Question

我想在现有的ResNet模型中提供 3,320,320张图片。该模型实际上期望输入大小为3、32、32 。因为我担心信息丢失，所以我并不想简单地调整图片大小。预处理图像以使其能够在ResNet34上运行的最佳方法是什么？我应该在ResNet的正向方法中添加其他图层吗？如果可以，哪种情况适合我？

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])

非常感谢！

关于，法比安

Answer 1

如果将avg_pool操作更改为'AdaptiveAvgPool2d'，则您的模型将适用于任何图像尺寸。

但是，在当前设置下，进入合并阶段的320x320图像将是40x40，这是要合并的大型功能图。考虑添加更多的转换层。

更改ResNet模型的输入形状尺寸（火炬）

1 个答案: