second

backend/runs/detect/train2/args.yaml

@@ -0,0 +1,109 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: ../datasets/road_signs_potholes/data.yaml
+epochs: 100
+time: null
+patience: 100
+batch: 16
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: cpu
+workers: 8
+project: null
+name: train2
+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: 0.0
+compile: 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
+end2end: null
+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
+rle: 1.0
+angle: 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: D:\Time-Pass-Projects\pothole-roadsign detection\backend\runs\detect\train2

backend/runs/detect/train3/args.yaml

@@ -0,0 +1,109 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: ../datasets/road_signs_potholes/data.yaml
+epochs: 100
+time: null
+patience: 100
+batch: 16
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: cpu
+workers: 8
+project: null
+name: train3
+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: 0.0
+compile: 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
+end2end: null
+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
+rle: 1.0
+angle: 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: D:\Time-Pass-Projects\pothole-roadsign detection\backend\runs\detect\train3

backend/runs/detect/train3/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
+1,2.40825,0.73927,3.11895,1.35202,0.01111,1,0.995,0.49941,1.48202,4.20092,2.65216,0,0,0
+2,4.8459,1.0476,3.3315,1.49622,0.01163,1,0.995,0.49949,1.43612,4.11708,2.60245,1.41485e-05,1.41485e-05,1.41485e-05
+3,7.56628,1.17518,3.19824,1.6378,0.0119,1,0.995,0.50579,1.36621,3.86984,2.5728,2.80141e-05,2.80141e-05,2.80141e-05
+4,11.7009,0.9701,3.29791,1.48036,0.01282,1,0.995,0.50994,1.25408,3.82529,2.57307,4.15968e-05,4.15968e-05,4.15968e-05
+5,14.9546,1.12225,3.25296,1.4848,0.01351,1,0.995,0.51171,1.03111,3.83363,2.56252,5.48965e-05,5.48965e-05,5.48965e-05
+6,17.9671,1.07953,3.10394,1.38546,0.01493,1,0.995,0.46433,1.02984,3.78998,2.63548,6.79132e-05,6.79132e-05,6.79132e-05
+7,20.917,0.98022,3.21253,1.33149,0.01562,1,0.995,0.54725,1.29799,3.89647,2.71359,8.0647e-05,8.0647e-05,8.0647e-05
+8,23.766,0.77437,2.78499,1.13387,0.01639,1,0.995,0.4975,1.1368,3.93033,2.61587,9.30979e-05,9.30979e-05,9.30979e-05
+9,26.9445,0.65576,2.69662,1.23904,0.01754,1,0.995,0.50579,1.30955,3.90774,2.69206,0.000105266,0.000105266,0.000105266
+10,29.8781,0.94802,2.67232,1.45246,0.01724,1,0.995,0.53067,1.36919,3.9226,2.93452,0.000117151,0.000117151,0.000117151
+11,32.8687,1.1376,2.73242,1.51246,0.01754,1,0.995,0.53067,1.26248,3.98887,3.0594,0.000128753,0.000128753,0.000128753
+12,35.7936,0.79428,2.3616,1.35153,0.02083,1,0.995,0.52593,1.15438,3.7328,3.75969,0.000140072,0.000140072,0.000140072
+13,38.7035,0.8048,2.32927,1.36265,0.02222,1,0.995,0.51171,1.07116,3.9262,3.56081,0.000151108,0.000151108,0.000151108
+14,41.5594,0.78035,2.09505,1.3535,0.02273,1,0.995,0.61911,1.28842,3.61172,3.27563,0.000161861,0.000161861,0.000161861
+15,44.4063,1.07043,2.12428,1.5162,0.02703,1,0.995,0.597,1.28061,3.58597,3.51845,0.000172332,0.000172332,0.000172332
+16,47.2556,0.92144,2.41709,1.2214,0.0303,1,0.995,0.597,1.34893,3.53204,3.50919,0.000182519,0.000182519,0.000182519
+17,50.0894,0.85151,1.98171,1.25107,0.0303,1,0.995,0.4975,1.20894,3.81426,3.7206,0.000192423,0.000192423,0.000192423
+18,52.8422,0.91481,2.21603,1.3634,0.0303,1,0.995,0.4975,1.20894,3.81426,3.7206,0.000202045,0.000202045,0.000202045
+19,55.6524,0.53186,1.97527,1.21071,0.03448,1,0.995,0.4975,1.16651,3.64236,3.62395,0.000211383,0.000211383,0.000211383
+20,58.4175,0.79056,1.70233,1.25893,0.03448,1,0.995,0.4975,1.16651,3.64236,3.62395,0.000220439,0.000220439,0.000220439
+21,61.1627,0.82181,2.0993,1.22513,0.03846,1,0.995,0.597,1.20689,3.43879,3.52638,0.000229212,0.000229212,0.000229212
+22,63.9656,0.65083,1.79582,1.1327,0.03846,1,0.995,0.597,1.20689,3.43879,3.52638,0.000237701,0.000237701,0.000237701
+23,66.7835,0.79614,1.89284,1.21315,0.03704,1,0.995,0.597,1.13331,3.43178,3.41124,0.000245908,0.000245908,0.000245908
+24,69.4754,0.74576,1.8944,1.21804,0.03704,1,0.995,0.597,1.13331,3.43178,3.41124,0.000253832,0.000253832,0.000253832
+25,72.3755,0.75619,1.81981,1.18747,0.04,1,0.995,0.597,1.04747,3.53722,3.08048,0.000261473,0.000261473,0.000261473
+26,75.2205,0.65729,1.59464,1.056,0.04,1,0.995,0.597,1.04747,3.53722,3.08048,0.000268831,0.000268831,0.000268831
+27,78.0384,0.7731,1.64118,1.35636,0.04167,1,0.995,0.597,1.00146,3.49249,2.81578,0.000275906,0.000275906,0.000275906
+28,80.7678,0.5182,1.47057,1.07106,0.04167,1,0.995,0.597,1.00146,3.49249,2.81578,0.000282698,0.000282698,0.000282698
+29,83.5794,0.61264,1.47068,1.12602,0.04545,1,0.995,0.6965,1.07116,3.27642,2.84232,0.000289207,0.000289207,0.000289207
+30,86.3482,0.63132,1.41729,1.07439,0.04545,1,0.995,0.6965,1.07116,3.27642,2.84232,0.000295433,0.000295433,0.000295433
+31,89.271,0.51512,1.38363,1.06875,0.04545,1,0.995,0.6965,1.10749,3.18763,2.68268,0.000301376,0.000301376,0.000301376
+32,92.0282,0.63916,1.27028,1.01609,0.04545,1,0.995,0.6965,1.10749,3.18763,2.68268,0.000307036,0.000307036,0.000307036
+33,94.765,0.85211,1.5878,1.10095,0.03704,1,0.995,0.6965,0.98478,3.15129,2.46901,0.000312414,0.000312414,0.000312414
+34,97.3487,0.51161,1.26976,1.07672,0.03704,1,0.995,0.6965,0.98478,3.15129,2.46901,0.000317508,0.000317508,0.000317508
+35,100.117,0.68592,1.86174,1.37262,0.03125,1,0.995,0.8955,0.93017,3.33924,2.33786,0.00032232,0.00032232,0.00032232
+36,102.907,0.69044,1.15139,1.11441,0.03125,1,0.995,0.8955,0.93017,3.33924,2.33786,0.000326848,0.000326848,0.000326848
+37,105.746,0.70236,1.72026,1.30143,0.03125,1,0.995,0.597,1.06368,3.36034,2.33155,0.000331094,0.000331094,0.000331094
+38,108.594,0.60369,1.20454,1.09724,0.03125,1,0.995,0.597,1.06368,3.36034,2.33155,0.000335056,0.000335056,0.000335056
+39,111.379,0.64458,1.09739,1.1314,0.02941,1,0.995,0.54725,1.04599,3.06585,2.37147,0.000338736,0.000338736,0.000338736
+40,114.147,0.58768,1.12047,1.08237,0.02941,1,0.995,0.54725,1.04599,3.06585,2.37147,0.000342133,0.000342133,0.000342133
+41,116.913,0.5523,1.28911,1.13936,0.76583,1,0.995,0.796,1.10066,2.58649,2.70288,0.000345246,0.000345246,0.000345246
+42,119.772,0.5748,1.12242,1.02836,0.76583,1,0.995,0.796,1.10066,2.58649,2.70288,0.000348077,0.000348077,0.000348077
+43,122.695,0.7034,1.49684,1.14269,0.93644,1,0.995,0.6965,1.17368,2.15814,2.89972,0.000350625,0.000350625,0.000350625
+44,125.508,0.64648,1.36938,1.08111,0.93644,1,0.995,0.6965,1.17368,2.15814,2.89972,0.00035289,0.00035289,0.00035289
+45,128.337,0.62663,1.20569,1.2217,0.95823,1,0.995,0.6965,1.27535,1.91939,3.08072,0.000354872,0.000354872,0.000354872
+46,131.102,0.57044,1.08864,1.03903,0.95823,1,0.995,0.6965,1.27535,1.91939,3.08072,0.000356571,0.000356571,0.000356571
+47,133.913,0.67371,1.21296,1.20454,0.96389,1,0.995,0.597,1.41449,1.82113,3.38192,0.000357987,0.000357987,0.000357987
+48,136.812,0.79162,1.31347,1.19651,0.96389,1,0.995,0.597,1.41449,1.82113,3.38192,0.000359121,0.000359121,0.000359121
+49,139.665,0.71485,1.33562,1.15952,0.96013,1,0.995,0.6965,1.21785,1.91745,3.03331,0.000359971,0.000359971,0.000359971
+50,142.22,0.77781,1.22762,1.07146,0.96013,1,0.995,0.6965,1.21785,1.91745,3.03331,0.000360538,0.000360538,0.000360538
+51,144.815,0.49387,1.16593,0.95972,0.95714,1,0.995,0.796,1.20779,2.26205,2.94029,0.000360822,0.000360822,0.000360822
+52,147.442,0.66571,1.47333,1.25323,0.95714,1,0.995,0.796,1.20779,2.26205,2.94029,0.000360824,0.000360824,0.000360824
+53,150.221,0.60411,1.16925,1.13773,0.95714,1,0.995,0.796,1.20779,2.26205,2.94029,0.000360542,0.000360542,0.000360542
+54,152.835,0.62281,1.20099,1.18351,0.94099,1,0.995,0.597,1.68171,2.27161,3.82805,0.000359978,0.000359978,0.000359978
+55,155.422,0.5557,1.17525,1.09804,0.94099,1,0.995,0.597,1.68171,2.27161,3.82805,0.000359131,0.000359131,0.000359131
+56,157.969,0.79564,1.51918,1.22704,0.94099,1,0.995,0.597,1.68171,2.27161,3.82805,0.000358,0.000358,0.000358
+57,160.59,0.58401,1.23112,1.09424,0.92175,1,0.995,0.40297,1.66282,2.46605,4.47709,0.000356587,0.000356587,0.000356587
+58,163.165,0.62411,1.13522,1.07946,0.92175,1,0.995,0.40297,1.66282,2.46605,4.47709,0.000354891,0.000354891,0.000354891
+59,165.794,0.63636,1.27518,1.14449,0.92175,1,0.995,0.40297,1.66282,2.46605,4.47709,0.000352912,0.000352912,0.000352912
+60,168.673,0.57301,1.15036,1.0193,0.91093,1,0.995,0.43117,1.56498,2.60744,4.47424,0.000350649,0.000350649,0.000350649
+61,171.371,0.65111,1.08347,1.21705,0.91093,1,0.995,0.43117,1.56498,2.60744,4.47424,0.000348104,0.000348104,0.000348104
+62,173.962,0.53155,0.96714,1.08217,0.91093,1,0.995,0.43117,1.56498,2.60744,4.47424,0.000345276,0.000345276,0.000345276
+63,176.565,0.5191,1.04895,1.08566,0.8943,1,0.995,0.5174,1.5863,2.48285,4.46662,0.000342165,0.000342165,0.000342165
+64,179.109,0.49147,0.98739,0.89501,0.8943,1,0.995,0.5174,1.5863,2.48285,4.46662,0.000338772,0.000338772,0.000338772
+65,181.646,0.59401,1.33664,1.11106,0.8943,1,0.995,0.5174,1.5863,2.48285,4.46662,0.000335095,0.000335095,0.000335095
+66,184.373,0.56993,1.01127,1.17296,0.89888,1,0.995,0.597,1.52682,2.44909,3.77196,0.000331135,0.000331135,0.000331135
+67,186.946,0.46862,1.07981,0.97948,0.89888,1,0.995,0.597,1.52682,2.44909,3.77196,0.000326892,0.000326892,0.000326892
+68,189.759,0.59038,1.87797,1.0484,0.89888,1,0.995,0.597,1.52682,2.44909,3.77196,0.000322367,0.000322367,0.000322367
+69,192.825,0.42615,0.87706,0.92668,0.89298,1,0.995,0.6965,1.10137,2.46605,2.52715,0.000317558,0.000317558,0.000317558
+70,195.676,0.78558,1.29921,1.34063,0.89298,1,0.995,0.6965,1.10137,2.46605,2.52715,0.000312467,0.000312467,0.000312467
+71,198.611,0.40177,0.90407,1.0263,0.89298,1,0.995,0.6965,1.10137,2.46605,2.52715,0.000307092,0.000307092,0.000307092
+72,201.438,0.44381,0.94243,0.96031,0.91712,1,0.995,0.4975,1.46309,2.36933,2.85069,0.000301435,0.000301435,0.000301435
+73,204.18,0.54444,1.05811,1.11158,0.91712,1,0.995,0.4975,1.46309,2.36933,2.85069,0.000295494,0.000295494,0.000295494
+74,206.933,0.63948,1.18863,1.04054,0.91712,1,0.995,0.4975,1.46309,2.36933,2.85069,0.000289271,0.000289271,0.000289271
+75,209.747,0.63635,1.12553,1.08396,0.89736,1,0.995,0.4975,2.01013,2.37889,4.34671,0.000282765,0.000282765,0.000282765
+76,212.426,0.56775,1.05188,1.02575,0.89736,1,0.995,0.4975,2.01013,2.37889,4.34671,0.000275976,0.000275976,0.000275976
+77,215.026,0.43724,0.95903,1.01736,0.89736,1,0.995,0.4975,2.01013,2.37889,4.34671,0.000268904,0.000268904,0.000268904
+78,217.817,0.49229,0.88203,1.01539,0.85551,1,0.995,0.4975,2.0952,2.52227,4.83762,0.000261548,0.000261548,0.000261548
+79,220.743,0.47117,1.11954,1.09779,0.85551,1,0.995,0.4975,2.0952,2.52227,4.83762,0.00025391,0.00025391,0.00025391
+80,223.356,0.58022,1.04246,0.99036,0.85551,1,0.995,0.4975,2.0952,2.52227,4.83762,0.000245989,0.000245989,0.000245989
+81,225.935,0.61401,1.13442,0.96073,0.83857,1,0.995,0.4975,2.19165,2.57405,5.03373,0.000237786,0.000237786,0.000237786
+82,228.522,0.47233,0.98295,0.93551,0.83857,1,0.995,0.4975,2.19165,2.57405,5.03373,0.000229299,0.000229299,0.000229299
+83,231.056,0.46086,0.95889,1.1165,0.83857,1,0.995,0.4975,2.19165,2.57405,5.03373,0.000220529,0.000220529,0.000220529
+84,233.689,0.52556,1.12957,1.14809,0.8797,1,0.995,0.398,2.21491,2.61625,5.02132,0.000211476,0.000211476,0.000211476
+85,236.229,0.49616,0.89619,1.0761,0.8797,1,0.995,0.398,2.21491,2.61625,5.02132,0.000202141,0.000202141,0.000202141
+86,238.705,0.57299,1.11491,1.08678,0.8797,1,0.995,0.398,2.21491,2.61625,5.02132,0.000192522,0.000192522,0.000192522
+87,241.259,0.45905,0.98139,0.9778,0.8797,1,0.995,0.398,2.21491,2.61625,5.02132,0.00018262,0.00018262,0.00018262
+88,243.933,0.38689,0.90251,0.9659,0.91757,1,0.995,0.398,2.22704,2.55291,4.98023,0.000172436,0.000172436,0.000172436
+89,246.436,0.43412,0.95737,0.94602,0.91757,1,0.995,0.398,2.22704,2.55291,4.98023,0.000161969,0.000161969,0.000161969
+90,248.988,0.50118,1.11218,1.05597,0.91757,1,0.995,0.398,2.22704,2.55291,4.98023,0.000151218,0.000151218,0.000151218
+91,251.53,0.52924,1.61464,1.14575,0.91757,1,0.995,0.398,2.22704,2.55291,4.98023,0.000140185,0.000140185,0.000140185
+92,254.092,0.52025,1.45265,1.09009,0.94187,1,0.995,0.4975,2.25588,2.44145,5.02005,0.000128869,0.000128869,0.000128869
+93,256.641,0.56167,1.64718,1.10248,0.94187,1,0.995,0.4975,2.25588,2.44145,5.02005,0.000117269,0.000117269,0.000117269
+94,259.287,0.37101,1.41386,0.97247,0.94187,1,0.995,0.4975,2.25588,2.44145,5.02005,0.000105387,0.000105387,0.000105387
+95,261.787,0.55259,1.68901,1.03943,0.94187,1,0.995,0.4975,2.25588,2.44145,5.02005,9.32222e-05,9.32222e-05,9.32222e-05
+96,264.336,0.52351,1.65839,0.94238,0.95212,1,0.995,0.4975,2.23013,2.49107,4.90353,8.07742e-05,8.07742e-05,8.07742e-05
+97,266.833,0.34686,1.46372,0.95087,0.95212,1,0.995,0.4975,2.23013,2.49107,4.90353,6.80433e-05,6.80433e-05,6.80433e-05
+98,269.624,0.50176,1.58134,1.06032,0.95212,1,0.995,0.4975,2.23013,2.49107,4.90353,5.50294e-05,5.50294e-05,5.50294e-05
+99,272.44,0.33641,1.38546,0.85527,0.95212,1,0.995,0.4975,2.23013,2.49107,4.90353,4.17325e-05,4.17325e-05,4.17325e-05
+100,275.169,0.43903,1.4893,1.03298,0.95601,1,0.995,0.4975,2.221,2.50947,4.8392,2.81527e-05,2.81527e-05,2.81527e-05

backend/test_model.py

@@ -1,11 +1,12 @@
-from backend.models.yolo_manager import YOLOManager
+from models.yolo_manager import YOLOManager
 import cv2
 import os
 
-def test_model(model_path="backend/models/best.pt", source="test_video.mp4"):
+def test_model(model_path=r"D:\Time-Pass-Projects\pothole-roadsign detection\backend\runs\detect\train3\weights\best.pt", source="test_video.mp4"):
     """
     Tests the YOLO model on a video or image.
     """
+    print(f"DEBUG: Looking for model at: {os.path.abspath(model_path)}")
     if not os.path.exists(model_path):
         print(f"Model not found at {model_path}. Using standard yolov8n.pt for demo.")
         model_path = "yolov8n.pt"
@@ -20,8 +21,9 @@ def test_model(model_path="backend/models/best.pt", source="test_video.mp4"):
             print(f"Could not read image: {source}")
             return
         
-        results = yolo.detect(frame)
+        results = yolo.detect(frame, conf=0.01)
         res_plotted = results.plot()
+        print(f"Detections: {len(results.boxes)}")
         cv2.imshow("YOLO Detection", res_plotted)
         cv2.waitKey(0)
         cv2.destroyAllWindows()
@@ -40,7 +42,7 @@ def test_model(model_path="backend/models/best.pt", source="test_video.mp4"):
                 break
             
             # Use 'track' or 'detect'
-            results = yolo.track(frame)
+            results = yolo.track(frame, conf=0.01)
             
             # Plot results on frame
             annotated_frame = results.plot()
@@ -54,7 +56,7 @@ def test_model(model_path="backend/models/best.pt", source="test_video.mp4"):
 
 if __name__ == "__main__":
     # CHANGE THIS to your test file
-    TEST_FILE = "d:/path/to/your/test/video_or_image.jpg" 
+    TEST_FILE = r"D:\Time-Pass-Projects\pothole-roadsign detection\datasets\road_signs_potholes\test_video.mp4" 
     
     if not os.path.exists(TEST_FILE):
         if TEST_FILE == "0":

datasets/road_signs_potholes/val/labels/road_003.txt

@@ -1 +1 @@
-0 0.4 0.4 0.15 0.15
+0 0.481481 0.488739 0.757202 0.815315