yolov5/models/common.py

# This file contains modules common to various models


import torch.nn.functional as F

from utils.utils import *


def DWConv(c1, c2, k=1, s=1, act=True):  # depthwise convolution
    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)


class Conv(nn.Module):  # standard convolution
    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
        super(Conv, self).__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, k // 2, groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.LeakyReLU(0.1, inplace=True) if act else nn.Identity()

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))


class Bottleneck(nn.Module):
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super(Bottleneck, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class BottleneckLight(nn.Module):
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super(BottleneckLight, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = nn.Conv2d(c_, c2, 3, 1, 3 // 2, groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.LeakyReLU(0.1, inplace=True)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return self.act(self.bn(x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))))


class BottleneckCSP(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super(BottleneckCSP, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
        self.cv4 = Conv(c2, c2, 1, 1)
        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
        self.act = nn.LeakyReLU(0.1, inplace=True)
        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])

    def forward(self, x):
        y1 = self.cv3(self.m(self.cv1(x)))
        y2 = self.cv2(x)
        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))


class Narrow(nn.Module):
    def __init__(self, c1, c2, shortcut=True, g=1):  # ch_in, ch_out, shortcut, groups
        super(Narrow, self).__init__()
        c_ = c2 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class Origami(nn.Module):  # 5-side layering
    def forward(self, x):
        y = F.pad(x, [1, 1, 1, 1])
        return torch.cat([x, y[..., :-2, 1:-1], y[..., 1:-1, :-2], y[..., 2:, 1:-1], y[..., 1:-1, 2:]], 1)


class ConvPlus(nn.Module):  # standard convolution
    def __init__(self, c1, c2, k=3, s=1, g=1, bias=True):  # ch_in, ch_out, kernel, stride, groups
        super(ConvPlus, self).__init__()
        self.cv1 = nn.Conv2d(c1, c2, (k, 1), s, (k // 2, 0), groups=g, bias=bias)
        self.cv2 = nn.Conv2d(c1, c2, (1, k), s, (0, k // 2), groups=g, bias=bias)

    def forward(self, x):
        return self.cv1(x) + self.cv2(x)


class SPP(nn.Module):  # Spatial pyramid pooling layer used in YOLOv3-SPP
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super(SPP, self).__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])

    def forward(self, x):
        x = self.cv1(x)
        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))


class Flatten(nn.Module):
    # Use after nn.AdaptiveAvgPool2d(1) to remove last 2 dimensions
    def forward(self, x):
        return x.view(x.size(0), -1)


class Focus(nn.Module):
    # Focus wh information into c-space
    def __init__(self, c1, c2, k=1):
        super(Focus, self).__init__()
        self.conv = Conv(c1 * 4, c2, k, 1)

    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))


class Concat(nn.Module):
    # Concatenate a list of tensors along dimension
    def __init__(self, dimension=1):
        super(Concat, self).__init__()
        self.d = dimension

    def forward(self, x):
        return torch.cat(x, self.d)


class MixConv2d(nn.Module):
    # Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
        super(MixConv2d, self).__init__()
        groups = len(k)
        if equal_ch:  # equal c_ per group
            i = torch.linspace(0, groups - 1E-6, c2).floor()  # c2 indices
            c_ = [(i == g).sum() for g in range(groups)]  # intermediate channels
        else:  # equal weight.numel() per group
            b = [c2] + [0] * groups
            a = np.eye(groups + 1, groups, k=-1)
            a -= np.roll(a, 1, axis=1)
            a *= np.array(k) ** 2
            a[0] = 1
            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b

        self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.LeakyReLU(0.1, inplace=True)

    def forward(self, x):
        return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))