风筝超冷

YOLOv5 第Y6周模型改进

本文为[365天深度学习训练营学习记录博客
参考文章：365天深度学习训练营
原作者：[K同学啊]
文章来源：[K同学的学习圈子](https://www.yuque.com/mingtian-fkmxf/zxwb45)

改进前模型框架图：

改进后模型框架图：

改进前：

改进后：

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],    # 1-P2/4
   [-1, 3, C3, [128]],            # 2
   [-1, 1, Conv, [256, 3, 2]],    # 3-P3/8
   [-1, 6, C2, [256]],            # 4-修改为C2*2
   [-1, 1, Conv, [512, 3, 2]],    # 5-P4/16
   [-1, 3, C3, [512]],            # 6-修改为C3*1
#   [-1, 1, Conv, [1024, 3, 2]],   # 7-删除P5/32
#   [-1, 3, C3, [1024]],           # 8-删除
   [-1, 1, SPPF, [512, 5]],      # 9-修改参数;层数变为7
  ]

修改前：

修改后：

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 3, 2]], # 修改参数
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13->11

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17->15 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 12], 1, Concat, [1]],  # cat head P4 修改层数-2
   [-1, 3, C3, [512, False]],  # 20->18 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 8], 1, Concat, [1]],  # cat head P5 修改层数-2
   [-1, 3, C3, [1024, False]],  # 23->21 (P5/32-large)

   [[15, 18, 21], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5) 修改层数-2
  ]

执行命令行：

python train.py --img 900 --batch 2 --epoch 100 --data D:/yolov5-master/data/ab.yaml --cfg D:/yolov5-master/models/yolov5s.yaml --weights yolov5s.pt

运行结果：

D:\yolov5-master>python train.py --img 900 --batch 2 --epoch 100 --data D:/yolov5-master/data/ab.yaml --cfg D:/yolov5-master/models/yolov5s.yaml --weights yolov5s.pt
train: weights=yolov5s.pt, cfg=D:/yolov5-master/models/yolov5s.yaml, data=D:/yolov5-master/data/ab.yaml, hyp=data\hyps\hyp.scratch-low.yaml, epochs=100, batch_size=2, imgsz=900, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=None, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs\train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
github: skipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5
YOLOv5  2023-10-15 Python-3.10.7 torch-2.0.1+cpu CPU

hyperparameters: 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=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, 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, mosaic=1.0, mixup=0.0, copy_paste=0.0
Comet: run 'pip install comet_ml' to automatically track and visualize YOLOv5  runs in Comet
TensorBoard: Start with 'tensorboard --logdir runs\train', view at http://localhost:6006/
Overriding model.yaml nc=80 with nc=4

                 from  n    params  module                                  arguments
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]
  2                -1  1     18816  models.common.C3                        [64, 64, 1]
  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]
  4                -1  2    115712  models.common.C2                        [128, 128, 2]
  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]
  6                -1  3    625152  models.common.C3                        [256, 256, 3]
  7                -1  1    296192  models.common.SPPF                      [256, 512, 5]
  8                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]
  9                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']
 10           [-1, 6]  1         0  models.common.Concat                    [1]
 11                -1  1    361984  models.common.C3                        [512, 256, 1, False]
 12                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]
 13                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']
 14           [-1, 4]  1         0  models.common.Concat                    [1]
 15                -1  1     90880  models.common.C3                        [256, 128, 1, False]
 16                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]
 17          [-1, 12]  1         0  models.common.Concat                    [1]
 18                -1  1    296448  models.common.C3                        [256, 256, 1, False]
 19                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]
 20           [-1, 8]  1         0  models.common.Concat                    [1]
 21                -1  1   1182720  models.common.C3                        [512, 512, 1, False]
 22      [15, 18, 21]  1     24273  models.yolo.Detect                      [4, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Traceback (most recent call last):
  File "D:\yolov5-master\train.py", line 647, in 
    main(opt)
  File "D:\yolov5-master\train.py", line 536, in main
    train(opt.hyp, opt, device, callbacks)
  File "D:\yolov5-master\train.py", line 130, in train
    model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
  File "D:\yolov5-master\models\yolo.py", line 195, in __init__
    m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
  File "D:\yolov5-master\models\yolo.py", line 194, in 
    forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)
  File "D:\yolov5-master\models\yolo.py", line 209, in forward
    return self._forward_once(x, profile, visualize)  # single-scale inference, train
  File "D:\yolov5-master\models\yolo.py", line 121, in _forward_once
    x = m(x)  # run
  File "D:\Python\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "D:\yolov5-master\models\common.py", line 336, in forward
    return torch.cat(x, self.d)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 32 but got size 16 for tensor number 1 in the list.

D:\yolov5-master>python train.py --img 900 --batch 2 --epoch 100 --data D:/yolov5-master/data/ab.yaml --cfg D:/yolov5-master/models/yolov5s.yaml --weights yolov5s.pt
train: weights=yolov5s.pt, cfg=D:/yolov5-master/models/yolov5s.yaml, data=D:/yolov5-master/data/ab.yaml, hyp=data\hyps\hyp.scratch-low.yaml, epochs=100, batch_size=2, imgsz=900, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=None, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs\train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
github: skipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5
YOLOv5  2023-10-15 Python-3.10.7 torch-2.0.1+cpu CPU

hyperparameters: 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=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, 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, mosaic=1.0, mixup=0.0, copy_paste=0.0
Comet: run 'pip install comet_ml' to automatically track and visualize YOLOv5  runs in Comet
TensorBoard: Start with 'tensorboard --logdir runs\train', view at http://localhost:6006/
Overriding model.yaml nc=80 with nc=4

                 from  n    params  module                                  arguments
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]
  2                -1  1     18816  models.common.C3                        [64, 64, 1]
  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]
  4                -1  2    115712  models.common.C2                        [128, 128, 2]
  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]
  6                -1  1    296448  models.common.C3                        [256, 256, 1]
  7                -1  1    164608  models.common.SPPF                      [256, 256, 5]
  8                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]
  9                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']
 10           [-1, 6]  1         0  models.common.Concat                    [1]
 11                -1  1    361984  models.common.C3                        [512, 256, 1, False]
 12                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]
 13                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']
 14           [-1, 4]  1         0  models.common.Concat                    [1]
 15                -1  1     90880  models.common.C3                        [256, 128, 1, False]
 16                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]
 17          [-1, 12]  1         0  models.common.Concat                    [1]
 18                -1  1    296448  models.common.C3                        [256, 256, 1, False]
 19                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]
 20           [-1, 8]  1         0  models.common.Concat                    [1]
 21                -1  1   1182720  models.common.C3                        [512, 512, 1, False]
 22      [15, 18, 21]  1     24273  models.yolo.Detect                      [4, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
YOLOv5s summary: 179 layers, 4304785 parameters, 4304785 gradients, 13.4 GFLOPs

Transferred 126/289 items from yolov5s.pt
WARNING  --img-size 900 must be multiple of max stride 32, updating to 928
optimizer: SGD(lr=0.01) with parameter groups 47 weight(decay=0.0), 50 weight(decay=0.0005), 50 bias
train: Scanning D:\yolov5-master\Y2\train... 1 images, 0 backgrounds, 159 corrupt: 100%|██████████| 160/160 [00:13<00:0
train: WARNING   D:\yolov5-master\Y2\images\fruit1.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit1.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit10.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit10.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit100.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit100.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit102.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit102.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit103.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit103.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit104.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit104.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit106.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit106.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit108.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit108.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit109.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit109.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit11.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit11.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit110.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit110.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit111.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit111.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit113.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit113.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit114.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit114.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit115.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit115.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit116.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit116.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit117.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit117.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit118.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit118.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit119.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit119.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit12.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit12.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit120.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit120.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit121.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit121.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit122.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit122.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit123.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit123.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit124.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit124.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit125.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit125.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit127.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit127.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit129.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit129.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit13.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit13.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit130.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit130.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit131.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit131.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit132.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit132.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit133.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit133.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit134.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit134.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit135.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit135.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit136.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit136.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit138.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit138.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit14.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit14.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit142.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit142.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit143.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit143.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit144.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit144.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit145.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit145.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit147.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit147.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit148.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit148.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit149.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit149.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit15.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit15.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit151.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit151.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit152.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit152.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit155.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit155.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit156.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit156.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit157.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit157.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit158.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit158.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit159.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit159.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit16.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit16.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit161.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit161.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit162.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit162.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit163.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit163.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit164.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit164.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit165.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit165.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit167.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit167.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit168.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit168.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit169.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit169.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit17.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit17.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit170.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit170.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit171.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit171.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit172.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit172.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit173.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit173.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit174.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit174.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit175.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit175.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit176.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit176.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit177.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit177.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit178.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit178.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit179.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit179.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit18.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit18.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit180.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit180.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit181.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit181.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit182.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit182.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit183.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit183.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit184.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit184.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit185.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit185.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit186.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit186.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit187.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit187.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit188.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit188.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit19.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit19.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit196.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit196.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit197.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit197.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit198.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit198.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit199.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit199.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit2.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit2.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit200.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit200.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit202.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit202.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit208.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit208.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit209.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit209.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit211.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit211.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit22.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit22.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit23.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit23.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit25.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit25.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit26.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit26.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit27.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit27.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit28.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit28.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit29.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit29.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit3.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit3.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit30.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit30.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit31.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit31.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit33.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit33.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit34.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit34.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit35.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit35.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit36.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit36.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit38.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit38.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit39.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit39.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit4.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit4.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit40.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit40.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit43.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit43.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit44.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit44.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit45.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit45.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit46.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit46.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit49.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit49.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit50.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit50.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit51.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit51.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit52.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit52.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit53.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit53.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit54.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit54.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit55.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit55.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit57.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit57.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit59.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit59.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit6.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit6.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit60.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit60.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit61.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit61.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit62.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit62.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit63.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit63.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit65.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit65.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit66.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit66.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit68.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit68.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit69.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit69.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit7.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit7.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit70.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit70.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit71.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit71.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit73.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit73.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit74.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit74.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit75.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit75.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit77.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit77.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit78.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit78.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit79.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit79.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit80.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit80.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit81.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit81.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit82.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit82.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit83.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit83.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit85.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit85.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit86.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit86.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit87.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit87.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit88.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit88.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit89.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit89.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit90.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit90.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit91.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit91.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit94.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit94.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit95.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit95.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit97.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit97.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit98.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit98.png'
train: WARNING   D:\yolov5-master\Y2\images\fruit99.png: ignoring corrupt image/label: [Errno 22] Invalid argument: ' D:\\yolov5-master\\Y2\\images\\fruit99.png'
train: WARNING  Cache directory D:\yolov5-master\Y2 is not writeable: [WinError 183] : 'D:\\yolov5-master\\Y2\\train.cache.npy' -> 'D:\\yolov5-master\\Y2\\train.cache'
val: Scanning D:\yolov5-master\Y2\val.cache... 1 images, 0 backgrounds, 19 corrupt: 100%|██████████| 20/20 [00:00

【目标检测数据集】卡车数据集1073张VOC+YOLO格式熬夜写代码的平头哥∰ 目标检测 YOLO 人工智能
数据集格式：PascalVOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)图片数量(jpg文件个数)：1073标注数量(xml文件个数)：1073标注数量(txt文件个数)：1073标注类别数：1标注类别名称:["truck"]每个类别标注的框数：truck框数=1120总框数：1120使用标注工具：labelImg标注
钢筋长度超限检测检数据集VOC+YOLO格式215张1类别 futureflsl 数据集 YOLO 深度学习机器学习
数据集格式：PascalVOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)图片数量(jpg文件个数)：215标注数量(xml文件个数)：215标注数量(txt文件个数)：215标注类别数：1标注类别名称:["iron"]每个类别标注的框数：iron框数=215总框数：215使用标注工具：labelImg标注规则：对类别进
COCO 格式的数据集转化为 YOLO 格式的数据集 QYQY77 YOLO python
"""--json_path输入的json文件路径--save_path保存的文件夹名字，默认为当前目录下的labels。"""importosimportjsonfromtqdmimporttqdmimportargparseparser=argparse.ArgumentParser()parser.add_argument('--json_path',default='./instances
yolov5＞onnx＞ncnn＞apk 图像处理大大大大大牛啊 opencv实战代码讲解 yolo onnx ncnn 安卓
一.yolov5pt模型转onnx条件：colabnotebookyolov51.安装环境!pipinstallonnx>=1.7.0#forONNXexport!pipinstallcoremltools==4.0#forCoreMLexport!pipinstallonnx-simplifier2.修改common.py在classFocus下面
[数据集][目标检测]汽车头部尾部检测数据集VOC+YOLO格式5319张3类别 FL1623863129 数据集目标检测汽车 YOLO
数据集制作单位：未来自主研究中心(FIRC)版权单位：未来自主研究中心(FIRC)版权声明：数据集仅仅供个人使用，不得在未授权情况下挂淘宝、咸鱼等交易网站公开售卖,由此引发的法律责任需自行承担数据集格式：PascalVOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)图片数量(jpg文件个数)：5319标注数量(xml文件
遥感图像分割系统：融合空间金字塔池化（FocalModulation)改进YOLOv8 xuehaisj YOLO 人工智能计算机视觉 yolov8
1.研究背景与意义项目参考AAAIAssociationfortheAdvancementofArtificialIntelligence研究背景与意义遥感图像分割是遥感技术领域中的一个重要研究方向，它的目标是将遥感图像中的不同地物或地物类别进行有效的分割和识别。随着遥感技术的不断发展和遥感图像数据的大规模获取，遥感图像分割在农业、城市规划、环境监测等领域具有广泛的应用前景。然而，由于遥感图像的特
如何理解深度学习的训练过程奋斗的草莓熊深度学习人工智能 python scikit-learn virtualenv numpy pandas
文章目录1.训练是干什么？2.预训练模型进行训练，主要更改的是预训练模型的什么东西？1.训练是干什么？以yolov5为例子，训练的目的是把一组输入猫狗图像放到神经网络中，得到一个输出模型，这个模型下次可以直接用来识别哪个是猫，哪个是狗2.预训练模型进行训练，主要更改的是预训练模型的什么东西？超参数（Hyperparameters）：这是模型结构中定义的参数，比如：卷积核大小（kernel_size
基于YOLOV5人脸检测打上码赛克 Deep-white YOLO 人工智能深度学习
还在为自己的隐私而烦恼吗，还在为拍摄的视频因不想露脸而无法发布吗。yolov5检测人脸，并打上马赛克，保护自己的隐私。只需下载代码，解压缩后就可以传入你想要打马赛克的视频或者图片了。这个是需要你对代码有一些了解的，等我开发一下使大家都可以用。里面权重已经训练好了，也有一些人脸的数据集，数据量不多，训练完的权重不是很好，但是给自己的视频打上马赛克足够了。大家要是想去增加数据集，可以使用里面的权重利用
yolov5单目测距+速度测量+目标跟踪 cv_2025 YOLO 目标跟踪人工智能计算机视觉机器学习图像处理 opencv
要在YOLOv5中添加测距和测速功能，您需要了解以下两个部分的原理：单目测距算法单目测距是使用单个摄像头来估计场景中物体的距离。常见的单目测距算法包括基于视差的方法（如立体匹配）和基于深度学习的方法（如神经网络）。基于深度学习的方法通常使用卷积神经网络（CNN）来学习从图像到深度图的映射关系。单目测距代码单目测距涉及到坐标转换，代码如下：defconvert_2D_to_3D(point2D,R,
粉尘识别数据集——工地/矿下粉尘数据识别，数据集已划分，YOLO格式-有权重，相关指数，map相当高毕设宇航 YOLO 机器学习目标跟踪
数据集名称粉尘识别数据集数据集描述这是一个专门针对工地或矿下粉尘识别设计的数据集，包含了大量的高清图像，用于识别施工或采矿环境中产生的粉尘。数据集已经按照标准的数据划分方法分为训练集、验证集和测试集，并且以YOLO格式进行了标注。此外，数据集中还包含了预训练的模型权重和相关性能指标，如mAP（MeanAveragePrecision），表明模型在粉尘识别任务上的表现优异。数据集特点高清图像：所有图
YOLOV8改进-C2f添加Deformable Conv V2 森爱。 YOLOV8改进 YOLO
目录1DeformableConvV2介绍2YOLOV8添加DeformableConvV22.1代码添加到Blocks2.1.1C2f_DCN代码2.1.2加入_all_导入2.1.3加入modules导入2.2添加至运行模块tasks2.2.1导入包2.2.2解析参数添加2.3在_init_中增加名称2.4模型配置文件yaml替换1DeformableConvV2介绍论文地址:https://
结合YOLOv8和OpenCV WeChat QRCode打造一款二维码识别器搜狐技术产品小编2023 YOLO opencv 微信人工智能计算机视觉
本文字数：3876字预计阅读时间：25分钟01引言二维码（QRCode）在现代生活中有广泛应用，从支付系统到信息传递，它们无处不在。本文提出了一种如何识别二维码的方法，主要贡献在于优化处理分辨率较高的图像时，由于二维码在整张图片中占据的比例较小，传统的OpenCVWeChatQRCode的识别方法表现不佳的问题。下面描述详细的优化过程。02OpenCVWeChatQRCodeWeChatQRCod
【目标检测数据集】番茄叶片病害数据集13940张9类VOC+YOLO格式熬夜写代码的平头哥∰ 数据集目标检测 YOLO 目标跟踪
数据集格式：PascalVOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)图片数量(jpg文件个数)：13946标注数量(xml文件个数)：13946标注数量(txt文件个数)：13946标注类别数：9标注类别名称:["EarlyBlight","Healthy","LateBlight","LeafMiner","Le
YOLOv8数据增强热心小张研究生 yolov8
1.找到augment.py（ultralytics/data/augment.py），修改对应内容#TransformsT=[A.Blur(p=0.01),A.MedianBlur(p=0.01),A.ToGray(p=0.01),A.CLAHE(p=0.01),A.RandomBrightnessContrast(p=0.0),A.RandomGamma(p=0.0),A.ImageCompr
[数据集][目标检测]血细胞检测数据集VOC+YOLO格式2757张4类别 FL1623863129 数据集目标检测 YOLO 人工智能
数据集格式：PascalVOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)图片数量(jpg文件个数)：2757标注数量(xml文件个数)：2757标注数量(txt文件个数)：2757标注类别数：4标注类别名称:["Platelets","RBC","WBC","sicklecell"]每个类别标注的框数：Platelet
目标检测YOLO系列从入门到精通技术详解100篇-【目标检测】工业相机格图素书数码相机目标检测人工智能
目录知识储备深度相机1TOF2双目视觉3结构光4智能门锁应用5手机应用算法原理相机的成像与标定模型相机标定的实施·标定过程的算法实施相机标定的扩展CCD工业相机、镜头倍率及相关参数计算方法知识储备深度相机1TOF1.1Kinectv2Kinectv2是Microsoft在2014年发售的，如图1-1所示。相比于Kinectv1在硬件和软件上作出了很大的进化，且在深度测量的系统和非系统误差方面表现出
ERROR: Could not install packages due to an OSError: [Errno 2] No such file or directory:错误解决 nomoremorphine python pip 计算机视觉目标检测
安装yolov8时(pipinstallultralytics)报错：ERROR:CouldnotinstallpackagesduetoanOSError:[Errno2]没有那个文件或目录:‘xxxx/anaconda3/envs/v8-test/lib/python3.7/site-packages/numpy-1.21.6.dist-info/METADATA’问题原因：安装环境里对应的安
论文阅读笔记（十九）：YOLO9000: Better, Faster, Stronger __Sunshine__ 笔记 YOLO9000 detection classification
WeintroduceYOLO9000,astate-of-the-art,real-timeobjectdetectionsystemthatcandetectover9000objectcategories.FirstweproposevariousimprovementstotheYOLOdetectionmethod,bothnovelanddrawnfrompriorwork.Theim
Yolo-v3利用GPU训练make时发生错误：/usr/bin/ld: cannot find -lcuda 徐小妞66666
一.利用GPU训练Yolov3时，首先要修改MakeFile文件，修改格式如下：GPU=1(原来为0)CUDNN=1(原来为0)NVCC=/usr/local/cuda/bin/nvcc(新建,注意自己本机的地址)二.此时make产生错误/usr/bin/ld:cannotfind-lcuda1.查看MakeFile文件找到该行代码：LDFLAGS+=-L/usr/local/cuda/lib64
yolov5 +gui界面+单目测距实现对图片视频摄像头的测距毕设宇航 QQ767172261 yolov5 单目测距
可实现对图片，视频，摄像头的检测项目概述本项目旨在实现一个集成了YOLOv5目标检测算法、图形用户界面（GUI）以及单目测距功能的系统。该系统能够对图片、视频或实时摄像头输入进行目标检测，并估算目标的距离。通过结合YOLOv5的强大检测能力和单目测距技术，系统能够在多种应用场景中提供高效、准确的目标检测和测距功能。技术栈YOLOv5：用于目标检测的深度学习模型。OpenCV：用于图像处理和单目测距
目标检测-YOLOv3 wydxry 深度学习目标检测 YOLO 深度学习
YOLOv3介绍YOLOv3(YouOnlyLookOnce,Version3)是YOLO系列目标检测模型的第三个版本，相较于YOLOv2有了显著的改进和增强，尤其在检测速度和精度上表现优异。YOLOv3的设计目标是在保持高速的前提下提升检测的准确性和稳定性。下面是对YOLOv3改进和优势的介绍，以及YOLOv3核心部分的代码展示。相比YOLOv2的改进与优势多尺度特征金字塔YOLOv3引入了FP
使用TensorRT对YOLOv8模型进行加速推理 fengbingchun Deep Learning CUDA/TensorRT YOLOv8 TensorRT
这里使用GitHub上shouxieai的infer框架对YOLOv8模型进行加速推理，操作过程如下所示：1.配置环境，依赖项，包括：(1).CUDA:11.8(2).cuDNN:8.7.0(3).TensorRT:8.5.3.1(4).ONNX:1.16.0(5).OpenCV:4.10.02.cloneinfer代码：https://github.com/shouxieai/infer3.使用
使用yolov8识别+深度相机+机械臂实现垃圾分拣机械臂（代码分享）调包侠@ YOLO 数码相机毕业设计
文章目录垃圾分拣机械臂总体介绍主要功能与特色视频演示文件目录程序主代码完整代码链接垃圾分拣机械臂总体介绍本作品将视觉识别技术部署在嵌入式设备，自动控制机械臂进行分拣任务，在我们的设计中，首先使用深度相机将图像信息发送到嵌入式设备，视觉识别算法进行分类检测，将垃圾分为感染性，损失性，病理性，药物性，化学性，并根据相机的深度值计算出目标的三维坐标，由于系统使用眼在手外的结构，根据手眼标定的结果，将坐标
【深度学习实战】行人检测追踪与双向流量计数系统【python源码+Pyqt5界面+数据集+训练代码】YOLOv8、ByteTrack、目标追踪、双向计数、行人检测追踪、过线计数阿_旭 AI应用软件开发实战深度学习实战深度学习 python 行人检测行人追踪过线计数
《博主简介》小伙伴们好，我是阿旭。专注于人工智能、AIGC、python、计算机视觉相关分享研究。✌更多学习资源，可关注公-仲-hao:【阿旭算法与机器学习】，共同学习交流~感谢小伙伴们点赞、关注！《------往期经典推荐------》一、AI应用软件开发实战专栏【链接】项目名称项目名称1.【人脸识别与管理系统开发】2.【车牌识别与自动收费管理系统开发】3.【手势识别系统开发】4.【人脸面部活体
pytorch训练后pt模型中保存内容详解(yolov8n.pt为例) yueguang8 yolo算法 pytorch YOLO 人工智能
在PyTorch中，.pt模型文件通常包含以下几类数据：模型参数：存储模型的权重和偏置参数。优化器状态：包含优化器的状态信息，以便在恢复训练时能够从中断的地方继续。训练状态：一些训练过程中的信息，例如当前的epoch数和训练进度。其他元数据：包括模型的配置、训练时使用的超参数等。在讲解pytorchpt(pth)文件中保存了什么内容之前，需要先了解pt在保存时保存了那些参数。以YOLO系列pt保存
实训day4 yolo1代码运行 Hazelyu27
yolo1代码运行今天主要是在pycharm上运行pytorch的yolo1训练和测试代码。主要遇到的问题：1.训练文件路径的修改，开始没有找到tmp_file文件，就在该文件夹下创建了这个txt文件，但是发现：ifisinstance(list_file,list):#Catmultiplelistfilestogether.#Thisisespeciallyusefulforvoc07/voc
[数据集][目标检测]街道乱堆垃圾检测数据集VOC+YOLO格式94张1类别 FL1623863129 数据集目标检测 YOLO 人工智能
数据集格式：PascalVOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)图片数量(jpg文件个数)：94标注数量(xml文件个数)：94标注数量(txt文件个数)：94标注类别数：1标注类别名称:["baolu"]每个类别标注的框数：baolu框数=107总框数：107使用标注工具：labelImg标注规则：对类别进行
地平线旭日x3派部署yolov8 巴啦啦魔仙变！！ YOLO python 数学建模
地平线旭日x3派部署yolov8总体流程1.导出onnx模型导出YOLOV8_onnxruntime.py验证onnxutils.py2.在开发机转为bin模型2.1准备数据图片2.2转换必备的yaml文件2.3开始转换3.开发机验证**quantized_model.onnx4.板子运行bin模型资源链接总体流程1.导出onnx模型导出使用yolov8的github库导出onnx模型。注意设置o
YOLOv8改进 | 检测头篇 | YOLOv8引入DynamicHead检测头小李学AI YOLOv8有效涨点专栏 YOLO 深度学习目标检测计算机视觉机器学习人工智能
1.DynamicHead描述1.1摘要：在目标检测中，定位和分类相结合的复杂性导致了各种方法的蓬勃发展。以往的工作试图提高各种目标检测头的性能，但未能呈现出统一的观点。本文根据目标检测的特点，推导了一种新的动态头部框架，将目标检测头部与注意力统一起来。该方法通过在特征层次间、空间位置间和输出通道内协调组合多种自注意机制，在不增加计算开销的情况下显著提高了目标检测头的表示能力。进一步的实验表明，本
YOLOv8 只检测人只画框不要标签 waketzheng YOLO
参考了这个：YOLOv8只检测人（或其他一种或者多种类别）_yolov8只检测指定类别-CSDN博客1.只检测人：predict的时候指定参数classes=[0]2.只画框不要标签：plot的时候传入labels=False3.标签中去掉置信度：result.plot(conf=False)示例代码如下：#!/usr/bin/envpythonimportcontextlibfromdateti
sql统计相同项个数并按名次显示朱辉辉33 java oracle
现在有如下这样一个表： A表 ID Name time ------------------------------ 0001 aaa 2006-11-18 0002 ccc 2006-11-18 0003 eee 2006-11-18 0004 aaa 2006-11-18 0005 eee 2006-11-18 0004 aaa 2006-11-18 0002 ccc 20
Android+Jquery Mobile学习系列-目录白糖_ JQuery Mobile
最近在研究学习基于Android的移动应用开发，准备给家里人做一个应用程序用用。向公司手机移动团队咨询了下，觉得使用Android的WebView上手最快，因为WebView等于是一个内置浏览器，可以基于html页面开发，不用去学习Android自带的七七八八的控件。然后加上Jquery mobile的样式渲染和事件等，就能非常方便的做动态应用了。从现在起，往后一段时间，我打算
如何给线程池命名 daysinsun 线程池
在系统运行后，在线程快照里总是看到线程池的名字为pool-xx，这样导致很不好定位，怎么给线程池一个有意义的名字呢。参照ThreadPoolExecutor类的ThreadFactory，自己实现ThreadFactory接口，重写newThread方法即可。参考代码如下： public class Named
IE 中"HTML Parsing Error:Unable to modify the parent container element before the 周凡杨 html 解析 error readyState
错误： IE 中"HTML Parsing Error:Unable to modify the parent container element before the child element is closed" 现象：同事之间几个IE 测试情况下，有的报这个错，有的不报。经查询资料后，可归纳以下原因。
java上传 g21121 java
我们在做web项目中通常会遇到上传文件的情况，用struts等框架的会直接用的自带的标签和组件，今天说的是利用servlet来完成上传。我们这里利用到commons-fileupload组件，相关jar包可以取apache官网下载：http://commons.apache.org/ 下面是servlet的代码： //定义一个磁盘文件工厂 DiskFileItemFactory fact
SpringMVC配置学习 510888780 spring mvc
spring MVC配置详解现在主流的Web MVC框架除了Struts这个主力外，其次就是Spring MVC了，因此这也是作为一名程序员需要掌握的主流框架，框架选择多了，应对多变的需求和业务时，可实行的方案自然就多了。不过要想灵活运用Spring MVC来应对大多数的Web开发，就必须要掌握它的配置及原理。　　一、Spring MVC环境搭建：（Spring 2.5.6 + Hi
spring mvc-jfreeChart 柱图(1) 布衣凌宇 jfreechart
第一步：下载jfreeChart包，注意是jfreeChart文件lib目录下的，jcommon-1.0.23.jar和jfreechart-1.0.19.jar两个包即可；第二步：配置web.xml; web.xml代码如下 <servlet> <servlet-name>jfreechart</servlet-nam
我的spring学习笔记13-容器扩展点之PropertyPlaceholderConfigurer aijuans Spring3
PropertyPlaceholderConfigurer是个bean工厂后置处理器的实现，也就是BeanFactoryPostProcessor接口的一个实现。关于BeanFactoryPostProcessor和BeanPostProcessor类似。我会在其他地方介绍。PropertyPlaceholderConfigurer可以将上下文（配置文件）中的属性值放在另一个单独的标准java P
java 线程池使用 Runnable&Callable&Future antlove java thread Runnable callable future
1. 创建线程池 ExecutorService executorService = Executors.newCachedThreadPool(); 2. 执行一次线程，调用Runnable接口实现 Future<?> future = executorService.submit(new DefaultRunnable()); System.out.prin
XML语法元素结构的总结百合不是茶 xml 树结构
1.XML介绍1969年 gml (主要目的是要在不同的机器进行通信的数据规范)1985年 sgml standard generralized markup language1993年 html(www网)1998年 xml extensible markup language
改变eclipse编码格式 bijian1013 eclipse 编码格式
1.改变整个工作空间的编码格式改变整个工作空间的编码格式，这样以后新建的文件也是新设置的编码格式。 Eclipse->window->preferences->General->workspace-
javascript中return的设计缺陷 bijian1013 JavaScript AngularJS
代码1： <script> var gisService = (function(window) { return { name:function () { alert(1); } }; })(this); gisService.name(); &l
【持久化框架MyBatis3八】Spring集成MyBatis3 bit1129 Mybatis3
pom.xml配置 Maven的pom中主要包括： MyBatis MyBatis-Spring Spring MySQL-Connector-Java Druid applicationContext.xml配置 <?xml version="1.0" encoding="UTF-8"?> &
java web项目启动时自动加载自定义properties文件 bitray java Web 监听器相对路径
创建一个类 public class ContextInitListener implements ServletContextListener 使得该类成为一个监听器。用于监听整个容器生命周期的，主要是初始化和销毁的。类创建后要在web.xml配置文件中增加一个简单的监听器配置，即刚才我们定义的类。 <listener> <des
用nginx区分文件大小做出不同响应 ronin47
昨晚和前21v的同事聊天，说到我离职后一些技术上的更新。其中有个给某大客户(游戏下载类)的特殊需求设计，因为文件大小差距很大——估计是大版本和补丁的区别——又走的是同一个域名，而squid在响应比较大的文件时，尤其是初次下载的时候，性能比较差，所以拆成两组服务器，squid服务于较小的文件，通过pull方式从peer层获取，nginx服务于较大的文件，通过push方式由peer层分发同步。外部发布
java-67-扑克牌的顺子.从扑克牌中随机抽5张牌，判断是不是一个顺子，即这5张牌是不是连续的.2-10为数字本身，A为1，J为11，Q为12，K为13，而大 bylijinnan java
package com.ljn.base; import java.util.Arrays; import java.util.Random; public class ContinuousPoker { /** * Q67 扑克牌的顺子从扑克牌中随机抽5张牌，判断是不是一个顺子，即这5张牌是不是连续的。 * 2-10为数字本身，A为1，J为1
翟鸿燊老师语录 ccii 翟鸿燊
一、国学应用智慧TAT之亮剑精神A 1. 角色就是人格就像你一回家的时候，你一进屋里面，你已经是儿子，是姑娘啦，给老爸老妈倒怀水吧，你还觉得你是老总呢？还拿派呢？就像今天一样，你们往这儿一坐，你们之间是什么，同学，是朋友。还有下属最忌讳的就是领导向他询问情况的时候，什么我不知道，我不清楚，该你知道的你凭什么不知道
[光速与宇宙]进行光速飞行的一些问题 comsci 问题
在人类整体进入宇宙时代，即将开展深空宇宙探索之前，我有几个猜想想告诉大家仅仅是猜想。。。未经官方证实 1：要在宇宙中进行光速飞行，必须首先获得宇宙中的航行通行证，而这个航行通行证并不是我们平常认为的那种带钢印的证书，是什么呢？下面我来告诉
oracle undo解析 cwqcwqmax9 oracle
oracle undo解析2012-09-24 09:02:01 我来说两句作者：虫师收藏我要投稿 Undo是干嘛用的？ &nb
java中各种集合的详细介绍 dashuaifu java 集合
一，java中各种集合的关系图 Collection 接口的接口对象的集合 ├ List 子接口 &n
卸载windows服务的方法 dcj3sjt126com windows service
卸载Windows服务的方法在Windows中，有一类程序称为服务，在操作系统内核加载完成后就开始加载。这里程序往往运行在操作系统的底层，因此资源占用比较大、执行效率比较高，比较有代表性的就是杀毒软件。但是一旦因为特殊原因不能正确卸载这些程序了，其加载在Windows内的服务就不容易删除了。即便是删除注册表中的相应项目，虽然不启动了，但是系统中仍然存在此项服务，只是没有加载而已。如果安装其他
Warning: The Copy Bundle Resources build phase contains this target's Info.plist dcj3sjt126com ios xcode
http://developer.apple.com/iphone/library/qa/qa2009/qa1649.html Excerpt: You are getting this warning because you probably added your Info.plist file to your Copy Bundle
2014之C++学习笔记（一） Etwo C++Etwo Etwo iterator 迭代器
已经有很长一段时间没有写博客了，可能大家已经淡忘了Etwo这个人的存在，这一年多以来，本人从事了AS的相关开发工作，但最近一段时间，AS在天朝的没落，相信有很多码农也都清楚，现在的页游基本上达到饱和，手机上的游戏基本被unity3D与cocos占据，AS基本没有容身之处。so。。。最近我并不打算直接转型
js跨越获取数据问题记录 haifengwuch jsonp json Ajax
js的跨越问题，普通的ajax无法获取服务器返回的值。第一种解决方案，通过getson，后台配合方式，实现。 Java后台代码： protected void doPost(HttpServletRequest req, HttpServletResponse resp) throws ServletException, IOException { String ca
蓝色jQuery导航条 ini JavaScript html jquery Web html5
效果体验：http://keleyi.com/keleyi/phtml/jqtexiao/39.htmHTML文件代码： <!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <title>jQuery鼠标悬停上下滑动导航条 - 柯乐义<
linux部署jdk,tomcat,mysql kerryg jdk tomcat linux mysql
1、安装java环境jdk: 一般系统都会默认自带的JDK,但是不太好用，都会卸载了，然后重新安装。 1.1）、卸载：（rpm -qa :查询已经安装哪些软件包； rmp -q 软件包：查询指定包是否已
DOMContentLoaded VS onload VS onreadystatechange mutongwu jquery js
1. DOMContentLoaded 在页面html、script、style加载完毕即可触发，无需等待所有资源（image/iframe）加载完毕。（IE9+） 2. onload是最早支持的事件，要求所有资源加载完毕触发。 3. onreadystatechange 开始在IE引入，后来其它浏览器也有一定的实现。涉及以下 document , applet, embed, fra
sql批量插入数据 qifeifei 批量插入
hi，自己在做工程的时候，遇到批量插入数据的数据修复场景。我的思路是在插入前准备一个临时表，临时表的整理就看当时的选择条件了，临时表就是要插入的数据集，最后再批量插入到数据库中。 WITH tempT AS ( SELECT item_id AS combo_id, item_id, now() AS create_date FROM a
log4j打印日志文件如何实现相对路径到项目工程下 thinkfreer Web log4j 应用服务器日志
最近为了实现统计一个网站的访问量，记录用户的登录信息，以方便站长实时了解自己网站的访问情况，选择了Apache 的log4j,但是在选择相对路径那块卡主了，X度了好多方法(其实大多都是一样的内用，还一个字都不差的)，都没有能解决问题，无奈搞了2天终于解决了，与大家分享一下需求：用户登录该网站时，把用户的登录名,ip,时间。统计到一个txt文档里，以方便其他系统调用此txt。项目名
linux下mysql-5.6.23.tar.gz安装与配置笑我痴狂 mysql linux unix
1.卸载系统默认的mysql [root@localhost ~]# rpm -qa | grep mysql mysql-libs-5.1.66-2.el6_3.x86_64 mysql-devel-5.1.66-2.el6_3.x86_64 mysql-5.1.66-2.el6_3.x86_64 [root@localhost ~]# rpm -e mysql-libs-5.1

YOLOv5 第Y6周 模型改进

你可能感兴趣的:(YOLO)

YOLOv5 第Y6周模型改进