[CF]提交文件

data/labels/test/1.txt

@@ -1 +0,0 @@
-0 0.1207 0.0900 0.0383 0.0785

data/labels/test/124bc07e-test_170.txt

@@ -0,0 +1 @@
+0 0.4882260596546311 0.7479504622361764 0.14285714285714285 0.1004709576138147

data/labels/test/2.txt

@@ -1 +0,0 @@
-0 0.1318 0.0900 0.0402 0.0949

data/labels/test/2c3a0daf-test_120.txt

@@ -0,0 +1 @@
+0 0.5003924646781784 0.4311878597592883 0.06514913657770793 0.2735042735042734

data/labels/test/3.txt

@@ -1 +0,0 @@
-0 0.1199 0.1080 0.0391 0.0738

data/labels/test/3ab9529c-test_150.txt

@@ -0,0 +1 @@
+0 0.4116954474097331 0.8044653758939466 0.12637362637362626 0.23024594453165872

data/labels/test/3dc0398b-test_180.txt

@@ -0,0 +1 @@
+0 0.43995290423861855 0.6000348857491713 0.13579277864992148 0.09768009768009758

data/labels/test/4.txt

@@ -1 +0,0 @@
-0 0.1139 0.1191 0.0402 0.0719

data/labels/test/4d8c6c92-test_60.txt

@@ -0,0 +1 @@
+0 0.5443485086342228 0.3014128728414442 0.07299843014128736 0.21768707482993196

data/labels/test/5.txt

@@ -1 +0,0 @@
-0 0.1334 0.0975 0.0332 0.0785

data/labels/test/53996c6c-test_200.txt

@@ -0,0 +1 @@
+0 0.41169544740973324 0.6453863596720733 0.13579277864992156 0.08791208791208784

data/labels/test/5bb06d35-test_190.txt

@@ -0,0 +1 @@
+0 0.422684458398744 0.6265480551194839 0.12951334379905818 0.09488923774638067

data/labels/test/62b7a876-test_40.txt

@@ -0,0 +1 @@
+0 0.37872841444270017 0.4172335600907029 0.11695447409733126 0.17024245595674156

data/labels/test/98fae6f6-test_100.txt

@@ -0,0 +1 @@
+0 0.6346153846153847 0.48979591836734654 0.05416012558869712 0.22605965463108302

data/labels/test/a7054cac-test_30.txt

@@ -0,0 +1 @@
+0 0.23547880690737835 0.5965463108320251 0.14913657770800626 0.1576835862550147

data/labels/test/b187ff7e-test_20.txt

@@ -0,0 +1 @@
+0 0.0726059654631083 0.928658642944357 0.1452119309262166 0.14093842665271233

data/labels/test/b99ddce0-test_130.txt

@@ -0,0 +1 @@
+0 0.4717425431711144 0.46607360893075167 0.07378335949764533 0.29024943310657597

data/labels/test/bb15ed26-test_110.txt

@@ -0,0 +1 @@
+0 0.5588697017268442 0.4590964590964591 0.05808477237048668 0.25396825396825395

data/labels/test/c2aa44cb-test_80.txt

@@ -0,0 +1 @@
+0 0.694662480376766 0.47235304378161513 0.053375196232339155 0.21908250479679048

data/labels/test/c7774575-test_50.txt

@@ -0,0 +1 @@
+0 0.46193092621664067 0.3460666317809176 0.0996860282574569 0.2037327751613468

data/labels/test/d6032bbd-test_70.txt

@@ -0,0 +1 @@
+0 0.6322605965463111 0.3425780568637712 0.07142857142857152 0.22466422466422475

data/labels/test/f8621c43-test_90.txt

@@ -0,0 +1 @@
+0 0.6954474097331239 0.47584161869876185 0.054945054945055215 0.22047793476364924

data/labels/test/ff93d629-test_140.txt

@@ -0,0 +1 @@
+0 0.4273940345368919 0.5260770975056684 0.08241758241758251 0.2930402930402928

runs/detect/train27/args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: C:\workspace\le-yolo\runs\detect\train26\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: train27
+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\train27

runs/detect/train27/results.csv

@@ -0,0 +1,55 @@
+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
+1,13.2669,0.43505,0.52308,0.85326,0.99849,0.97872,0.97506,0.93382,0.32359,0.49773,0.82428,0.00012,0.00012,0.00012
+2,25.801,0.44361,0.44178,0.83589,0.99845,0.97872,0.97506,0.91588,0.33912,0.51548,0.82003,0.000257426,0.000257426,0.000257426
+3,38.2037,0.54109,0.54769,0.9778,0.99827,0.97872,0.97506,0.89371,0.43446,0.53809,0.84371,0.00039208,0.00039208,0.00039208
+4,50.6353,0.66496,0.62828,1.11706,0.99852,0.97872,0.97506,0.9123,0.49509,0.55576,0.89711,0.000523962,0.000523962,0.000523962
+5,62.9126,0.56829,0.64357,0.89467,0.99874,0.97872,0.97506,0.90961,0.45408,0.5561,0.86885,0.000653072,0.000653072,0.000653072
+6,75.3132,0.58491,0.51649,0.87618,0.99878,0.97872,0.97506,0.88318,0.46088,0.62726,0.88711,0.00077941,0.00077941,0.00077941
+7,87.5407,0.54232,0.56334,0.88114,0.99823,0.97872,0.97506,0.86175,0.50212,0.73162,0.90725,0.000902976,0.000902976,0.000902976
+8,100.37,0.61618,0.53237,0.91974,0.99832,0.97872,0.97506,0.85986,0.53545,0.67665,0.93735,0.00102377,0.00102377,0.00102377
+9,112.624,0.5297,0.56286,0.87843,0.99853,0.97872,0.97506,0.87947,0.4903,0.66042,0.93648,0.00114179,0.00114179,0.00114179
+10,124.773,0.62524,0.54455,0.92483,0.99867,0.97872,0.97507,0.86054,0.56829,0.74766,0.97461,0.00125704,0.00125704,0.00125704
+11,137.571,0.65024,0.59284,0.97454,0.99888,0.97872,0.97507,0.85093,0.68737,0.69032,1.09134,0.00136952,0.00136952,0.00136952
+12,150.197,0.62675,0.65343,0.9614,0.99889,0.97872,0.97506,0.85546,0.72943,0.60515,1.11956,0.00147923,0.00147923,0.00147923
+13,162.537,0.56475,0.55125,0.87224,1,0.978,0.97506,0.87919,0.69957,0.56837,1.11947,0.00158616,0.00158616,0.00158616
+14,174.894,0.77236,0.83568,1.16568,1,0.978,0.97506,0.87919,0.69957,0.56837,1.11947,0.00169032,0.00169032,0.00169032
+15,187.211,0.56209,0.59946,0.899,0.99841,0.97872,0.97506,0.85699,0.67707,0.66874,1.05578,0.0017228,0.0017228,0.0017228
+16,199.453,0.50614,0.53907,0.87553,0.99808,0.97872,0.97506,0.84961,0.64327,0.70656,1.03661,0.001703,0.001703,0.001703
+17,211.741,0.58702,0.56443,0.8686,0.9984,0.97872,0.97506,0.86594,0.60795,0.77716,1.0314,0.0016832,0.0016832,0.0016832
+18,223.96,0.58811,0.60501,0.90207,0.99745,0.97872,0.97505,0.86917,0.54344,0.64444,0.96213,0.0016634,0.0016634,0.0016634
+19,236.219,0.61329,0.61213,0.93239,0.99824,0.97872,0.97505,0.87104,0.52549,0.56599,0.95366,0.0016436,0.0016436,0.0016436
+20,248.369,0.52961,0.53808,0.89246,0.99847,0.97872,0.97505,0.87598,0.52387,0.60491,0.95481,0.0016238,0.0016238,0.0016238
+21,260.634,0.55004,0.52542,0.87965,0.99859,0.97872,0.97507,0.87612,0.57552,0.66396,0.98333,0.001604,0.001604,0.001604
+22,272.873,0.58561,0.57592,0.91036,0.99859,0.97872,0.97507,0.87612,0.57552,0.66396,0.98333,0.0015842,0.0015842,0.0015842
+23,285.818,0.58799,0.54979,0.91666,0.99791,0.97872,0.97508,0.86002,0.5587,0.55277,0.94725,0.0015644,0.0015644,0.0015644
+24,298.786,0.61911,0.58429,0.91879,0.99802,0.97872,0.97508,0.8901,0.53012,0.51898,0.92542,0.0015446,0.0015446,0.0015446
+25,311.624,0.60795,0.54674,0.91007,0.99851,0.97872,0.97507,0.8884,0.46811,0.51122,0.91218,0.0015248,0.0015248,0.0015248
+26,323.861,0.56332,0.51842,0.91495,0.99858,0.97872,0.97507,0.88758,0.46055,0.50076,0.90961,0.001505,0.001505,0.001505
+27,336.11,0.61107,0.52477,0.9489,0.99852,0.97872,0.97508,0.88447,0.47659,0.52007,0.91791,0.0014852,0.0014852,0.0014852
+28,348.524,0.52445,0.52597,0.90869,0.99858,0.97872,0.97514,0.89268,0.48783,0.55657,0.92846,0.0014654,0.0014654,0.0014654
+29,360.714,0.73941,0.58597,1.14612,0.99856,0.97872,0.97528,0.89396,0.48926,0.48598,0.92929,0.0014456,0.0014456,0.0014456
+30,372.862,0.60665,0.53148,0.93829,0.99856,0.97872,0.97528,0.89396,0.48926,0.48598,0.92929,0.0014258,0.0014258,0.0014258
+31,385.004,0.54175,0.48149,0.88547,0.99754,0.97872,0.97534,0.88658,0.50492,0.47431,0.91589,0.001406,0.001406,0.001406
+32,397.24,0.53223,0.49272,0.90144,0.99757,0.97872,0.97543,0.87522,0.54734,0.46049,0.91889,0.0013862,0.0013862,0.0013862
+33,409.6,0.70963,0.58144,1.14893,0.99828,0.97872,0.97557,0.88292,0.51553,0.46331,0.91194,0.0013664,0.0013664,0.0013664
+34,421.872,0.53274,0.47675,0.87241,0.99819,0.97872,0.97594,0.90528,0.48265,0.42793,0.90231,0.0013466,0.0013466,0.0013466
+35,434.196,0.59791,0.49046,0.96181,0.99761,0.97872,0.97619,0.89282,0.47287,0.40913,0.89088,0.0013268,0.0013268,0.0013268
+36,446.277,0.49349,0.46565,0.88213,0.99807,0.97872,0.97637,0.91052,0.41674,0.41462,0.86097,0.001307,0.001307,0.001307
+37,458.421,0.50546,0.43836,0.82587,0.99829,0.97872,0.97639,0.88898,0.3967,0.42826,0.846,0.0012872,0.0012872,0.0012872
+38,470.524,0.50224,0.45655,0.88193,0.99829,0.97872,0.97639,0.88898,0.3967,0.42826,0.846,0.0012674,0.0012674,0.0012674
+39,482.788,0.47235,0.43442,0.83027,0.99846,0.97872,0.97612,0.89299,0.41034,0.46326,0.84896,0.0012476,0.0012476,0.0012476
+40,495.008,0.50886,0.45206,0.84377,0.99848,0.97872,0.9759,0.89828,0.40364,0.4753,0.85201,0.0012278,0.0012278,0.0012278
+41,507.313,0.48108,0.45373,0.94433,0.99782,0.97872,0.97588,0.91397,0.37663,0.5078,0.8438,0.001208,0.001208,0.001208
+42,519.715,0.5304,0.452,0.9249,0.99705,0.97872,0.97637,0.90622,0.38823,0.49181,0.84588,0.0011882,0.0011882,0.0011882
+43,532.013,0.53656,0.45268,0.86089,0.99575,0.97872,0.97699,0.89407,0.45639,0.45184,0.87829,0.0011684,0.0011684,0.0011684
+44,544.298,0.48039,0.44775,0.93198,0.99826,0.97872,0.97769,0.91188,0.45124,0.43533,0.88286,0.0011486,0.0011486,0.0011486
+45,556.611,0.46206,0.41506,0.84067,0.99808,0.97872,0.97787,0.90369,0.46115,0.44531,0.8902,0.0011288,0.0011288,0.0011288
+46,569.012,0.68981,0.61293,1.02449,0.99808,0.97872,0.97787,0.90369,0.46115,0.44531,0.8902,0.001109,0.001109,0.001109
+47,581.251,0.57723,0.46172,0.90314,0.9978,0.97872,0.97731,0.88975,0.48675,0.44816,0.89428,0.0010892,0.0010892,0.0010892
+48,593.483,0.47651,0.44804,0.85403,0.9968,0.97872,0.97655,0.90049,0.47049,0.4396,0.89356,0.0010694,0.0010694,0.0010694
+49,605.65,0.54616,0.49061,0.92223,0.99662,0.97872,0.97605,0.89475,0.48763,0.43542,0.89251,0.0010496,0.0010496,0.0010496
+50,617.853,0.52231,0.45301,0.92897,0.99079,0.97872,0.97586,0.90253,0.48184,0.47301,0.88831,0.0010298,0.0010298,0.0010298
+51,630.223,0.52221,0.44779,0.88502,0.9916,0.97872,0.97581,0.91319,0.48998,0.43281,0.89684,0.00101,0.00101,0.00101
+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

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/5.mp4", show=True, save=True)
+results = model.predict("../res/3.mp4", show=True, save=True)

src/train.py

@@ -1,5 +1,5 @@
 from ultralytics import YOLO
-model = YOLO("yolov8n.pt")
+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.val()
 print('训练完成')

src/video.py

@@ -1,13 +1,13 @@
 import cv2
-videopath = 'C:/workspace/le-yolo/res/2.mp4'
+videopath = 'C:/workspace/le-yolo/res/3.mp4'
 video = cv2.VideoCapture(videopath)
 num = 0
 if video.isOpened():
     ret, frame = video.read()
 else:
     ret = False
-timeF = 8
-filepath = 'C:/workspace/le-yolo/data/images/train/t2_'
+timeF = 10
+filepath = 'C:/workspace/le-yolo/data/images/test/test_'
 while ret:
     ret, frame = video.read()
     if num % timeF == 0: