Spaces:
Paused
Paused
| import torch | |
| import torch.nn as nn | |
| import numpy as np | |
| def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1): | |
| """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, out_planes, stride=1): | |
| """1x1 convolution""" | |
| return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) | |
| class Bottleneck(nn.Module): | |
| expansion = 4 | |
| __constants__ = ['downsample'] | |
| def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1, | |
| base_width=64, dilation=1, norm_layer=None): | |
| super(Bottleneck, self).__init__() | |
| if norm_layer is None: | |
| norm_layer = nn.BatchNorm2d | |
| width = int(planes * (base_width / 64.)) * groups | |
| # Both self.conv2 and self.downsample layers downsample the input when stride != 1 | |
| 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): | |
| 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, layers, num_classes=1, zero_init_residual=False, | |
| groups=1, width_per_group=64, replace_stride_with_dilation=None, | |
| norm_layer=None, df=15, bf=7): | |
| super(ResNet, self).__init__() | |
| if norm_layer is None: | |
| norm_layer = nn.BatchNorm2d | |
| self._norm_layer = norm_layer | |
| self.bf = bf | |
| self.inplanes = 64 | |
| self.dilation = 1 | |
| if replace_stride_with_dilation is None: | |
| # each element in the tuple indicates if we should replace | |
| # the 2x2 stride with a dilated convolution instead | |
| 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)) | |
| # 3fc | |
| # self.fc1 = nn.Sequential( | |
| # nn.Linear(512 * block.expansion, 256 * block.expansion), | |
| # nn.ReLU(), | |
| # nn.Linear(256 * block.expansion, 128 * block.expansion), | |
| # nn.ReLU(), | |
| # nn.Linear(128 * block.expansion, df) | |
| # ) | |
| # 1fc | |
| self.fc1 = nn.Linear(512 * block.expansion, df) | |
| self.fc2 = nn.Sequential( | |
| nn.ReLU(inplace=True), | |
| nn.Linear(df+bf, 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) | |
| def _make_layer(self, block, planes, blocks, stride=1, dilate=False): | |
| 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(self, x): | |
| # See note [TorchScript super()] | |
| 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) # 2048*7*7 | |
| x = self.avgpool(x) | |
| x = torch.flatten(x, 1) | |
| x = self.fc1(x) | |
| x = self.fc2(x) | |
| return x | |
| def _resnet(arch, block, layers, pretrained, progress, **kwargs): | |
| model = ResNet(block, layers, **kwargs) | |
| return model | |
| def BFDFNet(pretrained=False, progress=True, **kwargs): | |
| return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress, | |
| **kwargs) | |
| def DFNet(pretrained=False, progress=True, **kwargs): | |
| return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress, | |
| **kwargs) | |
| # x = torch.randn((4,3,224,224)) | |
| # name = torch.from_numpy(np.asarray(['1','3','4','5'])) | |
| # net = resnet101() | |
| # y = net(x,name) |