Spaces:
Sleeping
Sleeping
File size: 4,589 Bytes
591ba45 |
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 |
import torch.nn as nn
class ResidualBlock(nn.Module):
def __init__(self, in_planes, planes, norm_fn="group", stride=1):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(
in_planes, planes, kernel_size=3, padding=1, stride=stride
)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1)
self.relu = nn.ReLU(inplace=True)
num_groups = planes // 8
if norm_fn == "batch":
self.norm1 = nn.BatchNorm2d(planes)
self.norm2 = nn.BatchNorm2d(planes)
if not stride == 1:
self.norm3 = nn.BatchNorm2d(planes)
elif norm_fn == "instance":
self.norm1 = nn.InstanceNorm2d(planes)
self.norm2 = nn.InstanceNorm2d(planes)
if not stride == 1:
self.norm3 = nn.InstanceNorm2d(planes)
if stride == 1:
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 BottleneckBlock(nn.Module):
def __init__(self, in_planes, planes, norm_fn="group", stride=1):
super(BottleneckBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes // 4, kernel_size=1, padding=0)
self.conv2 = nn.Conv2d(
planes // 4, planes // 4, kernel_size=3, padding=1, stride=stride
)
self.conv3 = nn.Conv2d(planes // 4, planes, kernel_size=1, padding=0)
self.relu = nn.ReLU(inplace=True)
if norm_fn == "batch":
self.norm1 = nn.BatchNorm2d(planes // 4)
self.norm2 = nn.BatchNorm2d(planes // 4)
self.norm3 = nn.BatchNorm2d(planes)
if not stride == 1:
self.norm4 = nn.BatchNorm2d(planes)
elif norm_fn == "instance":
self.norm1 = nn.InstanceNorm2d(planes // 4)
self.norm2 = nn.InstanceNorm2d(planes // 4)
self.norm3 = nn.InstanceNorm2d(planes)
if not stride == 1:
self.norm4 = nn.InstanceNorm2d(planes)
if stride == 1:
self.downsample = None
else:
self.downsample = nn.Sequential(
nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride), self.norm4
)
def forward(self, x):
y = x
y = self.relu(self.norm1(self.conv1(y)))
y = self.relu(self.norm2(self.conv2(y)))
y = self.relu(self.norm3(self.conv3(y)))
if self.downsample is not None:
x = self.downsample(x)
return self.relu(x + y)
class BasicEncoder(nn.Module):
def __init__(self, output_dim=128, norm_fn="batch", dropout=0.0):
super(BasicEncoder, self).__init__()
self.norm_fn = norm_fn
if self.norm_fn == "batch":
self.norm1 = nn.BatchNorm2d(64)
elif self.norm_fn == "instance":
self.norm1 = nn.InstanceNorm2d(64)
self.conv1 = nn.Conv2d(3, 80, kernel_size=7, stride=2, padding=3)
self.relu1 = nn.ReLU(inplace=True)
self.in_planes = 80
self.layer1 = self._make_layer(80, stride=1)
self.layer2 = self._make_layer(160, stride=2)
self.layer3 = self._make_layer(240, stride=2)
# output convolution
self.conv2 = nn.Conv2d(240, output_dim, kernel_size=1)
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):
layer1 = ResidualBlock(self.in_planes, dim, self.norm_fn, stride=stride)
layer2 = ResidualBlock(dim, dim, self.norm_fn, stride=1)
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)
x = self.layer2(x)
x = self.layer3(x)
x = self.conv2(x)
return x
|