AttributeError: 'Conv2d' object has no attribute 'planes'

1

Hi,
When training a model based on the resnet50 network, the following error occurred(sometimes it can run, sometimes it will report an error):

Traceback (most recent call last):
  File "E:\Programs\MDA_2src\mfsan.py", line 158, in <module>
    model = models.MFSAN(num_classes=3)
  File "E:\Programs\MDA_2src\resnet.py", line 184, in __init__
    self.sharedNet = resnet50(True)
  File "E:\Programs\MDA_2src\resnet.py", line 271, in resnet50
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
  File "E:\Programs\MDA_2src\resnet.py", line 144, in __init__
    n = m.kernel_size[0] * m.kernel_size[1] * m.planes
  File "D:\Anaconda\lib\site-packages\torch\nn\modules\module.py", line 518, in __getattr__
    type(self).__name__, name))
AttributeError: 'Conv2d' object has no attribute 'planes'
[Finished in 1.4s with exit code 1]
2

Hi,

Could you provide more information to reproduce the error, e.g., which PyTorch you use and how ResNet is implemented in MDA_2src?

Though as far as I know the error sounds reasonable as an nn.Conv2d instance doesn’t have attribute planes

3

Thanks for reply.
Pytorch version is 0.4.1

__all__ = ['ResNet', 'resnet50']


model_urls = {
    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.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 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.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)

        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.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 ADDneck(nn.Module):

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(ADDneck, 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, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.stride = stride

    def forward(self, 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.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)
        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)
        self.baselayer = [self.conv1, self.bn1, self.layer1, self.layer2, self.layer3, self.layer4]
        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.planes
                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)

        return x

def resnet50(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:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
    return model

class MFSAN(nn.Module):

    def __init__(self, num_classes=3):
        super(MFSAN, self).__init__()
        self.sharedNet = resnet50(True)
        self.sonnet1 = ADDneck(2048, 256)
        self.sonnet2 = ADDneck(2048, 256)
        self.cls_fc_son1 = nn.Linear(256, num_classes)
        self.cls_fc_son2 = nn.Linear(256, num_classes)
        self.avgpool = nn.AvgPool2d(7, stride=1)

    def forward():
        ...
4

I think this m.planes should be either m.in_channels or m.out_channels. I’m not sure which is suitable though.

5

This is indeed the problem. After I commented out this part, the code can run. Is this for loop a part of the resnet network structure? Will it have an impact if it is removed?

6

I don’t know how exactly it affects, but it should have some effect. As to initialization, I think we can use torch.nn.init functions instead: torch.nn.init — PyTorch 1.8.1 documentation.

I’m not sure, but kaiming_uniform or kaiming_normal would be suitable for resnet architecture.