import torch from torch import nn from torch.utils.checkpoint import checkpoint using_ckpt = False def conv3x3(in_planes, out_planes, stride=1, groups=1): """3x3 convolution with padding""" return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, groups=groups, bias=False) 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 IBasicBlock(nn.Module): def __init__(self, inplanes, planes, stride=1, downsample=None): super(IBasicBlock, self).__init__() self.bn1 = nn.BatchNorm2d(inplanes, eps=1e-05,) self.conv1 = conv3x3(inplanes, planes) self.bn2 = nn.BatchNorm2d(planes, eps=1e-05,) self.prelu = nn.PReLU(planes) self.conv2 = conv3x3(planes, planes, stride) self.bn3 = nn.BatchNorm2d(planes, eps=1e-05,) self.downsample = downsample self.stride = stride def forward_impl(self, x): identity = x out = self.bn1(x) out = self.conv1(out) out = self.bn2(out) out = self.prelu(out) out = self.conv2(out) out = self.bn3(out) if self.downsample is not None: identity = self.downsample(x) out += identity return out def forward(self, x): if self.training and using_ckpt: return checkpoint(self.forward_impl, x) else: return self.forward_impl(x) class IResNet(nn.Module): def __init__(self, block, layers, dropout=0.4, num_features=512, zero_init_residual=False, groups=1, fp16=False): super(IResNet, self).__init__() self.extra_gflops = 0.0 self.fp16 = fp16 self.inplanes = 64 self.groups = groups self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(self.inplanes, eps=1e-05) self.prelu = nn.PReLU(self.inplanes) self.layer1 = self._make_layer(block, 64, layers[0], stride=2) 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) self.bn2 = nn.BatchNorm2d(512, eps=1e-05,) self.dropout = nn.Dropout(p=dropout, inplace=True) self.fc = nn.Linear(512 * 7 * 7, num_features) self.features = nn.BatchNorm1d(num_features, eps=1e-05) nn.init.constant_(self.features.weight, 1.0) self.features.weight.requires_grad = False for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.normal_(m.weight, 0, 0.1) 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, IBasicBlock): nn.init.constant_(m.bn2.weight, 0) def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes: downsample = nn.Sequential( conv1x1(self.inplanes, planes, stride), nn.BatchNorm2d(planes, eps=1e-05, ), ) layers = [] layers.append( block(self.inplanes, planes, stride, downsample)) self.inplanes = planes for _ in range(1, blocks): layers.append( block(self.inplanes, planes)) return nn.Sequential(*layers) def forward(self, x): with torch.cuda.amp.autocast(self.fp16): x = self.conv1(x) x = self.bn1(x) x = self.prelu(x) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x = self.layer4(x) x = self.bn2(x) x = torch.flatten(x, 1) x = self.dropout(x) x = self.fc(x.float() if self.fp16 else x) x = self.features(x) return x def iresnet(arch, pretrained=False, **kwargs): layer_dict = {"18": [2, 2, 2, 2], "34": [3, 4, 6, 3], "50": [3, 4, 14, 3], "100": [3, 13, 30, 3], "152": [3, 8, 36, 3], "200": [3, 13, 30, 3]} model = IResNet(IBasicBlock, layer_dict[arch], **kwargs) if pretrained: raise ValueError() return model