File size: 6,794 Bytes
250a0ca |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
import torch
from torch import nn
class BasicBlock(nn.Module):
"""Basic building block for ResNet-18/34"""
expansion = 1
def __init__(self, in_channels: int, out_channels: int, stride: int = 1, downsample: nn.Module = None):
super().__init__()
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)
self.downsample = downsample
def forward(self, x: torch.Tensor) -> torch.Tensor:
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Bottleneck(nn.Module):
"""Bottleneck building block for ResNet-50/101/152"""
expansion = 4
def __init__(self, in_channels: int, out_channels: int, stride: int = 1, downsample: nn.Module = None):
super().__init__()
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channels)
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channels)
self.conv3 = nn.Conv2d(out_channels, out_channels * self.expansion, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(out_channels * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def forward(self, x: torch.Tensor) -> torch.Tensor:
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
"""ResNet model for image classification
Supports ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152
Adapted for small images like MedMNIST (28x28)
"""
def __init__(
self,
block: type[BasicBlock | Bottleneck],
layers: list[int],
num_classes: int = 11,
in_channels: int = 1,
):
super().__init__()
self.in_channels = 64
# Initial convolution layer (adapted for small 28x28 images)
self.conv1 = nn.Conv2d(in_channels, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
# Removed maxpool for small images
# ResNet layers
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
# Global average pooling and classifier
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
# Initialize weights
self._initialize_weights()
def _make_layer(self, block: type[BasicBlock | Bottleneck], out_channels: int, blocks: int, stride: int = 1) -> nn.Sequential:
downsample = None
if stride != 1 or self.in_channels != out_channels * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.in_channels, out_channels * block.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(out_channels * block.expansion),
)
layers = []
layers.append(block(self.in_channels, out_channels, stride, downsample))
self.in_channels = out_channels * block.expansion
for _ in range(1, blocks):
layers.append(block(self.in_channels, out_channels))
return nn.Sequential(*layers)
def _initialize_weights(self):
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.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
def resnet18(num_classes: int = 11, in_channels: int = 1) -> ResNet:
"""ResNet-18 model
Args:
num_classes: Number of output classes (default: 11 for organamnist)
in_channels: Number of input channels (default: 1 for grayscale)
Returns:
ResNet-18 model
"""
return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes, in_channels=in_channels)
def resnet50(num_classes: int = 11, in_channels: int = 1) -> ResNet:
"""ResNet-50 model
Args:
num_classes: Number of output classes (default: 11 for organamnist)
in_channels: Number of input channels (default: 1 for grayscale)
Returns:
ResNet-50 model
"""
return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_channels=in_channels)
# Keep the old Model class for backward compatibility
class Model(nn.Module):
"""Just a dummy model to show how to structure your code"""
def __init__(self):
super().__init__()
self.layer = nn.Linear(1, 1)
def forward(self, x: torch.Tensor) -> torch.Tensor:
return self.layer(x)
if __name__ == "__main__":
# Test ResNet-18
model18 = resnet18(num_classes=11, in_channels=1)
x = torch.rand(4, 1, 28, 28) # Batch of 4 grayscale 28x28 images
output = model18(x)
print(f"ResNet-18 output shape: {output.shape}") # Should be [4, 11]
# Test ResNet-50
model50 = resnet50(num_classes=11, in_channels=1)
output50 = model50(x)
print(f"ResNet-50 output shape: {output50.shape}") # Should be [4, 11]
# Count parameters
params18 = sum(p.numel() for p in model18.parameters())
params50 = sum(p.numel() for p in model50.parameters())
print(f"ResNet-18 parameters: {params18:,}")
print(f"ResNet-50 parameters: {params50:,}")
|