[CF]提交文件

runs/detect/train42/results.csv

@@ -42,3 +42,60 @@ epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),met
 41,1014.57,0.59949,0.52836,0.90913,0.9976,0.97872,0.97507,0.87453,0.53395,0.60574,0.9754,0.001208,0.001208,0.001208
 42,1037.9,0.60692,0.51077,0.91856,0.99765,0.97872,0.97507,0.86385,0.5848,0.6038,1.0358,0.0011882,0.0011882,0.0011882
 43,1063.52,0.61637,0.54559,0.92315,0.99601,0.97872,0.97507,0.86796,0.57281,0.6059,1.04494,0.0011684,0.0011684,0.0011684
+44,1092.41,0.56682,0.542,0.91691,0.99739,0.97872,0.97507,0.86212,0.56192,0.65041,1.06014,0.0011486,0.0011486,0.0011486
+45,1117.06,0.64198,0.53349,0.96125,0.99455,0.97872,0.97507,0.86674,0.5539,0.69235,1.04594,0.0011288,0.0011288,0.0011288
+46,1141.63,0.60128,0.53201,0.91766,0.97669,0.97872,0.97464,0.87465,0.57068,0.7196,1.03372,0.001109,0.001109,0.001109
+47,1165.33,0.5519,0.58226,0.87766,0.99995,0.97872,0.97507,0.87923,0.57734,0.68746,1.04333,0.0010892,0.0010892,0.0010892
+48,1190.51,0.61955,0.55435,0.92372,0.99828,0.97872,0.97508,0.86899,0.59967,0.62745,1.04996,0.0010694,0.0010694,0.0010694
+49,1215.68,0.57611,0.5068,0.86542,0.99834,0.97872,0.97508,0.90285,0.53186,0.56817,1.04446,0.0010496,0.0010496,0.0010496
+50,1239.24,0.52518,0.46535,0.87764,1,0.97829,0.97508,0.88767,0.54936,0.55594,1.03008,0.0010298,0.0010298,0.0010298
+51,1263.25,0.60835,0.51077,0.90971,0.99781,0.97872,0.97508,0.89059,0.54906,0.57735,1.04816,0.00101,0.00101,0.00101
+52,1287.64,0.57438,0.5124,0.92987,0.97851,0.96899,0.97423,0.88824,0.61444,0.54986,1.07954,0.0009902,0.0009902,0.0009902
+53,1313.16,0.56937,0.48896,0.90152,0.99826,0.95745,0.97466,0.86378,0.60609,0.56536,1.047,0.0009704,0.0009704,0.0009704
+54,1339.05,0.61594,0.51975,0.95916,0.97714,0.97872,0.97423,0.86971,0.60094,0.57078,1.05624,0.0009506,0.0009506,0.0009506
+55,1365.76,0.57515,0.47696,0.89298,0.97705,0.97872,0.97423,0.87785,0.5651,0.58565,1.08914,0.0009308,0.0009308,0.0009308
+56,1389.14,0.5068,0.45113,0.88907,0.97696,0.97872,0.97467,0.87046,0.58345,0.57728,1.12494,0.000911,0.000911,0.000911
+57,1413.27,0.53803,0.45492,0.90522,0.97722,0.97872,0.97425,0.88975,0.49741,0.5502,1.03528,0.0008912,0.0008912,0.0008912
+58,1441.19,0.608,0.4931,0.93643,0.97735,0.97872,0.97426,0.8931,0.50678,0.55762,0.99923,0.0008714,0.0008714,0.0008714
+59,1468.55,0.54444,0.46445,0.95757,0.99848,0.97872,0.97512,0.89931,0.50644,0.53365,0.98802,0.0008516,0.0008516,0.0008516
+60,1493.47,0.5672,0.47496,0.90847,0.99857,0.97872,0.97514,0.89933,0.48361,0.49757,0.94558,0.0008318,0.0008318,0.0008318
+61,1519.16,0.56814,0.49767,0.89276,0.99854,0.97872,0.97515,0.8908,0.45367,0.44977,0.92588,0.000812,0.000812,0.000812
+62,1545.68,0.54123,0.46468,0.92992,0.99867,0.97872,0.97514,0.89709,0.44947,0.45708,0.93801,0.0007922,0.0007922,0.0007922
+63,1571.74,0.57246,0.46686,0.90762,0.99786,0.97872,0.97513,0.89482,0.46021,0.47385,0.94823,0.0007724,0.0007724,0.0007724
+64,1597.8,0.54624,0.43858,0.87308,0.99844,0.97872,0.97516,0.89729,0.49468,0.46887,0.96013,0.0007526,0.0007526,0.0007526
+65,1623.68,0.54364,0.44246,0.88962,0.99855,0.97872,0.97517,0.90365,0.51956,0.42429,0.95753,0.0007328,0.0007328,0.0007328
+66,1649.18,0.46981,0.40913,0.87546,0.99847,0.97872,0.9752,0.90499,0.43039,0.40576,0.90702,0.000713,0.000713,0.000713
+67,1673.24,0.52479,0.41543,0.86585,0.99841,0.97872,0.97522,0.89389,0.40141,0.42377,0.91541,0.0006932,0.0006932,0.0006932
+68,1697.64,0.5616,0.43932,0.90982,0.99837,0.97872,0.97529,0.89919,0.49413,0.43951,0.98202,0.0006734,0.0006734,0.0006734
+69,1723.64,0.52312,0.44072,0.90402,0.99831,0.97872,0.97536,0.89659,0.53139,0.44096,0.98169,0.0006536,0.0006536,0.0006536
+70,1749.65,0.50496,0.41511,0.90988,0.99819,0.97872,0.97539,0.91645,0.45378,0.42096,0.92256,0.0006338,0.0006338,0.0006338
+71,1777.56,0.51147,0.42693,0.86444,0.99821,0.97872,0.9754,0.92046,0.41803,0.38434,0.90736,0.000614,0.000614,0.000614
+72,1806.81,0.50723,0.44087,0.88909,0.99845,0.97872,0.97545,0.9141,0.41854,0.38573,0.90434,0.0005942,0.0005942,0.0005942
+73,1835.6,0.48878,0.42097,0.89505,0.99844,0.97872,0.97552,0.92009,0.40796,0.39896,0.89601,0.0005744,0.0005744,0.0005744
+74,1861.75,0.52419,0.4239,0.8862,0.99859,0.97872,0.9756,0.92316,0.40554,0.41532,0.88737,0.0005546,0.0005546,0.0005546
+75,1888.59,0.47155,0.38701,0.87038,0.99862,0.97872,0.9757,0.92891,0.38805,0.41992,0.8783,0.0005348,0.0005348,0.0005348
+76,1915.19,0.48355,0.39834,0.86732,0.99865,0.97872,0.97579,0.93202,0.37531,0.41166,0.86651,0.000515,0.000515,0.000515
+77,1941.02,0.52022,0.39644,0.90819,0.99874,0.97872,0.97588,0.93108,0.38676,0.42775,0.86735,0.0004952,0.0004952,0.0004952
+78,1967.17,0.49991,0.39252,0.87213,0.99874,0.97872,0.97597,0.92747,0.39723,0.40431,0.87254,0.0004754,0.0004754,0.0004754
+79,1993.36,0.46994,0.38264,0.87372,0.99871,0.97872,0.97598,0.94087,0.39048,0.38877,0.87239,0.0004556,0.0004556,0.0004556
+80,2019.46,0.44306,0.34784,0.85531,0.99874,0.97872,0.97598,0.94111,0.37653,0.37271,0.85693,0.0004358,0.0004358,0.0004358
+81,2045.91,0.52164,0.44215,0.90042,0.99874,0.97872,0.97605,0.93703,0.35099,0.35613,0.84375,0.000416,0.000416,0.000416
+82,2071.09,0.43583,0.36948,0.86455,0.99875,0.97872,0.97614,0.93687,0.33748,0.34432,0.83893,0.0003962,0.0003962,0.0003962
+83,2096.03,0.44289,0.36518,0.85191,0.99875,0.97872,0.97624,0.93707,0.3427,0.34866,0.84353,0.0003764,0.0003764,0.0003764
+84,2122.84,0.47123,0.37938,0.86435,0.99877,0.97872,0.97633,0.93289,0.36886,0.34391,0.86271,0.0003566,0.0003566,0.0003566
+85,2146.21,0.46956,0.37655,0.89478,0.99877,0.97872,0.97641,0.93346,0.35497,0.34737,0.85675,0.0003368,0.0003368,0.0003368
+86,2169.49,0.44497,0.38846,0.79774,0.99875,0.97872,0.97663,0.93787,0.35528,0.32827,0.84843,0.000317,0.000317,0.000317
+87,2192.97,0.42009,0.36714,0.84973,0.99875,0.97872,0.97668,0.94681,0.37703,0.32198,0.8541,0.0002972,0.0002972,0.0002972
+88,2218.43,0.43938,0.36407,0.83415,0.99876,0.97872,0.97678,0.94578,0.40722,0.32622,0.86835,0.0002774,0.0002774,0.0002774
+89,2241.97,0.42528,0.43108,0.82208,0.99881,0.97872,0.9769,0.94796,0.44235,0.33782,0.88634,0.0002576,0.0002576,0.0002576
+90,2265.32,0.47437,0.3832,0.88705,0.99884,0.97872,0.97706,0.94442,0.42207,0.32059,0.87479,0.0002378,0.0002378,0.0002378
+91,2289.85,0.37181,0.34761,0.84103,0.99886,0.97872,0.97701,0.94757,0.41277,0.32924,0.86992,0.000218,0.000218,0.000218
+92,2312.97,0.34648,0.34359,0.826,0.99884,0.97872,0.97732,0.94171,0.39116,0.32631,0.86015,0.0001982,0.0001982,0.0001982
+93,2335.99,0.36605,0.34218,0.84288,0.9988,0.97872,0.97724,0.94082,0.37981,0.3187,0.8523,0.0001784,0.0001784,0.0001784
+94,2359.71,0.38169,0.33456,0.84097,0.99881,0.97872,0.97728,0.94485,0.36443,0.33128,0.84394,0.0001586,0.0001586,0.0001586
+95,2383.48,0.37646,0.35094,0.83187,0.99881,0.97872,0.97726,0.94287,0.36169,0.32773,0.84267,0.0001388,0.0001388,0.0001388
+96,2407.26,0.36623,0.33836,0.84097,0.99879,0.97872,0.97731,0.94201,0.34619,0.32886,0.83634,0.000119,0.000119,0.000119
+97,2430.66,0.35889,0.34208,0.81934,0.99882,0.97872,0.97718,0.94312,0.32836,0.3326,0.83218,9.92e-05,9.92e-05,9.92e-05
+98,2454.19,0.34079,0.32036,0.79553,0.99882,0.97872,0.97726,0.94541,0.3094,0.33484,0.83082,7.94e-05,7.94e-05,7.94e-05
+99,2478.3,0.34663,0.32585,0.82711,0.99884,0.97872,0.9772,0.94542,0.30885,0.32567,0.82688,5.96e-05,5.96e-05,5.96e-05
+100,2502.43,0.34408,0.31704,0.82257,0.99883,0.97872,0.97737,0.94894,0.30604,0.32063,0.82739,3.98e-05,3.98e-05,3.98e-05

runs/detect/train43/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: yolov8n.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: train43
+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\train43

runs/detect/train43/results.csv

@@ -0,0 +1,10 @@
+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
+1,24.3756,1.21014,3.1702,1.19727,0.00313,0.97872,0.79623,0.64322,0.52877,3.00181,0.80078,0.00026,0.00026,0.00026
+2,48.2621,0.81396,2.37685,0.8738,0.00313,0.97872,0.91786,0.75913,0.59196,2.94612,0.82206,0.000534654,0.000534654,0.000534654
+3,73.8232,0.90479,1.60795,0.97833,1,0.22824,0.93879,0.66689,0.75898,2.86271,0.91755,0.000803764,0.000803764,0.000803764
+4,97.3313,0.8895,1.99802,0.91206,0.93431,0.30285,0.74521,0.55539,1.24471,3.01773,1.14351,0.00106733,0.00106733,0.00106733
+5,120.563,1.04688,1.71324,1.04767,1,0.24535,0.84327,0.51189,1.29624,2.99114,1.2371,0.00132535,0.00132535,0.00132535
+6,144.566,1.01511,1.47643,1.01558,0.58375,0.55319,0.61104,0.35898,1.30424,2.7948,1.37665,0.00157783,0.00157783,0.00157783
+7,167.911,0.9864,1.49348,1.04347,0.44618,0.4972,0.5101,0.32791,1.17259,2.53619,1.17558,0.00182476,0.00182476,0.00182476
+8,191.533,0.95161,1.72087,0.96641,0.35612,0.3617,0.35199,0.21519,1.13552,2.86189,1.32933,0.0018614,0.0018614,0.0018614
+9,214.965,0.88668,1.27559,1.01199,0.94045,0.85106,0.92187,0.71277,0.93981,2.32268,1.10274,0.0018416,0.0018416,0.0018416

src/data.yaml

@@ -3,7 +3,7 @@ train: images/train
 val: images/val
 test: images/test
 nc: 1
-names: [ 'person' ]
+names: [ 'aaa' ]
 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

src/test.py

@@ -1,3 +1,3 @@
 from ultralytics import YOLO
-model = YOLO(r"C:\workspace\le-yolo\runs\detect\train41\weights\best.pt")
+model = YOLO(r"C:\workspace\le-yolo\runs\detect\train42\weights\best.pt")
 results = model.predict("../res/5.mp4", show=True, save=True)