wehub-resource-sync
144 lines
4.1 KiB
Python
144 lines
4.1 KiB
Python
import torch
|
|
import time
|
|
|
|
import torch.nn.functional as F
|
|
import torch.nn as nn
|
|
|
|
from torchvision import datasets
|
|
from torchvision import transforms
|
|
from torch.utils.data import DataLoader
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
|
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, 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, 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, grayscale):
|
|
self.inplanes = 64
|
|
if grayscale:
|
|
in_dim = 1
|
|
else:
|
|
in_dim = 3
|
|
super(ResNet, self).__init__()
|
|
self.conv1 = nn.Conv2d(in_dim, 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)
|
|
self.avgpool = nn.AvgPool2d(7, stride=1, padding=2)
|
|
#self.fc = nn.Linear(2048 * block.expansion, num_classes)
|
|
self.fc = nn.Linear(2048, num_classes)
|
|
|
|
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, (2. / n)**.5)
|
|
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)
|
|
x = x.view(x.size(0), -1)
|
|
logits = self.fc(x)
|
|
probas = F.softmax(logits, dim=1)
|
|
return logits
|
|
|
|
|
|
|
|
def resnet101(num_classes, grayscale):
|
|
"""Constructs a ResNet-101 model."""
|
|
model = ResNet(block=Bottleneck,
|
|
layers=[3, 4, 23, 3],
|
|
num_classes=num_classes,
|
|
grayscale=grayscale)
|
|
return model
|
|
|
|
|
|
|
|
|