参数量计算：
(输入通道*w)*(输出通道*w)*k^2+(输出通道*w)*2

w是模型缩放里面的width

- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2

输出通道c2=64,k=3,s=2

P1/2 特征图变小一半

先定义算子层

再搭一个forward前向传播

class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""

    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including ac