| import torch |
| from torch import Tensor |
| import torch.nn as nn |
| from typing import Type, Any, Callable, Union, List, Optional |
| from torch.nn.functional import softmax |
|
|
| try: |
| from torch.hub import load_state_dict_from_url |
| except ImportError: |
| from torch.utils.model_zoo import load_url as load_state_dict_from_url |
|
|
| model_urls = { |
| 'resnet18': 'https://download.pytorch.org/models/resnet18-f37072fd.pth', |
| 'resnet34': 'https://download.pytorch.org/models/resnet34-b627a593.pth', |
| 'resnet50': 'https://download.pytorch.org/models/resnet50-0676ba61.pth', |
| 'resnet101': 'https://download.pytorch.org/models/resnet101-63fe2227.pth', |
| 'resnet152': 'https://download.pytorch.org/models/resnet152-394f9c45.pth', |
| 'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth', |
| 'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth', |
| 'wideget_backbone50_2': 'https://download.pytorch.org/models/wideget_backbone50_2-95faca4d.pth', |
| 'wideget_backbone101_2': 'https://download.pytorch.org/models/wideget_backbone101_2-32ee1156.pth', |
| } |
|
|
|
|
| def conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> nn.Conv2d: |
| """3x3 convolution with padding""" |
| return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, |
| padding=dilation, groups=groups, bias=False, dilation=dilation) |
|
|
|
|
| def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d: |
| """1x1 convolution""" |
| return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) |
|
|
|
|
| class BasicBlock(nn.Module): |
| expansion: int = 1 |
|
|
| def __init__( |
| self, |
| inplanes: int, |
| planes: int, |
| stride: int = 1, |
| downsample: Optional[nn.Module] = None, |
| groups: int = 1, |
| base_width: int = 64, |
| dilation: int = 1, |
| norm_layer: Optional[Callable[..., nn.Module]] = None |
| ) -> None: |
| super(BasicBlock, self).__init__() |
| if norm_layer is None: |
| norm_layer = nn.BatchNorm2d |
| if groups != 1 or base_width != 64: |
| raise ValueError('BasicBlock only supports groups=1 and base_width=64') |
| if dilation > 1: |
| raise NotImplementedError("Dilation > 1 not supported in BasicBlock") |
| |
| self.conv1 = conv3x3(inplanes, planes, stride) |
| self.bn1 = norm_layer(planes) |
| self.relu = nn.ReLU(inplace=True) |
| self.conv2 = conv3x3(planes, planes) |
| self.bn2 = norm_layer(planes) |
| self.downsample = downsample |
| self.stride = stride |
|
|
| def forward(self, x: Tensor) -> 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): |
| expansion: int = 4 |
|
|
| def __init__( |
| self, |
| inplanes: int, |
| planes: int, |
| stride: int = 1, |
| downsample: Optional[nn.Module] = None, |
| groups: int = 1, |
| base_width: int = 64, |
| dilation: int = 1, |
| norm_layer: Optional[Callable[..., nn.Module]] = None |
| ) -> None: |
| super(Bottleneck, self).__init__() |
| if norm_layer is None: |
| norm_layer = nn.BatchNorm2d |
| width = int(planes * (base_width / 64.)) * groups |
| |
| self.conv1 = conv1x1(inplanes, width) |
| self.bn1 = norm_layer(width) |
| self.conv2 = conv3x3(width, width, stride, groups, dilation) |
| self.bn2 = norm_layer(width) |
| self.conv3 = conv1x1(width, planes * self.expansion) |
| self.bn3 = norm_layer(planes * self.expansion) |
| self.relu = nn.ReLU(inplace=True) |
| self.downsample = downsample |
| self.stride = stride |
|
|
| def forward(self, x: Tensor) -> 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): |
|
|
| def __init__( |
| self, |
| block: Type[Union[BasicBlock, Bottleneck]], |
| layers: List[int], |
| num_classes: int = 1000, |
| zero_init_residual: bool = False, |
| groups: int = 1, |
| width_per_group: int = 64, |
| replace_stride_with_dilation: Optional[List[bool]] = None, |
| norm_layer: Optional[Callable[..., nn.Module]] = None |
| ) -> None: |
| super(ResNet, self).__init__() |
| if norm_layer is None: |
| norm_layer = nn.BatchNorm2d |
| self._norm_layer = norm_layer |
|
|
| self.inplanes = 64 |
| self.dilation = 1 |
| if replace_stride_with_dilation is None: |
| |
| |
| replace_stride_with_dilation = [False, False, False] |
| if len(replace_stride_with_dilation) != 3: |
| raise ValueError("replace_stride_with_dilation should be None " |
| "or a 3-element tuple, got {}".format(replace_stride_with_dilation)) |
| self.groups = groups |
| self.base_width = width_per_group |
| self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, |
| bias=False) |
| self.bn1 = norm_layer(self.inplanes) |
| self.relu = nn.ReLU(inplace=True) |
| self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) |
| self.layer1 = self._make_layer(block, 64, layers[0]) |
| self.layer2 = self._make_layer(block, 128, layers[1], stride=2, |
| dilate=replace_stride_with_dilation[0]) |
| self.layer3 = self._make_layer(block, 256, layers[2], stride=2, |
| dilate=replace_stride_with_dilation[1]) |
| self.layer4 = self._make_layer(block, 512, layers[3], stride=2, |
| dilate=replace_stride_with_dilation[2]) |
| self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) |
| self.get_weight = nn.Sequential( |
| nn.Linear(512 * block.expansion + 768, 1), |
| nn.Sigmoid() |
| ) |
| self.fc = nn.Linear(512 * block.expansion + 768, 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.GroupNorm)): |
| nn.init.constant_(m.weight, 1) |
| nn.init.constant_(m.bias, 0) |
|
|
| |
| |
| |
| if zero_init_residual: |
| for m in self.modules(): |
| if isinstance(m, Bottleneck): |
| nn.init.constant_(m.bn3.weight, 0) |
| elif isinstance(m, BasicBlock): |
| nn.init.constant_(m.bn2.weight, 0) |
|
|
| def _make_layer(self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int, |
| stride: int = 1, dilate: bool = False) -> nn.Sequential: |
| norm_layer = self._norm_layer |
| downsample = None |
| previous_dilation = self.dilation |
| if dilate: |
| self.dilation *= stride |
| stride = 1 |
| if stride != 1 or self.inplanes != planes * block.expansion: |
| downsample = nn.Sequential( |
| conv1x1(self.inplanes, planes * block.expansion, stride), |
| norm_layer(planes * block.expansion), |
| ) |
|
|
| layers = [] |
| layers.append(block(self.inplanes, planes, stride, downsample, self.groups, |
| self.base_width, previous_dilation, norm_layer)) |
| self.inplanes = planes * block.expansion |
| for _ in range(1, blocks): |
| layers.append(block(self.inplanes, planes, groups=self.groups, |
| base_width=self.base_width, dilation=self.dilation, |
| norm_layer=norm_layer)) |
|
|
| return nn.Sequential(*layers) |
|
|
| def _forward_impl(self, x, feature): |
| |
| |
| features, weights, parts, weights_org, weights_max = [list() for i in range(5)] |
| for i in range(len(x[0])): |
| features.clear() |
| weights.clear() |
| for j in range(len(x)): |
| f = x[j][i] |
| f = self.conv1(f) |
| f = self.bn1(f) |
| f = self.relu(f) |
| f = self.maxpool(f) |
| f = self.layer1(f) |
| f = self.layer2(f) |
| f = self.layer3(f) |
| f = self.layer4(f) |
| f = self.avgpool(f) |
| f = torch.flatten(f, 1) |
|
|
| |
| features.append(torch.cat([f, feature], dim=1)) |
| weights.append(self.get_weight(features[-1])) |
|
|
| features_stack = torch.stack(features, dim=2) |
| weights_stack = torch.stack(weights, dim=2) |
| weights_stack = softmax(weights_stack, dim=2) |
|
|
| weights_max.append(weights_stack[:, :, :len(x)].max(dim=2)[0]) |
| weights_org.append(weights_stack[:, :, 0]) |
| parts.append(features_stack.mul(weights_stack).sum(2).div(weights_stack.sum(2))) |
| parts_stack = torch.stack(parts, dim=0) |
| out = parts_stack.sum(0).div(parts_stack.shape[0]) |
|
|
| pred_score = self.fc(out) |
|
|
| return pred_score, weights_max, weights_org |
|
|
| def forward(self, x, feature): |
| return self._forward_impl(x, feature) |
|
|
|
|
| def _get_backbone( |
| arch: str, |
| block: Type[Union[BasicBlock, Bottleneck]], |
| layers: List[int], |
| pretrained: bool, |
| progress: bool, |
| **kwargs: Any |
| ) -> ResNet: |
| model = ResNet(block, layers, num_classes=1, **kwargs) |
| if pretrained: |
| state_dict = load_state_dict_from_url(model_urls[arch], progress=progress) |
| model.load_state_dict(state_dict) |
| return model |
|
|
|
|
| def get_backbone(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet: |
| r"""ResNet-50 model from |
| `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. |
| |
| Args: |
| pretrained (bool): If True, returns a model pre-trained on ImageNet |
| progress (bool): If True, displays a progress bar of the download to stderr |
| """ |
| return _get_backbone('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs) |
|
|
|
|
| if __name__ == '__main__': |
| model = get_backbone() |
| data = [[] for i in range(3)] |
| for i in range(3): |
| for j in range(5): |
| data[i].append(torch.rand((10, 3, 224, 224))) |
| feature = torch.rand((10, 768)) |
| pred_score, weights_max, weights_org = model(data, feature) |
| pass |
|
|
