Yolov5 Detect 的前向传播过程
目录
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 -- 115LoadImages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_gridDetect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
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))
)
)
)