YOLOv5白皮书-第Y6周：模型改进

最新推荐文章于 2024-05-11 09:29:21 发布

sdnugao

最新推荐文章于 2024-05-11 09:29:21 发布

阅读量561

点赞数

文章标签： python 人工智能深度学习

本文链接：https://blog.csdn.net/a52022920/article/details/128583949

版权

改进模型如下:
在这里插入图片描述
y5的模型如下：

可以看到区别是模型的 4：c3*2变成了c2*2
然后是模型的6和7去掉了。

1. yolov5s.yaml中修改

之前的

# 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]],
   [-1, 3, C2, [128]], # todo
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]
# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-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 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

改后的

# y6

# 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]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]], #4  todo: 修改为c2*2
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9 todo：修改参数[-1, 1, SPPF, [1024, 5]]：层数变为7
  ]


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

   [-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 (P3/8-small)

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

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

   [[15, 18, 21], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

2. 运行

python train.py --img 900 --batch 2 --epoch 2 --data paper_data/ab.yaml --cfg models/yolov5s.yaml --weights yolov5s.pt


train: weights=yolov5s.pt, cfg=models/yolov5s.yaml, data=paper_data/ab.yaml, hyp=data\hyps\hyp.scratch-low.yaml, epochs=2, 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, projec
t=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  2022-12-7 Python-3.9.15 torch-1.13.0+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
ClearML: run 'pip install clearml' to automatically track, visualize and remotely train YOLOv5  in ClearML
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.C3                        [128, 128, 2]
  5                -1  1    590848  models.common.Conv                      [128, 512, 3, 2]
  6                -1  1   1182720  models.common.C3                        [512, 512, 1]
  7                -1  1    656896  models.common.SPPF                      [512, 512, 5]
  8                -1  1   1180160  models.common.Conv                      [512, 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    427520  models.common.C3                        [768, 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, 6634129 parameters, 6634129 gradients, 19.4 GFLOPs

Transferred 90/289 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 E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master\paper_data\train... 180 images, 0 backgrounds, 0
train: WARNING  Cache directory E:\doc\1.\3.\21.365\y2\yolov5-master\paper_data is not writeable: [WinError 183] : 'E:\\doc\\1.\
\3.\\21.365\\y2\\yolov5-master\\paper_data\\train.cache.npy' -> 'E:\\doc\\1.\\3.\\21.365\\y2\\yolov5-master\\paper_data\\train.cache'
val: Scanning E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master\paper_data\val.cache... 20 images, 0 backgrounds, 

AutoAnchor: 4.82 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset
Plotting labels to runs\train\exp27\labels.jpg...
Image sizes 928 train, 928 val
Using 2 dataloader workers
Logging results to runs\train\exp27
Starting training for 2 epochs...

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
        0/1         0G     0.1104    0.06085    0.04321          9        928:   0%|          | 0/90 [00:02<?, ?it/s]WARNING  Te
nsorBoard graph visualization failure Sizes of tensors must match except in dimension 1. Expected size 58 but got size 57 for tensor number 1 in the list.
        0/1         0G     0.1057    0.06416    0.04225         11        928: 100%|██████████| 90/90 [03:06<00:00,  2.08s/it]
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:07<00:00,  1 
                   all         20         60   0.000126     0.0375   7.81e-05   1.72e-05

YOLOv5s summary: 132 layers, 6626161 parameters, 0 gradients, 19.2 GFLOPs
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:07<00:00,  1 
YOLOv5s summary: 132 layers, 6626161 parameters, 0 gradients, 19.2 GFLOPs
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:07<00:00,  1 
                   all         20         60    0.00197      0.194    0.00162   0.000497
                banana         20         16    0.00302      0.188    0.00181   0.000712
           snake fruit         20         20   0.000484       0.05   0.000313   3.13e-05
          dragon fruit         20         11          0          0          0          0
             pineapple         20         13    0.00439      0.538    0.00435    0.00125
Results saved to runs\train\exp27