43736,0.00121628,0.00121628,0.00121628
+29,237.613,0.40753,0.3248,0.81971,0.96667,0.6383,0.76729,0.59988,1.97006,1.00027,3.43736,0.00124322,0.00124322,0.00124322
+30,245.422,0.46855,0.33957,0.83293,0.96667,0.6383,0.76729,0.59988,1.97006,1.00027,3.43736,0.00126896,0.00126896,0.00126896
+31,253.586,0.44875,0.33158,0.83942,0.96165,0.68085,0.78683,0.61667,1.9898,0.9547,3.47161,0.00129352,0.00129352,0.00129352
+32,261.479,0.38018,0.31245,0.82953,0.96165,0.68085,0.78683,0.61667,1.9898,0.9547,3.47161,0.00131689,0.00131689,0.00131689
+33,269.5,0.42723,0.31661,0.80969,0.96427,0.68085,0.82413,0.61142,2.02612,0.88889,3.49381,0.00133907,0.00133907,0.00133907
+34,277.465,0.46419,0.35967,0.81705,0.96427,0.68085,0.82413,0.61142,2.02612,0.88889,3.49381,0.0013466,0.0013466,0.0013466
+35,286.267,0.44055,0.32526,0.79798,0.96427,0.68085,0.82413,0.61142,2.02612,0.88889,3.49381,0.0013268,0.0013268,0.0013268
+36,294.832,0.49247,0.32805,0.83552,0.91375,0.67632,0.80661,0.60158,2.04538,0.86125,3.50393,0.001307,0.001307,0.001307
+37,303.063,0.48706,0.32506,0.7951,0.91375,0.67632,0.80661,0.60158,2.04538,0.86125,3.50393,0.0012872,0.0012872,0.0012872
+38,310.897,0.54472,0.36198,0.7795,0.91375,0.67632,0.80661,0.60158,2.04538,0.86125,3.50393,0.0012674,0.0012674,0.0012674
+39,318.834,0.60229,0.40235,0.81024,0.98753,0.6383,0.79546,0.60461,2.00844,0.85695,3.50498,0.0012476,0.0012476,0.0012476
+40,327.064,0.54392,0.37821,0.88932,0.98753,0.6383,0.79546,0.60461,2.00844,0.85695,3.50498,0.0012278,0.0012278,0.0012278
+41,335.099,0.48987,0.34781,0.83311,0.99305,0.6383,0.76295,0.60753,1.95196,0.89293,3.50227,0.001208,0.001208,0.001208
+42,342.94,0.49943,0.36206,0.88794,0.99305,0.6383,0.76295,0.60753,1.95196,0.89293,3.50227,0.0011882,0.0011882,0.0011882
+43,350.724,0.53168,0.37784,0.85318,0.99305,0.6383,0.76295,0.60753,1.95196,0.89293,3.50227,0.0011684,0.0011684,0.0011684
+44,358.841,0.48026,0.32323,0.82805,0.93919,0.65732,0.75288,0.59644,1.89489,0.93265,3.43728,0.0011486,0.0011486,0.0011486
+45,367.235,0.47817,0.33588,0.81855,0.93919,0.65732,0.75288,0.59644,1.89489,0.93265,3.43728,0.0011288,0.0011288,0.0011288
+46,374.718,0.47735,0.34726,0.81497,0.93919,0.65732,0.75288,0.59644,1.89489,0.93265,3.43728,0.001109,0.001109,0.001109
+47,382.171,0.53274,0.35733,0.827,0.96447,0.6383,0.74791,0.59987,1.8863,0.98375,3.37524,0.0010892,0.0010892,0.0010892
+48,389.5,0.45228,0.32482,0.82346,0.96447,0.6383,0.74791,0.59987,1.8863,0.98375,3.37524,0.0010694,0.0010694,0.0010694
+49,396.985,0.38519,0.29235,0.79616,0.96769,0.63718,0.76674,0.61866,1.89778,1.01898,3.35371,0.0010496,0.0010496,0.0010496
+50,404.151,0.42674,0.33675,0.80645,0.96769,0.63718,0.76674,0.61866,1.89778,1.01898,3.35371,0.0010298,0.0010298,0.0010298
+51,411.316,0.43675,0.31832,0.78443,0.96769,0.63718,0.76674,0.61866,1.89778,1.01898,3.35371,0.00101,0.00101,0.00101
+52,418.45,0.48923,0.34622,0.80096,0.9014,0.68085,0.78429,0.62205,1.93623,1.03324,3.35306,0.0009902,0.0009902,0.0009902
+53,425.53,0.45956,0.34729,0.82005,0.9014,0.68085,0.78429,0.62205,1.93623,1.03324,3.35306,0.0009704,0.0009704,0.0009704
+54,432.998,0.47148,0.36725,0.80952,0.9014,0.68085,0.78429,0.62205,1.93623,1.03324,3.35306,0.0009506,0.0009506,0.0009506
+55,440.892,0.52212,0.37455,0.8684,0.94074,0.67559,0.78567,0.60949,1.97496,1.12751,3.33082,0.0009308,0.0009308,0.0009308
+56,448.841,0.48909,0.33077,0.82052,0.94074,0.67559,0.78567,0.60949,1.97496,1.12751,3.33082,0.000911,0.000911,0.000911
+57,457.237,0.45169,0.34139,0.81356,0.91226,0.68085,0.77816,0.60121,1.99595,1.25038,3.27048,0.0008912,0.0008912,0.0008912
+58,464.982,0.43371,0.33926,0.81177,0.91226,0.68085,0.77816,0.60121,1.99595,1.25038,3.27048,0.0008714,0.0008714,0.0008714
+59,472.52,0.46926,0.34772,0.78087,0.91226,0.68085,0.77816,0.60121,1.99595,1.25038,3.27048,0.0008516,0.0008516,0.0008516
+60,480.124,0.44435,0.3447,0.7987,0.91391,0.67765,0.75634,0.58707,2.00755,1.48145,3.21151,0.0008318,0.0008318,0.0008318
+61,488.122,0.37516,0.31585,0.76785,0.91391,0.67765,0.75634,0.58707,2.00755,1.48145,3.21151,0.000812,0.000812,0.000812
+62,496.18,0.42739,0.31334,0.81757,0.91391,0.67765,0.75634,0.58707,2.00755,1.48145,3.21151,0.0007922,0.0007922,0.0007922
+63,503.92,0.35688,0.31775,0.83449,0.95886,0.6383,0.73964,0.57895,1.98998,1.56766,3.17719,0.0007724,0.0007724,0.0007724
+64,511.657,0.47083,0.34682,0.86122,0.95886,0.6383,0.73964,0.57895,1.98998,1.56766,3.17719,0.0007526,0.0007526,0.0007526
+65,519.292,0.42381,0.308,0.8288,0.95616,0.65957,0.73959,0.57713,1.96236,1.63408,3.1384,0.0007328,0.0007328,0.0007328
+66,526.887,0.41907,0.32177,0.80649,0.95616,0.65957,0.73959,0.57713,1.96236,1.63408,3.1384,0.000713,0.000713,0.000713
+67,534.49,0.44403,0.34228,0.83091,0.95616,0.65957,0.73959,0.57713,1.96236,1.63408,3.1384,0.0006932,0.0006932,0.0006932
+68,541.994,0.43094,0.30689,0.83509,0.95229,0.6383,0.72453,0.57301,1.93048,1.53452,3.11053,0.0006734,0.0006734,0.0006734
+69,549.609,0.43473,0.32007,0.81512,0.95229,0.6383,0.72453,0.57301,1.93048,1.53452,3.11053,0.0006536,0.0006536,0.0006536
+70,557.362,0.34428,0.2709,0.7864,0.95229,0.6383,0.72453,0.57301,1.93048,1.53452,3.11053,0.0006338,0.0006338,0.0006338
+71,565.535,0.36505,0.30292,0.80656,0.98422,0.6383,0.72993,0.57265,1.93855,1.41402,3.12781,0.000614,0.000614,0.000614
+72,573.577,0.36691,0.30472,0.78999,0.98422,0.6383,0.72993,0.57265,1.93855,1.41402,3.12781,0.0005942,0.0005942,0.0005942
+73,582.232,0.36856,0.30893,0.82386,0.99003,0.6383,0.73597,0.57297,1.94036,1.40188,3.10195,0.0005744,0.0005744,0.0005744
+74,590.53,0.37341,0.32128,0.77437,0.99003,0.6383,0.73597,0.57297,1.94036,1.40188,3.10195,0.0005546,0.0005546,0.0005546
+75,597.896,0.36588,0.29135,0.81777,0.99003,0.6383,0.73597,0.57297,1.94036,1.40188,3.10195,0.0005348,0.0005348,0.0005348
+76,605.062,0.36989,0.30846,0.80583,1,0.65412,0.74334,0.57242,1.96056,1.42872,3.05714,0.000515,0.000515,0.000515
+77,612.231,0.40413,0.3006,0.8485,1,0.65412,0.74334,0.57242,1.96056,1.42872,3.05714,0.0004952,0.0004952,0.0004952
+78,619.336,0.50017,0.33594,0.84257,1,0.65412,0.74334,0.57242,1.96056,1.42872,3.05714,0.0004754,0.0004754,0.0004754
+79,626.556,0.40782,0.30418,0.82312,0.96952,0.6769,0.74734,0.56895,1.97144,1.46312,3.01376,0.0004556,0.0004556,0.0004556
+80,633.7,0.35281,0.28504,0.78898,0.96952,0.6769,0.74734,0.56895,1.97144,1.46312,3.01376,0.0004358,0.0004358,0.0004358
+81,640.996,0.32666,0.28593,0.85676,0.96009,0.68085,0.74655,0.57395,1.9735,1.47986,2.98044,0.000416,0.000416,0.000416
+82,648.153,0.3608,0.28343,0.80975,0.96009,0.68085,0.74655,0.57395,1.9735,1.47986,2.98044,0.0003962,0.0003962,0.0003962
+83,655.295,0.35393,0.27299,0.7407,0.96009,0.68085,0.74655,0.57395,1.9735,1.47986,2.98044,0.0003764,0.0003764,0.0003764
+84,662.521,0.41766,0.31876,0.87008,0.96472,0.68085,0.75045,0.587,1.96557,1.47483,2.96035,0.0003566,0.0003566,0.0003566
+85,669.644,0.29501,0.25728,0.80613,0.96472,0.68085,0.75045,0.587,1.96557,1.47483,2.96035,0.0003368,0.0003368,0.0003368
+86,676.93,0.35303,0.28266,0.78507,0.96472,0.68085,0.75045,0.587,1.96557,1.47483,2.96035,0.000317,0.000317,0.000317
+87,684.309,0.4529,0.34314,0.82019,0.96382,0.68085,0.75082,0.59002,1.94739,1.48231,2.94828,0.0002972,0.0002972,0.0002972
+88,691.557,0.33438,0.29299,0.82611,0.96382,0.68085,0.75082,0.59002,1.94739,1.48231,2.94828,0.0002774,0.0002774,0.0002774
+89,699.1,0.31265,0.244,0.78296,0.96956,0.67768,0.75704,0.5968,1.92316,1.51759,2.92821,0.0002576,0.0002576,0.0002576
+90,706.855,0.28191,0.26141,0.81374,0.96956,0.67768,0.75704,0.5968,1.92316,1.51759,2.92821,0.0002378,0.0002378,0.0002378
+91,714.9,0.38668,0.30909,0.7702,0.96956,0.67768,0.75704,0.5968,1.92316,1.51759,2.92821,0.000218,0.000218,0.000218
+92,722.49,0.31239,0.24597,0.70615,0.96895,0.68085,0.75589,0.59843,1.90459,1.48869,2.95784,0.0001982,0.0001982,0.0001982
+93,729.917,0.3361,0.25473,0.7747,0.96895,0.68085,0.75589,0.59843,1.90459,1.48869,2.95784,0.0001784,0.0001784,0.0001784
+94,737.136,0.31793,0.25355,0.85354,0.96895,0.68085,0.75589,0.59843,1.90459,1.48869,2.95784,0.0001586,0.0001586,0.0001586
+95,744.526,0.30198,0.22938,0.77425,0.96208,0.68085,0.75967,0.60633,1.89703,1.42654,2.98572,0.0001388,0.0001388,0.0001388
+96,752.052,0.29979,0.23958,0.7944,0.96208,0.68085,0.75967,0.60633,1.89703,1.42654,2.98572,0.000119,0.000119,0.000119
+97,759.889,0.33518,0.23319,0.825,0.96173,0.68085,0.75702,0.60612,1.87737,1.31697,2.98547,9.92e-05,9.92e-05,9.92e-05
+98,767.623,0.32568,0.24092,0.71382,0.96173,0.68085,0.75702,0.60612,1.87737,1.31697,2.98547,7.94e-05,7.94e-05,7.94e-05
+99,775.455,0.34399,0.24876,0.72955,0.96173,0.68085,0.75702,0.60612,1.87737,1.31697,2.98547,5.96e-05,5.96e-05,5.96e-05
+100,783.323,0.32392,0.2426,0.76629,0.96112,0.68085,0.75554,0.60325,1.85145,1.24333,2.96824,3.98e-05,3.98e-05,3.98e-05

runs/detect/train38/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: C:\workspace\le-yolo\runs\detect\train34\weights\last.pt
+data: data.yaml
+epochs: 100
+time: null
+patience: 100
+batch: 8
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: cpu
+workers: 8
+project: null
+name: train38
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: true
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: C:\workspace\le-yolo\runs\detect\train38

runs/detect/train38/results.csv

@@ -0,0 +1,14 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,7.63419,0.30828,0.28183,0.78764,0.86722,0.69493,0.79783,0.60216,1.87359,0.91892,2.94203,4e-05,4e-05,4e-05
+2,14.645,0.35212,0.30821,0.80886,0.86631,0.68952,0.80227,0.60808,1.86119,0.91462,2.95005,9.901e-05,9.901e-05,9.901e-05
+3,21.7566,0.26862,0.2501,0.75986,0.88308,0.68085,0.80748,0.61797,1.85552,0.89891,2.98183,0.000156832,0.000156832,0.000156832
+4,29.1495,0.28496,0.2599,0.79828,0.96558,0.65957,0.81509,0.62687,1.85645,0.88115,3.00633,0.000213466,0.000213466,0.000213466
+5,36.5832,0.33966,0.28165,0.80119,0.96147,0.65957,0.81595,0.62653,1.86387,0.88326,3.01386,0.000268912,0.000268912,0.000268912
+6,44.4226,0.33829,0.28887,0.80318,0.96183,0.65957,0.81014,0.62147,1.86848,0.86437,3.05306,0.00032317,0.00032317,0.00032317
+7,52.4005,0.31478,0.28083,0.81064,0.96355,0.65957,0.78394,0.60928,1.86892,0.87634,3.05709,0.00037624,0.00037624,0.00037624
+8,60.477,0.34567,0.29483,0.80056,0.96464,0.65957,0.77884,0.60987,1.86904,0.89065,3.05554,0.000428122,0.000428122,0.000428122
+9,67.7826,0.33369,0.31412,0.7704,0.96851,0.65445,0.77243,0.61168,1.87493,0.93488,3.07352,0.000478816,0.000478816,0.000478816
+10,75.0285,0.49483,0.32269,0.87559,0.93359,0.65957,0.7765,0.60857,1.86432,0.99859,3.02147,0.000528322,0.000528322,0.000528322
+11,82.2757,0.39982,0.29848,0.79798,0.91385,0.6772,0.78622,0.60723,1.86969,1.09871,2.9569,0.00057664,0.00057664,0.00057664
+12,89.8078,0.42748,0.30629,0.80657,0.97466,0.65957,0.78702,0.60116,1.86946,1.17368,2.89691,0.00062377,0.00062377,0.00062377
+13,97.6266,0.38214,0.32367,0.82461,0.96398,0.65957,0.79028,0.59399,1.86126,1.28949,2.79979,0.000669712,0.000669712,0.000669712

src/data.yaml

@@ -4,3 +4,14 @@ val: images/val
 test: images/train
 nc: 1
 names: [ 'person' ]
+augment:
+  flipud: 0.5 # 50% 概率进行垂直翻转
+  fliplr: 0.5 # 50% 概率进行水平翻转
+  mosaic: 1.0 # 启用 Mosaic 数据增强
+  mixup: 0.5 # 启用 Mixup 数据增强
+  hsv_h: 0.015 # 色调增强，范围为 ±0.015
+  hsv_s: 0.7 # 饱和度增强，范围为 ±0.7
+  hsv_v: 0.4 # 亮度增强，范围为 ±0.4
+  scale: 0.5 # 随机缩放，范围为 ±50%
+  shear: 0.0 # 随机剪切，设置为 0 禁用
+  perspective: 0.0 # 随机透视变换，设置为 0 禁用

src/labels.py

@@ -1,6 +1,7 @@
 import torch
 from ultralytics import YOLO
 import os
+
 class Yolov8Detect():
     def __init__(self, weights):
         cuda = True if torch.cuda.is_available() else False

src/test.py

@@ -1,3 +1,3 @@
 from ultralytics import YOLO
-model = YOLO(r"C:\workspace\le-yolo\runs\detect\train36\weights\best.pt")
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train38\weights\best.pt")
 results = model.predict("../res/4.mp4", show=True, save=True)

src/train.py

@@ -1,5 +1,5 @@
 from ultralytics import YOLO
-model = YOLO(r"C:\workspace\le-yolo\runs\detect\train36\weights\last.pt")
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train34\weights\last.pt")
-model.train(data="data.yaml", epochs=100,  batch=8, device='cpu',  imgsz=640)
+model.train(data="data.yaml", epochs=100,  batch=8, device='cpu',  imgsz=640, augment = True)
 model.val()
 print('训练完成')