Add dilation to the last convolution layer in resnet101

I am using the pytorch resnet101, I am removed the average pooling and fc layers and change the stride of the last layer to 1 instead of 2. everything works fine so far.
now for the last layer (layer 4) i want to use dilation =2, but it throws me an erro…
I appreciate it if someone can help me why i get the following error:

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
import torch

class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, dilation = 1 ):
        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, dilation = dilation, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        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):
        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=1, dilation = 1) # We modify the stide 2 here to be one
#        print(self.layer4)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, planes, blocks, stride=1, dilation = 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,  dilation = dilation))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, dilation = dilation))

        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)
        print('Output SIZE',x.size())
        return x

model = ResNet(Bottleneck, [3, 4, 23, 3])
output = model(input);

when dilation is equal to 1 in line self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation = 1) it works okay. but when i do dilation =2, it give me:

  File "<ipython-input-1-cf1b4471e44a>", line 1, in <module>
    runfile('/home/alireza/Downloads/SSD_Res101/', wdir='/home/alireza/Downloads/SSD_Res101')

  File "/home/alireza/anaconda3/lib/python3.6/site-packages/spyder_kernels/customize/", line 678, in runfile
    execfile(filename, namespace)

  File "/home/alireza/anaconda3/lib/python3.6/site-packages/spyder_kernels/customize/", line 106, in execfile
    exec(compile(, filename, 'exec'), namespace)

  File "/home/alireza/Downloads/SSD_Res101/", line 110, in <module>
    output = model(input);

  File "/home/alireza/anaconda3/lib/python3.6/site-packages/torch/nn/modules/", line 477, in __call__
    result = self.forward(*input, **kwargs)

  File "/home/alireza/Downloads/SSD_Res101/", line 103, in forward
    x = self.layer4(x)

  File "/home/alireza/anaconda3/lib/python3.6/site-packages/torch/nn/modules/", line 477, in __call__
    result = self.forward(*input, **kwargs)

  File "/home/alireza/anaconda3/lib/python3.6/site-packages/torch/nn/modules/", line 91, in forward
    input = module(input)

  File "/home/alireza/anaconda3/lib/python3.6/site-packages/torch/nn/modules/", line 477, in __call__
    result = self.forward(*input, **kwargs)

  File "/home/alireza/Downloads/SSD_Res101/", line 44, in forward
    out += residual

RuntimeError: The expanded size of the tensor (31) must match the existing size (33) at non-singleton dimension 3

Dilating a kernel adds spacing between kernel elements, for example: a 2-dilated 3x3-kernel can be viewed as a 5x5 kernel.

You will need to adjust for this by using larger padding.

Thank you for your answer!
I just figured that out, for some reason when i have padding = 2, the error disappears