Yolov5 Detect 的前向传播过程

发布时间：2023年12月22日

模型的搭建过程

数据的导入过程

数据的前向推理过程

Detect中的处理过程

?网络结构

模型的搭建过程

其实都在训练好的pt文件中加载进来的。所以推理时没有搭建整个网络的类实例对象过程,但是相应的模块的类的定义都在common.py文件中定义的，包括各个模块的结构，前向传播过程。

。pt文件中还包含了数据应有的类别标签信息

model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
1. model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse)    # common.py--356
2. model = Ensemble()   #  experiments.py--77  nn.ModuleList对象
3. ckpt = torch.load(attempt_download(w), map_location='cpu')   # 从pt加载模型本身，注意ckpt是 DetectionModel 类对象
4. model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval())  # model in eval mode  主要是将训练时得到的模型中 Conv2d 和 Bn 层混合到了一起

可以结合着后面末尾打印的网络结构参数，各个基本模块的构成以及前向传播流程如下所示

基本模块整合完毕后，可以结合下面的前向推理过程推导出整个模型的结构，并且self.add=True

数据的导入过程

YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`

图片和视频都能处理。将图片和视频放在同一路径下它也能自动处理。

dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)  #  detect.py -- 115

LoadImages单独定义的类对象，没有继承任何父类。最终加载输入图片。

数据的前向推理过程

1. pred = model(im, augment=augment, visualize=visualize)  # detect.py -- 132
2. y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)  # common.py--527
3. return self._forward_once(x, profile, visualize)  # yolo.py--209

前向推理

 def _forward_once(self, x, profile=False, visualize=False):
        y, dt = [], []  # outputs
        for m in self.model:
            if m.f != -1:  # if not from previous layer
                print('number{}, m.f is {}'.format(m.i, m.f))
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
        return x  # to --209

?打印m.f!=-1时的情况，如下所示

number12, m.f is [-1, 6]
number16, m.f is [-1, 4]
number19, m.f is [-1, 14]
number22, m.f is [-1, 10]
number24, m.f is [17, 20, 23]

其中number 是该模块的序号，对应打印的网络结构中的括号中的序号（0）~（24），总体的流程为

Detect中的处理过程

?从上图中可以看到，送入Detect头中的输入包含3个尺度。yolov5是基于anchor的检测器，它事先对锚框设定了一些参数，在yaml文件中

anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

?上述的锚框是在输入的尺度下的锚框的参数设定，映射到特征图上的参数设定需要除以各个尺度下的步长，其中的参数每一对为anchor的w和h。

tensor([[[ 1.25000,  1.62500],  # 例如 10/8， 13/8
         [ 2.00000,  3.75000],  # 16/8  ， 30/8
         [ 4.12500,  2.87500]],

        [[ 1.87500,  3.81250],
         [ 3.87500,  2.81250],
         [ 3.68750,  7.43750]],

        [[ 3.62500,  2.81250],
         [ 4.87500,  6.18750],
         [11.65625, 10.18750]]])

    def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
        d = self.anchors[i].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape  (1,3,4,4,2)
        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)  # [0,1,2,3]
        yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x)  # torch>=0.7 compatibility
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5  anchor 的中心点坐标，加补偿了
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)  # （1，3，4，4，2）
        return grid, anchor_grid

?Detect每一个尺度的输出经过sigmoid映射到0~1.其中的远离参考这里

xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)  # 按第4通道划分 (1,3,4,4,2) (1,3,4,4,2) (1,3,4,4,81)
xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
y = torch.cat((xy, wh, conf), 4)

根据上式，逆推标签与groundTruth的关系，为

$\frac{?{?{X_g}{Y_g} - {X_a}{Y_a}}}{2} = {X_l}{Y_l}$

$\frac{1}{2}\sqrt {\frac{?{?{W_g}{H_g}}}{?{?{W_a}{H_a}}}} = {W_l}{H_l}$

至此，最终的返回值为

return x if self.training else (torch.cat(z, 1), ) if self.export else (torch.cat(z, 1), x)  # yolo.py--79

?这里的 self.export=False,所以返回

(torch.cat(z, 1), x)

得到预测后，经NMS处理，筛选过程

1、 根据置信度阈值筛选， 即可能是包围目标的矩形框  
    xc = prediction[..., 4] > conf_thres  # candidates  挑选置信度大于阈值的
    x = x[xc[xi]]
2、 计算新的用来比较的分类得分  
    x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf
3、 预测的候选框坐标转换成角坐标形式
    box = xywh2xyxy(x[:, :4])  # center_x, center_y, width, height) to (x1, y1, x2, y2)
4、 对之前按置信度筛选后的，拿出每个目标的分类得分最大值的索引，即每个目标的类别
    conf, j = x[:, 5:mi].max(1, keepdim=True)
5、 矩形框角坐标，分类得分最大值，类别序号拼接一起，并挑选分类得分大于阈值的
    x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]
6、 按分类得分排序
    x = x[x[:, 4].argsort(descending=True)[:max_nms]]
7、 按不同的类别根据IoU进行筛选，先把box按不同的类别映射到不同的尺度范围
    c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
    boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
8、 进行NMS
    i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
9、 返回最终的预测结果
    output[xi] = x[i]  #  (n, 6)  n为目标数， 6 为步骤5中的拼接

接下来就是在原图上标注预测结果，以及保存结果。

?网络结构

DetectionModel(
  (model): Sequential(
    (0): Conv(
      (conv): Conv2d(3, 80, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2))
      (act): SiLU(inplace=True)
    )
    (1): Conv(
      (conv): Conv2d(80, 160, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (2): C3(
      (cv1): Conv(
        (conv): Conv2d(160, 80, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(160, 80, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (3): Conv(
      (conv): Conv2d(160, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (4): C3(
      (cv1): Conv(
        (conv): Conv2d(320, 160, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(320, 160, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (4): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (5): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (6): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (7): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (5): Conv(
      (conv): Conv2d(320, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (6): C3(
      (cv1): Conv(
        (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (4): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (5): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (6): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (7): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (8): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (9): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (10): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (11): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (7): Conv(
      (conv): Conv2d(640, 1280, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (8): C3(
      (cv1): Conv(
        (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (9): SPPF(
      (cv1): Conv(
        (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(2560, 1280, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
    )
    (10): Conv(
      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
      (act): SiLU(inplace=True)
    )
    (11): Upsample(scale_factor=2.0, mode='nearest')
    (12): Concat()
    (13): C3(
      (cv1): Conv(
        (conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (14): Conv(
      (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1))
      (act): SiLU(inplace=True)
    )
    (15): Upsample(scale_factor=2.0, mode='nearest')
    (16): Concat()
    (17): C3(
      (cv1): Conv(
        (conv): Conv2d(640, 160, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(640, 160, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (18): Conv(
      (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (19): Concat()
    (20): C3(
      (cv1): Conv(
        (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (21): Conv(
      (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (22): Concat()
    (23): C3(
      (cv1): Conv(
        (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (24): Detect(
      (m): ModuleList(
        (0): Conv2d(320, 255, kernel_size=(1, 1), stride=(1, 1))
        (1): Conv2d(640, 255, kernel_size=(1, 1), stride=(1, 1))
        (2): Conv2d(1280, 255, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
)

ckpt中的内容

其中ckpt中的model

Sequential(
  (0): Conv(
    (conv): Conv2d(3, 80, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2), bias=False)
    (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (1): Conv(
    (conv): Conv2d(80, 160, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (2): C3(
    (cv1): Conv(
      (conv): Conv2d(160, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(160, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (3): Conv(
    (conv): Conv2d(160, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (4): C3(
    (cv1): Conv(
      (conv): Conv2d(320, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(320, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (4): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (5): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (6): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (7): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (5): Conv(
    (conv): Conv2d(320, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (6): C3(
    (cv1): Conv(
      (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (4): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (5): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (6): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (7): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (8): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (9): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (10): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (11): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (7): Conv(
    (conv): Conv2d(640, 1280, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(1280, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (8): C3(
    (cv1): Conv(
      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(1280, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1280, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (9): SPPF(
    (cv1): Conv(
      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(2560, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1280, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
  )
  (10): Conv(
    (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (11): Upsample(scale_factor=2.0, mode='nearest')
  (12): Concat()
  (13): C3(
    (cv1): Conv(
      (conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (14): Conv(
    (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (15): Upsample(scale_factor=2.0, mode='nearest')
  (16): Concat()
  (17): C3(
    (cv1): Conv(
      (conv): Conv2d(640, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(640, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (18): Conv(
    (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (19): Concat()
  (20): C3(
    (cv1): Conv(
      (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(320, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (21): Conv(
    (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
    (act): SiLU(inplace=True)
  )
  (22): Concat()
  (23): C3(
    (cv1): Conv(
      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv2): Conv(
      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (cv3): Conv(
      (conv): Conv2d(1280, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1280, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (3): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(640, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (cv2): Conv(
          (conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(640, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
  )
  (24): Detect(
    (m): ModuleList(
      (0): Conv2d(320, 255, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(640, 255, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(1280, 255, kernel_size=(1, 1), stride=(1, 1))
    )
  )
)

文章来源:https://blog.csdn.net/allrubots/article/details/135090126
本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若内容造成侵权/违法违规/事实不符，请联系我的编程经验分享网邮箱：chenni525@qq.com进行投诉反馈，一经查实，立即删除！