File size: 4,226 Bytes
5189ac9 |
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 |
import torch.nn as nn
from .trident_conv import MultiScaleTridentConv
class ResidualBlock(nn.Module):
def __init__(
self,
in_planes,
planes,
norm_layer=nn.InstanceNorm2d,
stride=1,
dilation=1,
):
super().__init__()
self.conv1 = nn.Conv2d(
in_planes,
planes,
kernel_size=3,
dilation=dilation,
padding=dilation,
stride=stride,
bias=False,
)
self.conv2 = nn.Conv2d(
planes, planes, kernel_size=3, dilation=dilation, padding=dilation, bias=False
)
self.relu = nn.ReLU(inplace=True)
self.norm1 = norm_layer(planes)
self.norm2 = norm_layer(planes)
if not stride == 1 or in_planes != planes:
self.norm3 = norm_layer(planes)
if stride == 1 and in_planes == planes:
self.downsample = None
else:
self.downsample = nn.Sequential(
nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride), self.norm3
)
def forward(self, x):
y = x
y = self.relu(self.norm1(self.conv1(y)))
y = self.relu(self.norm2(self.conv2(y)))
if self.downsample is not None:
x = self.downsample(x)
return self.relu(x + y)
class CNNEncoder(nn.Module):
def __init__(
self,
output_dim=128,
norm_layer=nn.InstanceNorm2d,
num_output_scales=1,
**kwargs,
):
super().__init__()
self.num_branch = num_output_scales
feature_dims = [64, 96, 128]
self.conv1 = nn.Conv2d(
3, feature_dims[0], kernel_size=7, stride=2, padding=3, bias=False
) # 1/2
self.norm1 = norm_layer(feature_dims[0])
self.relu1 = nn.ReLU(inplace=True)
self.in_planes = feature_dims[0]
self.layer1 = self._make_layer(feature_dims[0], stride=1, norm_layer=norm_layer) # 1/2
self.layer2 = self._make_layer(feature_dims[1], stride=2, norm_layer=norm_layer) # 1/4
# highest resolution 1/4 or 1/8
stride = 2 if num_output_scales == 1 else 1
self.layer3 = self._make_layer(
feature_dims[2],
stride=stride,
norm_layer=norm_layer,
) # 1/4 or 1/8
self.conv2 = nn.Conv2d(feature_dims[2], output_dim, 1, 1, 0)
if self.num_branch > 1:
if self.num_branch == 4:
strides = (1, 2, 4, 8)
elif self.num_branch == 3:
strides = (1, 2, 4)
elif self.num_branch == 2:
strides = (1, 2)
else:
raise ValueError
self.trident_conv = MultiScaleTridentConv(
output_dim,
output_dim,
kernel_size=3,
strides=strides,
paddings=1,
num_branch=self.num_branch,
)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
elif isinstance(m, (nn.BatchNorm2d, nn.InstanceNorm2d, nn.GroupNorm)):
if m.weight is not None:
nn.init.constant_(m.weight, 1)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
def _make_layer(self, dim, stride=1, dilation=1, norm_layer=nn.InstanceNorm2d):
layer1 = ResidualBlock(
self.in_planes, dim, norm_layer=norm_layer, stride=stride, dilation=dilation
)
layer2 = ResidualBlock(dim, dim, norm_layer=norm_layer, stride=1, dilation=dilation)
layers = (layer1, layer2)
self.in_planes = dim
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.norm1(x)
x = self.relu1(x)
x = self.layer1(x) # 1/2
x = self.layer2(x) # 1/4
x = self.layer3(x) # 1/8 or 1/4
x = self.conv2(x)
if self.num_branch > 1:
out = self.trident_conv([x] * self.num_branch) # high to low res
else:
out = [x]
return out
|