File size: 5,933 Bytes
1e84a23 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
# 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)))
|