引用中提到的Grad-CAM:Visual Explanations from Deep Networks via Gradient-based Localization的复现采用了resnet50预训练网络，下面是一个简单的resnet50代码复现的步骤：
1.导入必要的库和模块：
```
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torchvision.datasets as datasets
from torch.utils.data import DataLoader
```
2.定义ResNet50模型：
```
class ResNet50(nn.Module):
def __init__(self, num_classes=1000):
super(ResNet50, 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(64, 3)
self.layer2 = self._make_layer(128, 4, stride=2)
self.layer3 = self._make_layer(256, 6, stride=2)
self.layer4 = self._make_layer(512, 3, stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * 1 * 1, num_classes)
def _make_layer(self, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * 4:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * 4, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * 4),
)
layers = []
layers.append(Bottleneck(self.inplanes, planes, stride, downsample))
self.inplanes = planes * 4
for _ in range(1, blocks):
layers.append(Bottleneck(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)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
```
3.定义Bottleneck模块：
```
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):
identity = 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:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
```
4.定义数据预处理：
```
transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
```
5.加载数据集：
```
train_dataset = datasets.ImageFolder('path/to/train', transform=transform)
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
val_dataset = datasets.ImageFolder('path/to/val', transform=transform)
val_loader = DataLoader(val_dataset, batch_size=32, shuffle=False)
```
6.定义损失函数和优化器：
```
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.9, weight_decay=1e-4)
```
7.训练模型：
```
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
loss = criterion(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
```
8.测试模型：
```
with torch.no_grad():
correct = 0
total = 0
for images, labels in val_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))
```
扫一扫
1275
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
