FPN
bottom up + top down.
参考:https://github.com/luliyucoordinate/FPN_pytorch/blob/master/fpn.py
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
import torch.nn as nn import torch.nn.functional as F import math __all__=['FPN'] class Bottleneck(nn.Module): expansion = 4 def __init__(self, in_planes, planes, stride=1, downsample=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False) self.bn1 = nn.BatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, self.expansion * planes, kernel_size=1, bias=False) self.bn3 = nn.BatchNorm2d(self.expansion * planes) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride def forward(self, x): residual = 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: residual = self.downsample(x) out += residual out = self.relu(out) return out class FPN(nn.Module): def __init__(self, block, layers): super(FPN, self).__init__() self.inplanes = 64 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) # Bottom-up 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) # Top layer self.toplayer = nn.Conv2d(2048, 256, kernel_size=1, stride=1, padding=0) # Reduce channels # Smooth layers self.smooth1 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1) self.smooth2 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1) self.smooth3 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1) # Lateral layers self.latlayer1 = nn.Conv2d(1024, 256, kernel_size=1, stride=1, padding=0) self.latlayer2 = nn.Conv2d( 512, 256, kernel_size=1, stride=1, padding=0) self.latlayer3 = nn.Conv2d( 256, 256, kernel_size=1, stride=1, padding=0) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != block.expansion * planes: downsample = nn.Sequential( nn.Conv2d(self.inplanes, block.expansion * planes, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(block.expansion * planes) ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) return nn.Sequential(*layers) def _upsample_add(self, x, y): _,_,H,W = y.size() return F.upsample(x, size=(H,W), mode='bilinear') + y def forward(self, x): # Bottom-up x = self.conv1(x) x = self.bn1(x) x = self.relu(x) c1 = self.maxpool(x) c2 = self.layer1(c1) c3 = self.layer2(c2) c4 = self.layer3(c3) c5 = self.layer4(c4) # Top-down p5 = self.toplayer(c5) p4 = self._upsample_add(p5, self.latlayer1(c4)) p3 = self._upsample_add(p4, self.latlayer2(c3)) p2 = self._upsample_add(p3, self.latlayer3(c2)) # Smooth p4 = self.smooth1(p4) p3 = self.smooth2(p3) p2 = self.smooth3(p2) return p2, p3, p4, p5 def FPN101(): return FPN(Bottleneck, [2,2,2,2])
RetinaNet
retinanet的结构和FPN在输出层上有些区别.
参考:https://github.com/yhenon/pytorch-retinanet/blob/master/model.py
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
import torch.nn as nn import torch import math import time import torch.utils.model_zoo as model_zoo from utils import BasicBlock, Bottleneck, BBoxTransform, ClipBoxes from anchors import Anchors import losses from lib.nms.pth_nms import pth_nms def nms(dets, thresh): "Dispatch to either CPU or GPU NMS implementations. Accept dets as tensor""" return pth_nms(dets, thresh) model_urls = { 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth', 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth', 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth', 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth', 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth', } class PyramidFeatures(nn.Module): def __init__(self, C3_size, C4_size, C5_size, feature_size=256): super(PyramidFeatures, self).__init__() # upsample C5 to get P5 from the FPN paper self.P5_1 = nn.Conv2d(C5_size, feature_size, kernel_size=1, stride=1, padding=0) self.P5_upsampled = nn.Upsample(scale_factor=2, mode='nearest') self.P5_2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, stride=1, padding=1) # add P5 elementwise to C4 self.P4_1 = nn.Conv2d(C4_size, feature_size, kernel_size=1, stride=1, padding=0) self.P4_upsampled = nn.Upsample(scale_factor=2, mode='nearest') self.P4_2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, stride=1, padding=1) # add P4 elementwise to C3 self.P3_1 = nn.Conv2d(C3_size, feature_size, kernel_size=1, stride=1, padding=0) self.P3_2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, stride=1, padding=1) # "P6 is obtained via a 3x3 stride-2 conv on C5" self.P6 = nn.Conv2d(C5_size, feature_size, kernel_size=3, stride=2, padding=1) # "P7 is computed by applying ReLU followed by a 3x3 stride-2 conv on P6" self.P7_1 = nn.ReLU() self.P7_2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, stride=2, padding=1) def forward(self, inputs): C3, C4, C5 = inputs P5_x = self.P5_1(C5) P5_upsampled_x = self.P5_upsampled(P5_x) P5_x = self.P5_2(P5_x) P4_x = self.P4_1(C4) P4_x = P5_upsampled_x + P4_x P4_upsampled_x = self.P4_upsampled(P4_x) P4_x = self.P4_2(P4_x) P3_x = self.P3_1(C3) P3_x = P3_x + P4_upsampled_x P3_x = self.P3_2(P3_x) P6_x = self.P6(C5) P7_x = self.P7_1(P6_x) P7_x = self.P7_2(P7_x) return [P3_x, P4_x, P5_x, P6_x, P7_x] class RegressionModel(nn.Module): def __init__(self, num_features_in, num_anchors=9, feature_size=256): super(RegressionModel, self).__init__() self.conv1 = nn.Conv2d(num_features_in, feature_size, kernel_size=3, padding=1) self.act1 = nn.ReLU() self.conv2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1) self.act2 = nn.ReLU() self.conv3 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1) self.act3 = nn.ReLU() self.conv4 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1) self.act4 = nn.ReLU() self.output = nn.Conv2d(feature_size, num_anchors*4, kernel_size=3, padding=1) def forward(self, x): out = self.conv1(x) out = self.act1(out) out = self.conv2(out) out = self.act2(out) out = self.conv3(out) out = self.act3(out) out = self.conv4(out) out = self.act4(out) out = self.output(out) # out is B x C x W x H, with C = 4*num_anchors out = out.permute(0, 2, 3, 1) return out.contiguous().view(out.shape[0], -1, 4) class ClassificationModel(nn.Module): def __init__(self, num_features_in, num_anchors=9, num_classes=80, prior=0.01, feature_size=256): super(ClassificationModel, self).__init__() self.num_classes = num_classes self.num_anchors = num_anchors self.conv1 = nn.Conv2d(num_features_in, feature_size, kernel_size=3, padding=1) self.act1 = nn.ReLU() self.conv2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1) self.act2 = nn.ReLU() self.conv3 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1) self.act3 = nn.ReLU() self.conv4 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1) self.act4 = nn.ReLU() self.output = nn.Conv2d(feature_size, num_anchors*num_classes, kernel_size=3, padding=1) self.output_act = nn.Sigmoid() def forward(self, x): out = self.conv1(x) out = self.act1(out) out = self.conv2(out) out = self.act2(out) out = self.conv3(out) out = self.act3(out) out = self.conv4(out) out = self.act4(out) out = self.output(out) out = self.output_act(out) # out is B x C x W x H, with C = n_classes + n_anchors out1 = out.permute(0, 2, 3, 1) batch_size, width, height, channels = out1.shape out2 = out1.view(batch_size, width, height, self.num_anchors, self.num_classes) return out2.contiguous().view(x.shape[0], -1, self.num_classes) class ResNet(nn.Module): def __init__(self, num_classes, block, layers): self.inplanes = 64 super(ResNet, self).__init__() 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) 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) if block == BasicBlock: fpn_sizes = [self.layer2[layers[1]-1].conv2.out_channels, self.layer3[layers[2]-1].conv2.out_channels, self.layer4[layers[3]-1].conv2.out_channels] elif block == Bottleneck: fpn_sizes = [self.layer2[layers[1]-1].conv3.out_channels, self.layer3[layers[2]-1].conv3.out_channels, self.layer4[layers[3]-1].conv3.out_channels] self.fpn = PyramidFeatures(fpn_sizes[0], fpn_sizes[1], fpn_sizes[2]) self.regressionModel = RegressionModel(256) self.classificationModel = ClassificationModel(256, num_classes=num_classes) self.anchors = Anchors() self.regressBoxes = BBoxTransform() self.clipBoxes = ClipBoxes() self.focalLoss = losses.FocalLoss() for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() prior = 0.01 self.classificationModel.output.weight.data.fill_(0) self.classificationModel.output.bias.data.fill_(-math.log((1.0-prior)/prior)) self.regressionModel.output.weight.data.fill_(0) self.regressionModel.output.bias.data.fill_(0) self.freeze_bn() def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) return nn.Sequential(*layers) def freeze_bn(self): '''Freeze BatchNorm layers.''' for layer in self.modules(): if isinstance(layer, nn.BatchNorm2d): layer.eval() def forward(self, inputs): if self.training: img_batch, annotations = inputs else: img_batch = inputs x = self.conv1(img_batch) x = self.bn1(x) x = self.relu(x) x = self.maxpool(x) x1 = self.layer1(x) x2 = self.layer2(x1) x3 = self.layer3(x2) x4 = self.layer4(x3) features = self.fpn([x2, x3, x4]) regression = torch.cat([self.regressionModel(feature) for feature in features], dim=1) classification = torch.cat([self.classificationModel(feature) for feature in features], dim=1) anchors = self.anchors(img_batch) if self.training: return self.focalLoss(classification, regression, anchors, annotations) else: transformed_anchors = self.regressBoxes(anchors, regression) transformed_anchors = self.clipBoxes(transformed_anchors, img_batch) scores = torch.max(classification, dim=2, keepdim=True)[0] scores_over_thresh = (scores>0.05)[0, :, 0] if scores_over_thresh.sum() == 0: # no boxes to NMS, just return return [torch.zeros(0), torch.zeros(0), torch.zeros(0, 4)] classification = classification[:, scores_over_thresh, :] transformed_anchors = transformed_anchors[:, scores_over_thresh, :] scores = scores[:, scores_over_thresh, :] anchors_nms_idx = nms(torch.cat([transformed_anchors, scores], dim=2)[0, :, :], 0.5) nms_scores, nms_class = classification[0, anchors_nms_idx, :].max(dim=1) return [nms_scores, nms_class, transformed_anchors[0, anchors_nms_idx, :]] def resnet18(num_classes, pretrained=False, **kwargs): """Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = ResNet(num_classes, BasicBlock, [2, 2, 2, 2], **kwargs) if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['resnet18'], model_dir='.'), strict=False) return model def resnet34(num_classes, pretrained=False, **kwargs): """Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = ResNet(num_classes, BasicBlock, [3, 4, 6, 3], **kwargs) if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['resnet34'], model_dir='.'), strict=False) return model def resnet50(num_classes, pretrained=False, **kwargs): """Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = ResNet(num_classes, Bottleneck, [3, 4, 6, 3], **kwargs) if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['resnet50'], model_dir='.'), strict=False) return model def resnet101(num_classes, pretrained=False, **kwargs): """Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = ResNet(num_classes, Bottleneck, [3, 4, 23, 3], **kwargs) if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['resnet101'], model_dir='.'), strict=False) return model def resnet152(num_classes, pretrained=False, **kwargs): """Constructs a ResNet-152 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = ResNet(num_classes, Bottleneck, [3, 8, 36, 3], **kwargs) if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['resnet152'], model_dir='.'), strict=False) return model
ResNet
包含两种block:Basic block and Bottleneck block。Basic block没有用1x1卷机进行降维和升维,堆叠两层3x3 conv,适合于浅层的网络res18,res32,bottleneck操作进行了降维升维操作,适合深层网络res50,res101等。用bottleneck时会用到对identity进行downsample来使得identity和bottleneck输出维度一致。注意identity的add在relu之前。
参考:https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
import torch import torch.nn as nn from .utils import load_state_dict_from_url __all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d', 'wide_resnet50_2', 'wide_resnet101_2'] model_urls = { 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth', 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth', 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth', 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth', 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth', 'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth', 'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth', 'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth', 'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth', } 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 BasicBlock(nn.Module): expansion = 1 def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=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") # Both self.conv1 and self.downsample layers downsample the input when stride != 1 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): 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 in torchvision places the stride for downsampling at 3x3 convolution(self.conv2) # while original implementation places the stride at the first 1x1 convolution(self.conv1) # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385. # This variant is also known as ResNet V1.5 and improves accuracy according to # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch. expansion = 4 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=1000, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=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: # 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)) self.fc = nn.Linear(512 * block.expansion, num_classes) 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) # Zero-initialize the last BN in each residual branch, # so that the residual branch starts with zeros, and each residual block behaves like an identity. # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677 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, 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_impl(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) x = self.avgpool(x) x = torch.flatten(x, 1) x = self.fc(x) return x def forward(self, x): return self._forward_impl(x) def _resnet(arch, block, layers, pretrained, progress, **kwargs): model = ResNet(block, layers, **kwargs) if pretrained: state_dict = load_state_dict_from_url(model_urls[arch], progress=progress) model.load_state_dict(state_dict) return model def resnet18(pretrained=False, progress=True, **kwargs): r"""ResNet-18 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 _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress, **kwargs) def resnet34(pretrained=False, progress=True, **kwargs): r"""ResNet-34 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 _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress, **kwargs) def resnet50(pretrained=False, progress=True, **kwargs): 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 _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs) def resnet101(pretrained=False, progress=True, **kwargs): r"""ResNet-101 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 _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs) def resnet152(pretrained=False, progress=True, **kwargs): r"""ResNet-152 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 _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress, **kwargs) def resnext50_32x4d(pretrained=False, progress=True, **kwargs): r"""ResNeXt-50 32x4d model from `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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 """ kwargs['groups'] = 32 kwargs['width_per_group'] = 4 return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs) def resnext101_32x8d(pretrained=False, progress=True, **kwargs): r"""ResNeXt-101 32x8d model from `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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 """ kwargs['groups'] = 32 kwargs['width_per_group'] = 8 return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs) def wide_resnet50_2(pretrained=False, progress=True, **kwargs): r"""Wide ResNet-50-2 model from `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_ The model is the same as ResNet except for the bottleneck number of channels which is twice larger in every block. The number of channels in outer 1x1 convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048 channels, and in Wide ResNet-50-2 has 2048-1024-2048. 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 """ kwargs['width_per_group'] = 64 * 2 return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs) def wide_resnet101_2(pretrained=False, progress=True, **kwargs): r"""Wide ResNet-101-2 model from `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_ The model is the same as ResNet except for the bottleneck number of channels which is twice larger in every block. The number of channels in outer 1x1 convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048 channels, and in Wide ResNet-50-2 has 2048-1024-2048. 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 """ kwargs['width_per_group'] = 64 * 2 return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs)