123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181 |
- import math
- import torch
- import torch.nn.functional as F
- from torch import nn
- from torch.nn import Parameter
- from .config import device, num_classes
- def create_model(opt):
- if opt.model == 'pix2pixHD':
- #from .pix2pixHD_model import Pix2PixHDModel, InferenceModel
- from .fs_model import fsModel
- model = fsModel()
- else:
- from .ui_model import UIModel
- model = UIModel()
- model.initialize(opt)
- if opt.verbose:
- print("model [%s] was created" % (model.name()))
- if opt.isTrain and len(opt.gpu_ids) and not opt.fp16:
- model = torch.nn.DataParallel(model, device_ids=opt.gpu_ids)
- return model
- class SEBlock(nn.Module):
- def __init__(self, channel, reduction=16):
- super(SEBlock, self).__init__()
- self.avg_pool = nn.AdaptiveAvgPool2d(1)
- self.fc = nn.Sequential(
- nn.Linear(channel, channel // reduction),
- nn.PReLU(),
- nn.Linear(channel // reduction, channel),
- nn.Sigmoid()
- )
- def forward(self, x):
- b, c, _, _ = x.size()
- y = self.avg_pool(x).view(b, c)
- y = self.fc(y).view(b, c, 1, 1)
- return x * y
- class IRBlock(nn.Module):
- expansion = 1
- def __init__(self, inplanes, planes, stride=1, downsample=None, use_se=True):
- super(IRBlock, self).__init__()
- self.bn0 = nn.BatchNorm2d(inplanes)
- self.conv1 = conv3x3(inplanes, inplanes)
- self.bn1 = nn.BatchNorm2d(inplanes)
- self.prelu = nn.PReLU()
- self.conv2 = conv3x3(inplanes, planes, stride)
- self.bn2 = nn.BatchNorm2d(planes)
- self.downsample = downsample
- self.stride = stride
- self.use_se = use_se
- if self.use_se:
- self.se = SEBlock(planes)
- def forward(self, x):
- residual = x
- out = self.bn0(x)
- out = self.conv1(out)
- out = self.bn1(out)
- out = self.prelu(out)
- out = self.conv2(out)
- out = self.bn2(out)
- if self.use_se:
- out = self.se(out)
- if self.downsample is not None:
- residual = self.downsample(x)
- out += residual
- out = self.prelu(out)
- return out
- class ResNet(nn.Module):
- def __init__(self, block, layers, use_se=True):
- self.inplanes = 64
- self.use_se = use_se
- super(ResNet, self).__init__()
- self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, bias=False)
- self.bn1 = nn.BatchNorm2d(64)
- self.prelu = nn.PReLU()
- self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
- 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)
- self.bn2 = nn.BatchNorm2d(512)
- self.dropout = nn.Dropout()
- self.fc = nn.Linear(512 * 7 * 7, 512)
- self.bn3 = nn.BatchNorm1d(512)
- for m in self.modules():
- if isinstance(m, nn.Conv2d):
- nn.init.xavier_normal_(m.weight)
- elif isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d):
- nn.init.constant_(m.weight, 1)
- nn.init.constant_(m.bias, 0)
- elif isinstance(m, nn.Linear):
- nn.init.xavier_normal_(m.weight)
- nn.init.constant_(m.bias, 0)
- 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, use_se=self.use_se))
- self.inplanes = planes
- for i in range(1, blocks):
- layers.append(block(self.inplanes, planes, use_se=self.use_se))
- return nn.Sequential(*layers)
- def forward(self, x):
- x = self.conv1(x)
- x = self.bn1(x)
- x = self.prelu(x)
- x = self.maxpool(x)
- x = self.layer1(x)
- x = self.layer2(x)
- x = self.layer3(x)
- x = self.layer4(x)
- x = self.bn2(x)
- x = self.dropout(x)
- x = x.view(x.size(0), -1)
- x = self.fc(x)
- x = self.bn3(x)
- return x
- class ArcMarginModel(nn.Module):
- def __init__(self, args):
- super(ArcMarginModel, self).__init__()
- self.weight = Parameter(torch.FloatTensor(num_classes, args.emb_size))
- nn.init.xavier_uniform_(self.weight)
- self.easy_margin = args.easy_margin
- self.m = args.margin_m
- self.s = args.margin_s
- self.cos_m = math.cos(self.m)
- self.sin_m = math.sin(self.m)
- self.th = math.cos(math.pi - self.m)
- self.mm = math.sin(math.pi - self.m) * self.m
- def forward(self, input, label):
- x = F.normalize(input)
- W = F.normalize(self.weight)
- cosine = F.linear(x, W)
- sine = torch.sqrt(1.0 - torch.pow(cosine, 2))
- phi = cosine * self.cos_m - sine * self.sin_m # cos(theta + m)
- if self.easy_margin:
- phi = torch.where(cosine > 0, phi, cosine)
- else:
- phi = torch.where(cosine > self.th, phi, cosine - self.mm)
- one_hot = torch.zeros(cosine.size(), device=device)
- one_hot.scatter_(1, label.view(-1, 1).long(), 1)
- output = (one_hot * phi) + ((1.0 - one_hot) * cosine)
- output *= self.s
- return output
|