| import torch
|
| import torch.nn as nn
|
| import torch.nn.functional as F
|
| import numpy as np
|
| import functools
|
| from collections import OrderedDict
|
| import random
|
| import os
|
| import math
|
| import pickle
|
|
|
|
|
|
|
| def load_state_dict(model, fname):
|
| """
|
| Set parameters converted from Caffe models authors of VGGFace2 provide.
|
| See https://www.robots.ox.ac.uk/~vgg/data/vgg_face2/.
|
|
|
| Arguments:
|
| model: model
|
| fname: file name of parameters converted from a Caffe model, assuming the file format is Pickle.
|
| """
|
| with open(fname, 'rb') as f:
|
| weights = pickle.load(f, encoding='latin1')
|
|
|
| own_state = model.state_dict()
|
| for name, param in weights.items():
|
| if name in own_state:
|
| try:
|
| own_state[name].copy_(torch.from_numpy(param))
|
| except Exception:
|
| raise RuntimeError('While copying the parameter named {}, whose dimensions in the model are {} and whose '\
|
| 'dimensions in the checkpoint are {}.'.format(name, own_state[name].size(), param.size()))
|
| else:
|
|
|
| print('unexpected key "{}" in state_dict'.format(name))
|
|
|
|
|
| def conv3x3(in_planes, out_planes, stride=1):
|
| """3x3 convolution with padding"""
|
| return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
|
| padding=1, bias=False)
|
|
|
| def conv1x1(in_planes, out_planes, bias=True):
|
| """3x3 convolution with padding"""
|
| return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1,bias=bias )
|
|
|
| class Bottleneck(nn.Module):
|
| expansion = 4
|
|
|
| def __init__(self, inplanes, planes, stride=1, downsample=None):
|
| super(Bottleneck, self).__init__()
|
| self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=False)
|
| self.bn1 = nn.BatchNorm2d(planes)
|
| self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
|
| self.bn2 = nn.BatchNorm2d(planes)
|
| self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
|
| self.bn3 = nn.BatchNorm2d(planes * 4)
|
| 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 ResNet(nn.Module):
|
|
|
| def __init__(self, block, layers, num_classes=-1, include_top=True):
|
| self.inplanes = 64
|
| super(ResNet, self).__init__()
|
| self.include_top = include_top
|
|
|
| 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=0, ceil_mode=True)
|
|
|
| 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.avgpool = nn.AvgPool2d(7, stride=1)
|
|
|
|
|
|
|
|
|
| self.fc_dims={
|
| "id": 80,
|
| "ex": 64,
|
| "tex": 80,
|
| "angles":3,
|
| "gamma":27,
|
| "XY":2,
|
| "Z":1}
|
|
|
|
|
|
|
|
|
|
|
| _outdim = 512 * block.expansion
|
| '''
|
| self.fcid = nn.Linear(_outdim, 80)
|
| self.fcex = nn.Linear(_outdim, 64)
|
| self.fctex = nn.Linear(_outdim, 80)
|
| self.fcangles = nn.Linear(_outdim, 3)
|
| self.fcgamma = nn.Linear(_outdim, 27)
|
| self.fcXY = nn.Linear(_outdim, 2)
|
| self.fcZ = nn.Linear(_outdim, 1)
|
| '''
|
| self.fcid = conv1x1(_outdim, 80)
|
| self.fcex = conv1x1(_outdim, 64)
|
| self.fctex = conv1x1(_outdim, 80)
|
| self.fcangles = conv1x1(_outdim, 3)
|
| self.fcgamma = conv1x1(_outdim, 27)
|
| self.fcXY = conv1x1(_outdim, 2)
|
| self.fcZ = conv1x1(_outdim, 1)
|
|
|
|
|
| self.arr_fc = [self.fcid, self.fcex, self.fctex,
|
| self.fcangles, self.fcgamma, self.fcXY, self.fcZ]
|
|
|
| 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 != 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 forward(self, x):
|
| 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)
|
|
|
|
|
| n_b = x.size(0)
|
|
|
|
|
|
|
| outs=[]
|
| for fc in self.arr_fc:
|
| outs.append( fc(x).view(n_b, -1) )
|
|
|
| return outs
|
|
|
| def resnet50_use():
|
| """Constructs a ResNet-50 model.
|
| """
|
| model = ResNet(Bottleneck, [3, 4, 6, 3])
|
|
|
| return model
|
|
|
|
|
