yolov5+csl旋转目标检测代码解析3
本篇主要记录学习yolov5+csl旋转目标检测的原理，主要是探究代码中pred的生成过程。参考知乎 略略略 https://zhuanlan.zhihu.com/p/358441134； yangxue https://zhuanlan.zhihu.com/p/111493759
一、debug记录
首先train.py这里改变图片尺寸（/255）作归一化，给tensor处理，同时改为浮点类型，shape不变
这里把图片（图片shape[b, 3, height, width], RGB）喂给网络,
然后在forward里迭代网络的各个层（卷积、C3等）
经过第一层卷积：
Conv(
(conv): Conv2d(3, 48, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
之后x的shape变成如图（2， 48， 512，512）
第二层网络结构：经过第二层网络之后的x的shape:(2, 96, 256, 256)
Conv(
(conv): Conv2d(48, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
依此类推，需要注意的是在第12层concat层，将当前层（即上一层输出的x）和m.f参数指定的之前保存的某一层结合作list
在第16层的时候同样，将当前层和m.f参数指定的之前保存的某一层结合作list，下面还有concat层，不作记录
共25层，下面是最后一层detect层之前，可以看到，过程中根据self.save参数保存了部分层的输出，并且根据m.f参数，指定当前层的输入是单一的上一层输出还是和之前层组成的list
比如detect层的m.f参数是如下：
则意味着要把y中这几个层的输出联合成list
detect层内容：
Detect(
(m): ModuleList(
(0): Conv2d(192, 603, kernel_size=(1, 1), stride=(1, 1))
(1): Conv2d(384, 603, kernel_size=(1, 1), stride=(1, 1))
(2): Conv2d(768, 603, kernel_size=(1, 1), stride=(1, 1))
)
)
分别对三个尺度的tensor作卷积，经过detect层之后三个尺度的输出：
1.detect层细节处理
下面是detect层处理的一些细节：
首先进入forward，按lawyer（3层）操作，经过第一次卷积之后x[0]变成如图：
这里把x[i]进行重组（我的理解相当于一个线性层，但不完全一样）：
201是self.no参数，在detect类中定义（如下图），代表着[16个类别，cx,cy,l,s,theta，180个gaussian_theta_labels]，值得注意的是，这201个参数是相对于一个anchor来说的。这里2是bz，3是每一个grid负责的anchor数量，即一个grid产生3个anchor，然后每一张图片，按3个尺度，分成128×128，64×64，32×32个grid。
二、网络结构
这是self.model全部内容，共25层，最后一层detect层：
Sequential(
(0): Conv(
(conv): Conv2d(3, 48, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): Conv(
(conv): Conv2d(48, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(2): C3(
(cv1): Conv(
(conv): Conv2d(96, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(3): Conv(
(conv): Conv2d(96, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(4): C3(
(cv1): Conv(
(conv): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(3): Bottleneck(
(cv1): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(5): Conv(
(conv): Conv2d(192, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(6): C3(
(cv1): Conv(
(conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(3): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(4): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(5): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(7): Conv(
(conv): Conv2d(384, 768, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(8): C3(
(cv1): Conv(
(conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(9): SPPF(
(cv1): Conv(
(conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(1536, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(768, 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(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, 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(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(14): Conv(
(conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, 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(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(18): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(19): Concat()
(20): C3(
(cv1): Conv(
(conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(21): Conv(
(conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(22): Concat()
(23): C3(
(cv1): Conv(
(conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(24): Detect(
(m): ModuleList(
(0): Conv2d(192, 603, kernel_size=(1, 1), stride=(1, 1))
(1): Conv2d(384, 603, kernel_size=(1, 1), stride=(1, 1))
(2): Conv2d(768, 603, kernel_size=(1, 1), stride=(1, 1))
)
)
)
本博客所有文章除特别声明外，均采用 CC BY-NC-SA 4.0 许可协议。转载请注明来自 不听话的兔子君！