File size: 6,713 Bytes
ca1e533 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 | 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:
#raise KeyError('unexpected key "{}" in state_dict'.format(name))
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 = nn.Linear(512 * block.expansion, num_classes)
# CHJ_ADD task use
self.fc_dims={
"id": 80,
"ex": 64,
"tex": 80,
"angles":3,
"gamma":27,
"XY":2,
"Z":1}
#self.fc_dims_arr=[0] * (1+len(self.fc_dims))
#for i, (k, v) in enumerate(self.fc_dims.items()):
# self.fc_dims_arr[i+1] = v + self.fc_dims_arr[i]
_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)
# 这里不需要view
n_b = x.size(0)
#x = x.view(n_b, -1)
#x = self.fc(x) # 打算cat在一起
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])
#load_state_dict(model, fweight_file)
return model
|