Spaces:
Sleeping
Sleeping
File size: 3,090 Bytes
721508a |
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 |
import torch
from torch import nn
class ResNet18(nn.Module):
def __init__(self, in_channels: int, num_classes: int):
super().__init__()
self.initial_conv = nn.Conv2d(
in_channels=in_channels,
out_channels=64,
kernel_size=7,
stride=2,
padding=3,
bias=False,
)
self.bn = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.max_pool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = nn.Sequential(BasicBlock(64, 64), BasicBlock(64, 64))
self.layer2 = nn.Sequential(
BasicBlock(64, 128, stride=2, downsample=self._downsample(64, 128)),
BasicBlock(128, 128),
)
self.layer3 = nn.Sequential(
BasicBlock(128, 256, stride=2, downsample=self._downsample(128, 256)),
BasicBlock(256, 256),
)
self.layer4 = nn.Sequential(
BasicBlock(256, 512, stride=2, downsample=self._downsample(256, 512)),
BasicBlock(512, 512),
)
self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
self.drop = nn.Dropout(0.15)
self.flatten = nn.Flatten(1)
self.fc = nn.Linear(512, num_classes)
@staticmethod
def _downsample(in_channels: int, out_channels: int) -> nn.Sequential:
return nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=2, bias=False),
nn.BatchNorm2d(out_channels),
)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.initial_conv(x)
x = self.bn(x)
x = self.relu(x)
x = self.max_pool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avg_pool(x)
x = self.drop(x) # because linear layers tends to overfit more
x = self.flatten(x)
x = self.fc(x)
return x
class BasicBlock(nn.Module):
def __init__(
self,
in_channels: int,
out_channels: int,
stride: int = 1,
downsample: nn.Module = None,
):
super().__init__()
self.downsample = downsample
self.conv1 = nn.Conv2d(
in_channels,
out_channels,
kernel_size=3,
stride=stride,
padding=1,
bias=False,
)
self.bn1 = nn.BatchNorm2d(out_channels)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(
out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False
)
self.bn2 = nn.BatchNorm2d(out_channels)
def forward(self, x: torch.Tensor) -> torch.Tensor:
identity = x
output = self.conv1(x)
output = self.bn1(output)
output = self.relu(output)
output = self.conv2(output)
output = self.bn2(output)
if self.downsample is not None:
identity = self.downsample(x)
output += identity
output = self.relu(output)
return output
|