Spaces:
Sleeping
Sleeping
| import torch | |
| import torch.nn as nn | |
| import torchvision.models as models | |
| class Bottleneck(nn.Module): | |
| expansion = 4 | |
| def __init__(self, in_channels, out_channels, stride=1, downsample=None): | |
| super(Bottleneck, self).__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): | |
| 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 ResNet50(nn.Module): | |
| def __init__(self, num_classes=1000): | |
| super(ResNet50, self).__init__() | |
| self.in_channels = 64 | |
| # Initial layers | |
| self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) | |
| self.bn1 = nn.BatchNorm2d(64) | |
| self.relu = nn.ReLU(inplace=True) | |
| self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) | |
| # Residual layers | |
| self.layer1 = self._make_layer(64, 3) | |
| self.layer2 = self._make_layer(128, 4, stride=2) | |
| self.layer3 = self._make_layer(256, 6, stride=2) | |
| self.layer4 = self._make_layer(512, 3, stride=2) | |
| # Classification head | |
| self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) | |
| self.fc = nn.Linear(512 * Bottleneck.expansion, num_classes) | |
| # Weight initialization | |
| self._initialize_weights() | |
| def _make_layer(self, out_channels, blocks, stride=1): | |
| downsample = None | |
| if stride != 1 or self.in_channels != out_channels * Bottleneck.expansion: | |
| downsample = nn.Sequential( | |
| nn.Conv2d(self.in_channels, out_channels * Bottleneck.expansion, | |
| kernel_size=1, stride=stride, bias=False), | |
| nn.BatchNorm2d(out_channels * Bottleneck.expansion), | |
| ) | |
| layers = [] | |
| layers.append(Bottleneck(self.in_channels, out_channels, stride, downsample)) | |
| self.in_channels = out_channels * Bottleneck.expansion | |
| for _ in range(1, blocks): | |
| layers.append(Bottleneck(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): | |
| x = self.conv1(x) | |
| x = self.bn1(x) | |
| x = self.relu(x) | |
| x = self.maxpool(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 create_model(num_classes, pretrained=False): | |
| """ | |
| Create a ResNet-50 model | |
| Args: | |
| num_classes: Number of output classes | |
| pretrained: Whether to use pretrained weights from ImageNet | |
| """ | |
| # Load model with or without pretrained weights | |
| model = models.resnet50(pretrained=pretrained) | |
| # Modify the final layer for our number of classes | |
| num_ftrs = model.fc.in_features | |
| model.fc = nn.Linear(num_ftrs, num_classes) | |
| return model |