[CF]提交文件

runs/detect/train27/results.csv

@@ -53,3 +53,49 @@ epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),met
 52,642.866,0.45736,0.42001,0.86042,0.995,0.97872,0.97579,0.91128,0.44751,0.38538,0.87923,0.0009902,0.0009902,0.0009902
 53,655.752,0.50949,0.40852,0.84028,0.99695,0.97872,0.97587,0.89758,0.42592,0.394,0.86972,0.0009704,0.0009704,0.0009704
 54,669.236,0.51675,0.42571,0.90519,0.99695,0.97872,0.97587,0.89758,0.42592,0.394,0.86972,0.0009506,0.0009506,0.0009506
+55,684.522,0.51549,0.44171,0.86596,0.99772,0.97872,0.97602,0.90772,0.4241,0.4243,0.87173,0.0009308,0.0009308,0.0009308
+56,699.009,0.43566,0.45707,0.77815,0.99802,0.97872,0.97618,0.91811,0.47426,0.4429,0.90565,0.000911,0.000911,0.000911
+57,711.707,0.44331,0.38959,0.87796,0.99802,0.97872,0.97645,0.91774,0.53877,0.50974,0.98151,0.0008912,0.0008912,0.0008912
+58,724.385,0.52104,0.41772,0.89773,0.99807,0.97872,0.97681,0.90763,0.57093,0.47406,1.03008,0.0008714,0.0008714,0.0008714
+59,736.77,0.45971,0.39982,0.90185,0.99865,0.97872,0.97715,0.89895,0.53644,0.47611,0.97104,0.0008516,0.0008516,0.0008516
+60,748.907,0.4667,0.40731,0.8844,0.99859,0.97872,0.97724,0.91679,0.51662,0.47041,0.92538,0.0008318,0.0008318,0.0008318
+61,761.053,0.48002,0.37858,0.89243,0.99837,0.97872,0.97717,0.91843,0.46335,0.442,0.88409,0.000812,0.000812,0.000812
+62,773.145,0.43463,0.36283,0.88207,0.99837,0.97872,0.97717,0.91843,0.46335,0.442,0.88409,0.0007922,0.0007922,0.0007922
+63,785.412,0.43289,0.39154,0.84871,0.99813,0.97872,0.97739,0.9354,0.40914,0.40732,0.86189,0.0007724,0.0007724,0.0007724
+64,797.744,0.43502,0.38236,0.91039,0.99827,0.97872,0.97784,0.93752,0.37865,0.37176,0.85167,0.0007526,0.0007526,0.0007526
+65,810.068,0.43921,0.41188,0.86485,0.99846,0.97872,0.97884,0.9381,0.35086,0.3462,0.83593,0.0007328,0.0007328,0.0007328
+66,822.284,0.44575,0.3927,0.86253,0.99864,0.97872,0.97944,0.93368,0.32992,0.32072,0.82701,0.000713,0.000713,0.000713
+67,834.473,0.46097,0.41194,0.89441,0.99872,0.97872,0.9798,0.94983,0.31568,0.32609,0.82776,0.0006932,0.0006932,0.0006932
+68,846.959,0.40676,0.3752,0.84464,0.99868,0.97872,0.97935,0.93999,0.31936,0.34046,0.83023,0.0006734,0.0006734,0.0006734
+69,859.17,0.47302,0.4116,0.89503,0.9987,0.97872,0.97938,0.93014,0.32576,0.34619,0.82973,0.0006536,0.0006536,0.0006536
+70,871.788,0.52011,0.39728,0.85958,0.9987,0.97872,0.97938,0.93014,0.32576,0.34619,0.82973,0.0006338,0.0006338,0.0006338
+71,884.043,0.58306,0.41963,0.95591,0.99873,0.97872,0.97854,0.92242,0.32627,0.33877,0.83329,0.000614,0.000614,0.000614
+72,896.191,0.44905,0.40614,0.83903,0.99844,0.97872,0.97813,0.92729,0.34406,0.34312,0.83949,0.0005942,0.0005942,0.0005942
+73,908.587,0.50462,0.45495,0.92286,0.99833,0.97872,0.97786,0.93191,0.35212,0.34966,0.84209,0.0005744,0.0005744,0.0005744
+74,920.956,0.49598,0.4015,0.91827,0.99864,0.97872,0.97752,0.93552,0.34121,0.34949,0.83354,0.0005546,0.0005546,0.0005546
+75,933.127,0.43941,0.35474,0.85717,0.99888,0.97872,0.97728,0.94156,0.32274,0.33697,0.83019,0.0005348,0.0005348,0.0005348
+76,945.319,0.33304,0.35789,0.75322,0.99887,0.97872,0.97697,0.94246,0.31782,0.30712,0.82927,0.000515,0.000515,0.000515
+77,957.422,0.42698,0.36528,0.87527,0.99887,0.97872,0.97668,0.93877,0.31583,0.29704,0.82583,0.0004952,0.0004952,0.0004952
+78,969.506,0.41869,0.35186,0.85568,0.99887,0.97872,0.97668,0.93877,0.31583,0.29704,0.82583,0.0004754,0.0004754,0.0004754
+79,981.665,0.52069,0.44429,0.93525,0.99886,0.97872,0.97674,0.93952,0.30169,0.28544,0.8193,0.0004556,0.0004556,0.0004556
+80,993.91,0.49789,0.39059,0.87927,0.99887,0.97872,0.97674,0.94902,0.31148,0.29732,0.81772,0.0004358,0.0004358,0.0004358
+81,1006.02,0.31553,0.48867,0.72427,0.99888,0.97872,0.97694,0.93883,0.3188,0.31809,0.81523,0.000416,0.000416,0.000416
+82,1018.11,0.40259,0.32382,0.80621,0.99889,0.97872,0.97754,0.94697,0.32522,0.3372,0.81375,0.0003962,0.0003962,0.0003962
+83,1030.39,0.38935,0.33893,0.85587,0.99891,0.97872,0.97806,0.95306,0.32833,0.3454,0.81443,0.0003764,0.0003764,0.0003764
+84,1042.67,0.40809,0.33476,0.86239,0.99892,0.97872,0.97833,0.95458,0.33555,0.34576,0.81603,0.0003566,0.0003566,0.0003566
+85,1055.11,0.37372,0.32195,0.87594,0.99893,0.97872,0.97864,0.95668,0.33034,0.34069,0.81314,0.0003368,0.0003368,0.0003368
+86,1067.38,0.34389,0.35748,0.71996,0.99893,0.97872,0.97864,0.95668,0.33034,0.34069,0.81314,0.000317,0.000317,0.000317
+87,1079.54,0.42785,0.34565,0.86451,0.99893,0.97872,0.97898,0.96041,0.32701,0.33851,0.81154,0.0002972,0.0002972,0.0002972
+88,1091.67,0.42802,0.39065,0.84544,0.99894,0.97872,0.97973,0.95603,0.33187,0.33307,0.81161,0.0002774,0.0002774,0.0002774
+89,1103.77,0.34123,0.3423,0.73218,0.99893,0.97872,0.9809,0.95938,0.32137,0.32051,0.80593,0.0002576,0.0002576,0.0002576
+90,1116.04,0.44599,0.36038,0.85304,0.99892,0.97872,0.98183,0.96393,0.30159,0.31016,0.79929,0.0002378,0.0002378,0.0002378
+91,1128.28,0.33562,0.32043,0.8962,0.9989,0.97872,0.98176,0.96518,0.28064,0.30545,0.79248,0.000218,0.000218,0.000218
+92,1140.55,0.29044,0.29998,0.82584,0.99888,0.97872,0.98136,0.96358,0.26929,0.29644,0.78901,0.0001982,0.0001982,0.0001982
+93,1152.73,0.37089,0.34126,0.84921,0.99886,0.97872,0.9805,0.95585,0.26883,0.29813,0.78796,0.0001784,0.0001784,0.0001784
+94,1164.71,0.3162,0.30507,0.83164,0.99886,0.97872,0.9805,0.95585,0.26883,0.29813,0.78796,0.0001586,0.0001586,0.0001586
+95,1177.4,0.33659,0.29096,0.81282,0.99881,0.97872,0.98023,0.95581,0.26573,0.29376,0.78614,0.0001388,0.0001388,0.0001388
+96,1189.79,0.33457,0.31,0.85468,0.9988,0.97872,0.98019,0.95007,0.25759,0.28612,0.78493,0.000119,0.000119,0.000119
+97,1201.95,0.31452,0.29857,0.78745,0.99877,0.97872,0.98015,0.95625,0.24977,0.27814,0.78481,9.92e-05,9.92e-05,9.92e-05
+98,1214.46,0.28257,0.30092,0.73517,0.99877,0.97872,0.97991,0.95591,0.24404,0.27119,0.78563,7.94e-05,7.94e-05,7.94e-05
+99,1226.52,0.3032,0.30324,0.79579,0.99876,0.97872,0.9795,0.95321,0.24443,0.26892,0.78643,5.96e-05,5.96e-05,5.96e-05
+100,1238.62,0.28926,0.29137,0.84311,0.99876,0.97872,0.97947,0.95331,0.24457,0.27006,0.78689,3.98e-05,3.98e-05,3.98e-05

runs/detect/train28/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: C:\workspace\le-yolo\runs\detect\train27\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: train28
+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\train28

runs/detect/train28/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
+1,12.8898,0.42045,0.35811,0.83878,0.99888,0.97872,0.98045,0.94717,0.25909,0.25594,0.79012,0.00012,0.00012,0.00012
+2,25.2346,0.35106,0.32729,0.81189,0.9987,0.97872,0.97796,0.94786,0.28372,0.28065,0.79161,0.000257426,0.000257426,0.000257426
+3,37.509,0.42684,0.36561,0.92835,0.99873,0.97872,0.97651,0.91721,0.36242,0.36029,0.82176,0.00039208,0.00039208,0.00039208
+4,49.7907,0.48991,0.42391,0.97558,0.9987,0.97872,0.97668,0.9092,0.48784,0.3597,0.88719,0.000523962,0.000523962,0.000523962
+5,62,0.4171,0.36673,0.84649,0.99866,0.97872,0.97694,0.90723,0.41375,0.31067,0.83483,0.000653072,0.000653072,0.000653072
+6,74.5189,0.46492,0.36189,0.86238,0.99874,0.97872,0.97706,0.90584,0.36981,0.33527,0.81853,0.00077941,0.00077941,0.00077941
+7,87.0543,0.45367,0.35448,0.85598,0.99877,0.97872,0.9774,0.9174,0.36202,0.35508,0.81799,0.000902976,0.000902976,0.000902976
+8,99.7457,0.468,0.35802,0.88222,0.99868,0.97872,0.97886,0.89385,0.40219,0.34555,0.81661,0.00102377,0.00102377,0.00102377
+9,112.075,0.42675,0.34936,0.83937,0.99867,0.97872,0.97908,0.89783,0.39352,0.3544,0.81836,0.00114179,0.00114179,0.00114179
+10,124.251,0.46832,0.39023,0.87854,0.99857,0.97872,0.97852,0.9185,0.40772,0.35783,0.83179,0.00125704,0.00125704,0.00125704
+11,136.43,0.49747,0.39796,0.92529,0.99838,0.97872,0.97724,0.90424,0.46589,0.37978,0.85472,0.00136952,0.00136952,0.00136952
+12,148.75,0.47779,0.40427,0.85314,0.99826,0.97872,0.97752,0.88793,0.4349,0.41487,0.84797,0.00147923,0.00147923,0.00147923
+13,160.981,0.49587,0.41066,0.85236,0.99814,0.97872,0.97806,0.89666,0.38742,0.38746,0.82839,0.00158616,0.00158616,0.00158616
+14,173.222,0.60818,0.48836,1.0053,0.99814,0.97872,0.97806,0.89666,0.38742,0.38746,0.82839,0.00169032,0.00169032,0.00169032
+15,185.505,0.5591,0.45534,0.90106,0.99873,0.97872,0.97963,0.90732,0.38875,0.36032,0.83228,0.0017228,0.0017228,0.0017228
+16,197.784,0.49203,0.41578,0.86667,0.99883,0.97872,0.97995,0.88718,0.42631,0.38961,0.85123,0.001703,0.001703,0.001703
+17,210.602,0.50972,0.41536,0.84633,0.99879,0.97872,0.97858,0.90502,0.45283,0.40764,0.86435,0.0016832,0.0016832,0.0016832
+18,223.162,0.50205,0.42412,0.8768,0.99881,0.97872,0.97689,0.8975,0.43323,0.38334,0.85573,0.0016634,0.0016634,0.0016634
+19,235.758,0.51367,0.42235,0.91477,0.99855,0.97872,0.97622,0.89677,0.44669,0.38793,0.8636,0.0016436,0.0016436,0.0016436
+20,248.34,0.47927,0.41004,0.88417,0.99837,0.97872,0.97598,0.88506,0.46257,0.41785,0.88352,0.0016238,0.0016238,0.0016238
+21,260.744,0.49621,0.42791,0.85998,1,0.97494,0.97583,0.86898,0.52189,0.43437,0.9222,0.001604,0.001604,0.001604
+22,273.076,0.51594,0.43627,0.87771,1,0.97494,0.97583,0.86898,0.52189,0.43437,0.9222,0.0015842,0.0015842,0.0015842
+23,285.571,0.51302,0.4198,0.88604,0.99844,0.97872,0.97586,0.91783,0.45922,0.41468,0.92684,0.0015644,0.0015644,0.0015644
+24,298.064,0.5295,0.4135,0.89507,0.99867,0.97872,0.9761,0.90927,0.4924,0.41789,0.92029,0.0015446,0.0015446,0.0015446
+25,310.664,0.53314,0.41396,0.87422,0.99867,0.97872,0.97625,0.86547,0.52732,0.44117,0.91177,0.0015248,0.0015248,0.0015248
+26,323.099,0.5168,0.41398,0.87366,0.99857,0.97872,0.97623,0.8876,0.50863,0.45359,0.89227,0.001505,0.001505,0.001505
+27,336.014,0.50949,0.4285,0.9138,0.99851,0.97872,0.97602,0.88947,0.45507,0.41671,0.8743,0.0014852,0.0014852,0.0014852
+28,348.379,0.51373,0.41268,0.88484,0.99894,0.97872,0.97583,0.90491,0.42585,0.38745,0.86905,0.0014654,0.0014654,0.0014654
+29,360.713,0.59736,0.45199,1.01931,0.99887,0.97872,0.97578,0.91282,0.40277,0.35426,0.85866,0.0014456,0.0014456,0.0014456
+30,380.95,0.54852,0.40149,0.8981,0.99887,0.97872,0.97578,0.91282,0.40277,0.35426,0.85866,0.0014258,0.0014258,0.0014258
+31,400.231,0.53546,0.39386,0.88916,1,0.97753,0.97569,0.90832,0.39341,0.35966,0.84885,0.001406,0.001406,0.001406
+32,412.456,0.4968,0.39358,0.8874,0.99855,0.97872,0.97563,0.91558,0.39661,0.35247,0.84648,0.0013862,0.0013862,0.0013862
+33,424.565,0.69685,0.42992,1.14738,0.99846,0.97872,0.97569,0.90825,0.40487,0.33801,0.8449,0.0013664,0.0013664,0.0013664
+34,436.876,0.50861,0.37221,0.85299,0.99858,0.97872,0.97598,0.92767,0.38705,0.33415,0.85492,0.0013466,0.0013466,0.0013466
+35,449.112,0.50912,0.3935,0.93167,0.99873,0.97872,0.97632,0.90494,0.43978,0.34657,0.90764,0.0013268,0.0013268,0.0013268
+36,461.509,0.49925,0.38904,0.87365,0.99867,0.97872,0.97669,0.91411,0.3946,0.35283,0.88274,0.001307,0.001307,0.001307
+37,475.887,0.50156,0.37965,0.8218,0.99881,0.97872,0.97714,0.91877,0.39932,0.35709,0.88075,0.0012872,0.0012872,0.0012872
+38,488.154,0.48354,0.37645,0.85872,0.99881,0.97872,0.97714,0.91877,0.39932,0.35709,0.88075,0.0012674,0.0012674,0.0012674
+39,500.907,0.45268,0.36231,0.81738,0.99894,0.97872,0.97724,0.89576,0.44908,0.36364,0.89408,0.0012476,0.0012476,0.0012476
+40,514.827,0.48821,0.36677,0.84483,0.99898,0.97872,0.9777,0.89226,0.46507,0.36343,0.89683,0.0012278,0.0012278,0.0012278
+41,529.143,0.51124,0.37549,0.93212,0.99886,0.97872,0.97775,0.89984,0.42873,0.36872,0.89283,0.001208,0.001208,0.001208
+42,542.346,0.48834,0.37426,0.90231,0.99882,0.97872,0.97805,0.90368,0.42706,0.33498,0.91146,0.0011882,0.0011882,0.0011882
+43,555.384,0.49343,0.35605,0.84723,0.99874,0.97872,0.97831,0.91179,0.40411,0.31937,0.91146,0.0011684,0.0011684,0.0011684
+44,567.516,0.47956,0.37061,0.91986,0.99872,0.97872,0.97788,0.91241,0.42681,0.32234,0.88364,0.0011486,0.0011486,0.0011486
+45,579.755,0.47351,0.34208,0.84733,0.99864,0.97872,0.97731,0.92169,0.416,0.32044,0.87003,0.0011288,0.0011288,0.0011288
+46,591.908,0.66822,0.51659,0.99349,0.99864,0.97872,0.97731,0.92169,0.416,0.32044,0.87003,0.001109,0.001109,0.001109
+47,604.039,0.48248,0.38953,0.87439,0.99846,0.97872,0.97691,0.91944,0.39587,0.32528,0.86492,0.0010892,0.0010892,0.0010892
+48,616.306,0.44215,0.33933,0.8316,0.9985,0.97872,0.97695,0.91828,0.39513,0.31652,0.86306,0.0010694,0.0010694,0.0010694
+49,628.405,0.46974,0.42094,0.89366,0.99876,0.97872,0.97769,0.92599,0.38188,0.30558,0.85999,0.0010496,0.0010496,0.0010496
+50,640.463,0.39522,0.34726,0.87482,0.99874,0.97872,0.97873,0.92599,0.38272,0.32357,0.86347,0.0010298,0.0010298,0.0010298
+51,652.872,0.46654,0.36193,0.86166,0.99864,0.97872,0.97916,0.91349,0.39986,0.33621,0.85705,0.00101,0.00101,0.00101
+52,665.015,0.45287,0.3511,0.87112,0.99873,0.97872,0.98003,0.91012,0.43681,0.31813,0.85845,0.0009902,0.0009902,0.0009902
+53,677.337,0.52232,0.3657,0.84321,0.99864,0.97872,0.98027,0.91412,0.43278,0.32396,0.85777,0.0009704,0.0009704,0.0009704
+54,689.989,0.45584,0.3607,0.88242,0.99864,0.97872,0.98027,0.91412,0.43278,0.32396,0.85777,0.0009506,0.0009506,0.0009506
+55,702.772,0.53684,0.3668,0.87466,0.99853,0.97872,0.98074,0.9279,0.41034,0.32684,0.85732,0.0009308,0.0009308,0.0009308
+56,715.209,0.39035,0.33511,0.75192,0.99852,0.97872,0.98032,0.92524,0.39062,0.31801,0.84513,0.000911,0.000911,0.000911
+57,727.55,0.41096,0.34614,0.86737,0.99859,0.97872,0.9805,0.9288,0.37836,0.32234,0.84203,0.0008912,0.0008912,0.0008912
+58,740.092,0.43703,0.36361,0.87275,0.99866,0.97872,0.98205,0.93833,0.37688,0.3239,0.83576,0.0008714,0.0008714,0.0008714
+59,752.232,0.42748,0.33582,0.87849,0.99879,0.97872,0.98321,0.93783,0.38368,0.29086,0.82562,0.0008516,0.0008516,0.0008516
+60,764.467,0.45502,0.33375,0.88375,0.99882,0.97872,0.98353,0.95411,0.3452,0.28943,0.82145,0.0008318,0.0008318,0.0008318
+61,778.116,0.42438,0.31405,0.87841,0.99871,0.97872,0.98263,0.95423,0.3198,0.25891,0.80635,0.000812,0.000812,0.000812
+62,801.793,0.35721,0.28666,0.85522,0.99871,0.97872,0.98263,0.95423,0.3198,0.25891,0.80635,0.0007922,0.0007922,0.0007922
+63,818.152,0.39025,0.32622,0.84043,0.99846,0.97872,0.98136,0.9542,0.3144,0.2614,0.80204,0.0007724,0.0007724,0.0007724
+64,830.445,0.41269,0.33488,0.89536,0.99843,0.97872,0.98162,0.95645,0.31942,0.26337,0.80933,0.0007526,0.0007526,0.0007526
+65,842.604,0.39713,0.32425,0.85552,0.99857,0.97872,0.9844,0.95287,0.34574,0.28552,0.82599,0.0007328,0.0007328,0.0007328
+66,854.749,0.40625,0.33846,0.84377,0.99877,0.97872,0.98638,0.95786,0.36686,0.3005,0.83526,0.000713,0.000713,0.000713
+67,867.101,0.41966,0.34919,0.87871,0.99876,0.97872,0.98513,0.95168,0.37638,0.28713,0.84464,0.0006932,0.0006932,0.0006932
+68,879.61,0.40099,0.3142,0.84361,0.9987,0.97872,0.98301,0.95025,0.38194,0.26652,0.85218,0.0006734,0.0006734,0.0006734
+69,891.775,0.41387,0.3339,0.87537,0.99866,0.97872,0.98183,0.94997,0.37499,0.28858,0.84238,0.0006536,0.0006536,0.0006536
+70,903.962,0.45338,0.33663,0.8423,0.99866,0.97872,0.98183,0.94997,0.37499,0.28858,0.84238,0.0006338,0.0006338,0.0006338
+71,916.062,0.50643,0.33279,0.9241,0.99863,0.97872,0.98045,0.93756,0.36763,0.29023,0.83293,0.000614,0.000614,0.000614
+72,928.252,0.45032,0.36154,0.82999,0.99861,0.97872,0.97911,0.93056,0.35907,0.27206,0.82151,0.0005942,0.0005942,0.0005942
+73,941.067,0.45296,0.36075,0.90313,0.99861,0.97872,0.97879,0.94404,0.33268,0.25472,0.80681,0.0005744,0.0005744,0.0005744
+74,953.719,0.44318,0.33914,0.87394,0.99864,0.97872,0.97886,0.95475,0.29298,0.24309,0.79194,0.0005546,0.0005546,0.0005546
+75,966.298,0.39712,0.29869,0.83828,0.9986,0.97872,0.9793,0.95507,0.27014,0.23423,0.78235,0.0005348,0.0005348,0.0005348
+76,978.458,0.36501,0.30713,0.75332,0.99857,0.97872,0.98015,0.94481,0.26685,0.23692,0.77925,0.000515,0.000515,0.000515
+77,990.708,0.43407,0.3047,0.86787,0.99862,0.97872,0.98074,0.94518,0.26936,0.23827,0.77974,0.0004952,0.0004952,0.0004952
+78,1002.92,0.39178,0.29779,0.84488,0.99862,0.97872,0.98074,0.94518,0.26936,0.23827,0.77974,0.0004754,0.0004754,0.0004754
+79,1015.02,0.47965,0.3819,0.93702,0.99867,0.97872,0.98112,0.94772,0.27123,0.22973,0.78087,0.0004556,0.0004556,0.0004556
+80,1027.32,0.45112,0.3419,0.86119,0.99872,0.97872,0.98213,0.94717,0.29609,0.24435,0.78522,0.0004358,0.0004358,0.0004358
+81,1039.86,0.3028,0.33919,0.71928,0.99876,0.97872,0.98281,0.94487,0.3121,0.24699,0.79206,0.000416,0.000416,0.000416
+82,1052.41,0.35602,0.28423,0.79771,0.99878,0.97872,0.98342,0.94624,0.31603,0.24031,0.79987,0.0003962,0.0003962,0.0003962
+83,1064.77,0.35567,0.27337,0.84639,0.99882,0.97872,0.98332,0.94743,0.32053,0.23592,0.80526,0.0003764,0.0003764,0.0003764
+84,1076.96,0.36042,0.28098,0.85128,0.99884,0.97872,0.98221,0.94796,0.32919,0.24268,0.81042,0.0003566,0.0003566,0.0003566
+85,1089.26,0.37428,0.28026,0.87265,0.99886,0.97872,0.98221,0.94908,0.31776,0.25241,0.805,0.0003368,0.0003368,0.0003368
+86,1101.59,0.31867,0.25367,0.71689,0.99886,0.97872,0.98221,0.94908,0.31776,0.25241,0.805,0.000317,0.000317,0.000317
+87,1114.06,0.38496,0.30786,0.84856,0.99886,0.97872,0.98229,0.94861,0.31084,0.25736,0.80439,0.0002972,0.0002972,0.0002972
+88,1126.85,0.39607,0.33479,0.83886,0.99887,0.97872,0.98263,0.94704,0.30677,0.26994,0.80285,0.0002774,0.0002774,0.0002774
+89,1139.04,0.32131,0.26493,0.72703,0.99886,0.97872,0.98301,0.95294,0.29747,0.26916,0.79741,0.0002576,0.0002576,0.0002576
+90,1151.37,0.44532,0.33387,0.85804,0.99888,0.97872,0.98272,0.95811,0.28496,0.26672,0.79204,0.0002378,0.0002378,0.0002378
+91,1163.63,0.33359,0.28629,0.88836,0.99889,0.97872,0.98169,0.9563,0.26795,0.25706,0.78541,0.000218,0.000218,0.000218
+92,1175.9,0.29363,0.26195,0.82068,0.99889,0.97872,0.98032,0.95598,0.25763,0.24138,0.78058,0.0001982,0.0001982,0.0001982
+93,1188.46,0.31758,0.24923,0.82758,0.99888,0.97872,0.9795,0.95798,0.25853,0.22807,0.77924,0.0001784,0.0001784,0.0001784
+94,1200.73,0.2941,0.25918,0.82094,0.99888,0.97872,0.9795,0.95798,0.25853,0.22807,0.77924,0.0001586,0.0001586,0.0001586
+95,1213.1,0.31419,0.22755,0.79767,0.99885,0.97872,0.97911,0.95684,0.25964,0.23219,0.77761,0.0001388,0.0001388,0.0001388
+96,1225.2,0.33218,0.27002,0.84346,0.99884,0.97872,0.97918,0.95929,0.2589,0.23171,0.77632,0.000119,0.000119,0.000119
+97,1237.39,0.30554,0.2535,0.77551,0.99884,0.97872,0.97924,0.95676,0.25592,0.23301,0.77527,9.92e-05,9.92e-05,9.92e-05
+98,1249.55,0.26152,0.23051,0.71792,0.99883,0.97872,0.97935,0.957,0.25389,0.23283,0.77503,7.94e-05,7.94e-05,7.94e-05
+99,1262.09,0.28429,0.24512,0.77567,0.99882,0.97872,0.97927,0.95995,0.25514,0.23616,0.77588,5.96e-05,5.96e-05,5.96e-05
+100,1274.2,0.30278,0.25123,0.83641,0.99881,0.97872,0.97921,0.95976,0.25783,0.23404,0.77676,3.98e-05,3.98e-05,3.98e-05

runs/detect/train29/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: C:\workspace\le-yolo\runs\detect\train28\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: train29
+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\train29

runs/detect/train29/results.csv

@@ -0,0 +1,6 @@
+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
+1,10.9915,0.32252,0.30008,0.82477,0.70044,0.61111,0.70693,0.40802,1.4156,1.82764,1.29528,0.00012,0.00012,0.00012
+2,21.3682,0.53183,0.3616,0.91691,0.72802,0.59561,0.70432,0.41349,1.33528,1.92446,1.26227,0.000257426,0.000257426,0.000257426
+3,31.8168,0.42738,0.31044,0.85128,0.82643,0.61111,0.66695,0.40551,1.29937,1.92941,1.24453,0.00039208,0.00039208,0.00039208
+4,42.1957,0.37061,0.29492,0.73008,0.77904,0.61111,0.64413,0.38489,1.31936,1.98984,1.23691,0.000523962,0.000523962,0.000523962
+5,52.9546,0.41831,0.31655,0.84052,0.85674,0.66465,0.68326,0.41733,1.30685,2.14326,1.23156,0.000653072,0.000653072,0.000653072

runs/detect/train30/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: C:\workspace\le-yolo\runs\detect\train28\weights\last.pt
+data: data.yaml
+epochs: 500
+time: null
+patience: 100
+batch: 8
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: cpu
+workers: 8
+project: null
+name: train30
+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\train30

runs/detect/train30/results.csv

@@ -0,0 +1,3 @@
+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
+1,11.1511,0.32252,0.30008,0.82477,0.70044,0.61111,0.70693,0.40802,1.4156,1.82764,1.29528,0.00012,0.00012,0.00012
+2,22.5621,0.53184,0.36156,0.91688,0.72808,0.5958,0.70432,0.41349,1.33491,1.92438,1.2624,0.000259485,0.000259485,0.000259485

src/data.py

@@ -2,5 +2,26 @@ import cv2
 import numpy as np
 import os
 from PIL import Image,ImageEnhance
+from PIL import Image
+import os
 
+# 指定文件夹路径
+folder_path = 'your_folder_path'
+
+# 遍历文件夹中的所有文件
+for filename in os.listdir(folder_path):
+    # 检查文件是否是图片（这里以常见的图片格式为例）
+    if filename.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.gif')):
+        # 打开图片
+        img_path = os.path.join(folder_path, filename)
+        img = Image.open(img_path)
+
+        # 转换为灰度图像
+        gray_img = img.convert('L')
+
+        # 保存灰度图像（可以保存到原文件夹或指定的新文件夹）
+        # 这里以在原文件夹保存为例，文件名不变，只是修改了内容
+        gray_img.save(img_path)
+
+        print(f"已将 {filename} 转换为灰度图像并保存")
 

src/data.yaml

@@ -1,6 +1,6 @@
 path: C:\workspace\le-yolo\data
 train: images/train
-val: images/val
-test: images/test
+val: images/test
+test: images/val
 nc: 1
 names: [ 'person' ]

src/test.py

@@ -1,3 +1,3 @@
 from ultralytics import YOLO
-model = YOLO(r"C:\workspace\le-yolo\runs\detect\train26\weights\best.pt")
-results = model.predict("../res/3.mp4", show=True, save=True)
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train28\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\train26\weights\last.pt")
-model.train(data="data.yaml", epochs=100,  batch=8, device='cpu',  imgsz=640)
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train28\weights\last.pt")
+model.train(data="data.yaml", epochs=500,  batch=8, device='cpu',  imgsz=640)
 model.val()
 print('训练完成')