为resnet layer1 层之前和layer4层之后分别添加一个cbam注意力模块，进行debug 分别为resnetclass 里ca,sa,和botterleneck的forward设置断点跳不到resnet class 类的forward 函数里去，但会跳到ca 和sa的模块里去，也可以跳到botterneck里去。
resnet_cbam 的代码我是从https://github.com/luuuyi/CBAM.PyTorch 里进行相应更改形成的，其中本来特征图经过ca和sa后会在resnet forward里再乘以原来的特征图，但是报错：期待输入特征图32维，但实际输入维度为1维，即维度不匹配，为了解决此问题，我就将相CA和SA模块里相乘放进了CA和SA里。
问题相关代码，请勿粘贴截图
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
__all__ = ['ResNet', 'resnet18_cbam', 'resnet34_cbam', 'resnet50_cbam', 'resnet101_cbam',
'resnet152_cbam']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}
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 ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.fc = nn.Sequential(nn.Conv2d(in_planes, in_planes // 16, 1, bias=False),
nn.ReLU(),
nn.Conv2d(in_planes // 16, in_planes, 1, bias=False))
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc(self.avg_pool(x))
max_out = self.fc(self.max_pool(x))
out = avg_out + max_out
out = self.sigmoid(out)
out = out * x
return out
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=kernel_size//2, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
tem = x
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
out = torch.cat([avg_out, max_out], dim=1)
out = self.conv1(out)
out = self.sigmoid(out)
# return self.sigmoid(x)
out = out*tem
return out
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
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.ca = ChannelAttention(planes)
# self.sa = SpatialAttention()
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.ca(out) * out
# out = self.sa(out) * out
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
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.ca = ChannelAttention(planes * 4)
# self.sa = SpatialAttention()
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)
# out = self.ca(out) * out
# out = self.sa(out) * 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.relu = nn.ReLU(inplace=True)
# 网络的第一层加入注意力机制
self.ca = ChannelAttention(self.inplanes)
self.sa = SpatialAttention()
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)
# 网络的卷积层的最后一层加入注意力机制
self.ca1 = ChannelAttention(self.inplanes)
self.sa1 = SpatialAttention()
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
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):
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.ca(x) * x
x = self.ca(x)
x = self.sa(x)
print("this is the resnet backbone.")
x = self.maxpool(x)
x1 = self.layer1(x)
x2 = self.layer2(x1)
x3 = self.layer3(x2)
x4 = self.layer4(x3)
last = self.ca1(x4)
last = self.sa1(last)
last = self.avgpool(last)
# last = self.avgpool(x4)
last = torch.flatten(last, 1)
last = self.fc(last)
# x = self.avgpool(x)
# x = torch.flatten(x, 1)
# x = self.fc(x)
# return x
return last
def resnet18_cbam(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet18'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet34_cbam(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet34'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet50_cbam(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet50'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet101_cbam(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet101'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet152_cbam(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet152'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
if __name__ == "__main__":
test = resnet50_cbam()
print(test)
运行结果及报错内容
我的解答思路和尝试过的方法
本身我是为了在resnet指定层加CBAM模块， 但加入模块后会报输入维度不匹配的错，于是进行debug，为CA和SA设置断点和print语句，结果发现resnet class里的forward函数不输出，打断点也从未经过。
（会不会是GPU并行运行程序，导致不输出啊？但我看另一个博主的bolg，也会输出的啊。）
我想要达到的结果
为resnet第一层残差块结构前加个CBAM模块，和最后一层残差块后加个CBAM模块，以及为什么resnet CLASS的forward函数不输出。
谢谢各位。
