training for JC deployment

runs/detect/train12/args.yaml

@@ -0,0 +1,107 @@
+task: detect
+mode: train
+model: yolo11s.pt
+data: ./yolov11-pecan/data.yaml
+epochs: 25
+time: null
+patience: 100
+batch: 20
+imgsz: 1280
+save: true
+save_period: -1
+cache: false
+device: cuda
+workers: 16
+project: null
+name: train12
+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
+save_hybrid: 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: 4
+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
+label_smoothing: 0.0
+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
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+crop_fraction: 1.0
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/engr-ugaif/USDA-throughput-control/runs/detect/train12

runs/detect/train12/results.csv

@@ -0,0 +1,26 @@
+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
+1,506.754,0.69773,0.6443,0.98677,0.85746,0.90067,0.95602,0.81969,0.57211,0.44531,0.84271,0.000665995,0.000665995,0.000665995
+2,775.31,0.67191,0.46142,0.96903,0.89594,0.91124,0.96492,0.83347,0.56171,0.43418,0.84033,0.00127989,0.00127989,0.00127989
+3,1042.43,0.64879,0.43295,0.95724,0.89927,0.92376,0.97455,0.84793,0.53096,0.3909,0.82332,0.00184098,0.00184098,0.00184098
+4,1309.29,0.63499,0.41484,0.94974,0.8901,0.90711,0.96519,0.83708,0.53559,0.41364,0.82635,0.0017624,0.0017624,0.0017624
+5,1576.24,0.6194,0.39346,0.94417,0.92455,0.92984,0.97784,0.85866,0.51774,0.35537,0.81741,0.0016832,0.0016832,0.0016832
+6,1843.45,0.60151,0.37385,0.93784,0.89506,0.93742,0.96631,0.83846,0.55381,0.38597,0.82555,0.001604,0.001604,0.001604
+7,2110.63,0.58751,0.35579,0.93003,0.90571,0.9501,0.97622,0.86446,0.51076,0.3642,0.8146,0.0015248,0.0015248,0.0015248
+8,2377.57,0.57208,0.34024,0.92507,0.90235,0.93492,0.9714,0.86352,0.50438,0.35819,0.81116,0.0014456,0.0014456,0.0014456
+9,2644.65,0.55947,0.32402,0.91929,0.91572,0.94436,0.97664,0.87084,0.49431,0.34051,0.80756,0.0013664,0.0013664,0.0013664
+10,2911.65,0.54281,0.31078,0.91366,0.91424,0.93562,0.9652,0.86171,0.4887,0.38716,0.80484,0.0012872,0.0012872,0.0012872
+11,3178.42,0.52475,0.29805,0.90675,0.90982,0.9442,0.96658,0.86221,0.49884,0.37786,0.80951,0.001208,0.001208,0.001208
+12,3445.37,0.50654,0.28378,0.90022,0.91695,0.94206,0.96273,0.85841,0.50642,0.37648,0.81476,0.0011288,0.0011288,0.0011288
+13,3712.44,0.48918,0.27473,0.89372,0.91413,0.9375,0.961,0.85692,0.51257,0.38685,0.81386,0.0010496,0.0010496,0.0010496
+14,3979.6,0.47069,0.26422,0.88725,0.91369,0.94444,0.96014,0.85136,0.51508,0.37853,0.81735,0.0009704,0.0009704,0.0009704
+15,4246.8,0.45515,0.25584,0.88293,0.89485,0.94321,0.94822,0.84115,0.51803,0.40433,0.81875,0.0008912,0.0008912,0.0008912
+16,4509.67,0.40004,0.21119,0.8626,0.91392,0.93884,0.94297,0.83674,0.5208,0.42094,0.8231,0.000812,0.000812,0.000812
+17,4771.34,0.37703,0.19988,0.85195,0.90937,0.94359,0.94351,0.83788,0.52937,0.41134,0.82689,0.0007328,0.0007328,0.0007328
+18,5032.84,0.35892,0.19194,0.84558,0.90822,0.93263,0.93177,0.82919,0.52888,0.46293,0.8317,0.0006536,0.0006536,0.0006536
+19,5294.47,0.34436,0.18312,0.84155,0.91178,0.93976,0.9361,0.83365,0.52819,0.43623,0.83142,0.0005744,0.0005744,0.0005744
+20,5556.06,0.3276,0.17687,0.83577,0.9108,0.9393,0.9371,0.83403,0.52633,0.4396,0.83187,0.0004952,0.0004952,0.0004952
+21,5817.69,0.31108,0.16883,0.83093,0.91184,0.93631,0.93389,0.83055,0.52741,0.45089,0.83429,0.000416,0.000416,0.000416
+22,6079.32,0.29764,0.1618,0.8259,0.91338,0.93828,0.93298,0.83033,0.52668,0.4425,0.83452,0.0003368,0.0003368,0.0003368
+23,6340.95,0.28511,0.15486,0.82229,0.91827,0.93003,0.9306,0.82773,0.52781,0.47135,0.8384,0.0002576,0.0002576,0.0002576
+24,6602.43,0.27296,0.14872,0.81929,0.91692,0.92886,0.93197,0.82858,0.52829,0.48239,0.83885,0.0001784,0.0001784,0.0001784
+25,6864.01,0.26224,0.14304,0.81588,0.91716,0.93172,0.93469,0.83199,0.52728,0.48326,0.84022,9.92e-05,9.92e-05,9.92e-05

yolov11-pecan/train.py

@@ -0,0 +1,8 @@
+from ultralytics import YOLO
+import torch
+
+device = torch.device('cuda')
+# device = 'cpu'
+
+model = YOLO('yolo11s.pt')
+model.train(data='./yolov11-pecan/data.yaml',device=device,batch=20,epochs=25,workers=16, imgsz = 1280)