Thanks for your reply. I am using resnet34. My architecture code is:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from torch.autograd import Function
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']
model_urls = {
'resnet18': 'https://s3.amazonaws.com/pytorch/models/resnet18-5c106cde.pth',
'resnet34': 'https://s3.amazonaws.com/pytorch/models/resnet34-333f7ec4.pth',
'resnet50': 'https://s3.amazonaws.com/pytorch/models/resnet50-19c8e357.pth',
'resnet101':
'https://s3.amazonaws.com/pytorch/models/resnet101-5d3b4d8f.pth',
'resnet152':
'https://s3.amazonaws.com/pytorch/models/resnet152-b121ed2d.pth',
}
def init_weights(m):
classname = m.__class__.__name__
if classname.find('Conv2d') != -1 or \
classname.find('ConvTranspose2d') != -1:
nn.init.kaiming_uniform_(m.weight)
nn.init.zeros_(m.bias)
elif classname.find('BatchNorm') != -1:
nn.init.normal_(m.weight, 1.0, 0.02)
nn.init.zeros_(m.bias)
elif classname.find('Linear') != -1:
nn.init.xavier_normal_(m.weight)
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 GradReverse(Function):
def __init__(self, lambd):
self.lambd = lambd
def forward(self, x):
return x.view_as(x)
def backward(self, grad_output):
return (grad_output * -self.lambd)
def grad_reverse(x, lambd=1.0):
return GradReverse(lambd)(x)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, nobn=False):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
self.nobn = nobn
def forward(self, x, source=True):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ScaleLayer(nn.Module):
def __init__(self, init_value=1e-3):
super(ScaleLayer, self).__init__()
self.scale = nn.Parameter(torch.FloatTensor([init_value]))
def forward(self, input):
print(self.scale)
return input * self.scale
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, nobn=False):
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
self.nobn = nobn
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=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.in1 = nn.InstanceNorm2d(64)
self.in2 = nn.InstanceNorm2d(128)
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)
self.fc = nn.Linear(512 * block.expansion, 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, 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, nobn=False):
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, nobn=nobn))
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)
return x
def resnet34(pretrained=True):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
return model
Is there some issue with this code?
Thanks,
Megh