Change input shape dimensions for ResNet model (pytorch)

Question

I want to feed my 3,320,320 pictures in an existing ResNet model. The model actually expects input of size 3,32,32. As I am afraid of loosing information I don't simply want to resize my pictures. What is the best way to preprocess my images, so that they are able to run on the ResNet34? Should I add additional layers in the forward method of ResNet? If yes, what would be a suitable combination in my case?

import torch
import torch.nn as nn
import torch.nn.functional as F
from pytorch_fitmodule import FitModule
from torch.autograd import Variable
import numpy as np


def conv3x3(in_planes, out_planes, stride=1):
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)


class BasicBlock(FitModule):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(in_planes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion * planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, self.expansion * planes,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(self.expansion * planes)
            )

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = F.relu(out)
        return out



class ResNet(FitModule):
    def __init__(self, block, num_blocks, num_classes=10):
        super(ResNet, self).__init__()
        self.in_planes = 64

        self.conv1 = conv3x3(3, 64)
        self.bn1 = nn.BatchNorm2d(64)                                           
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)      
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)     
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)     
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)     
        self.linear = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(self, block, planes, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes * block.expansion
        return nn.Sequential(*layers)


    def forward(self, x):    # add additional layers here?                                       
        x = x.float()                                              
        out = F.relu(self.bn1(self.conv1(x).float()).float())      
        out = self.layer1(out)                                      
        out = self.layer2(out)                                     
        out = self.layer3(out)                                      
        out = self.layer4(out)                                      
        out = F.avg_pool2d(out, 4)                                 
        out = out.view(out.size(0), -1)                            
        out = self.linear(out)
        return out



def ResNet34():
    return ResNet(BasicBlock, [3, 4, 6, 3])

Thanks plenty!

Regards, Fabian

Answer 1

If you change your avg_pool operation to 'AdaptiveAvgPool2d' your model will work for any image size.

However with your current setup, your 320x320 images would be 40x40 going into the pooling stage, which is a large feature map to pool over. Consider adding more conv layers.