复习日
作业：
kaggle找到一个图像数据集，用cnn网络进行训练并且用grad-cam做可视化
进阶：并拆分成多个文件
我选择ouIntel Image Classification | Kagglezz，该数据集分为六类，包含建筑、森林、冰川、山脉、海洋和街道。
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
import numpy as np
import matplotlib.pyplot as plt
import os
from PIL import Image
import warnings# 设置随机种子
torch.manual_seed(42)
np.random.seed(42)# 数据预处理：转换为张量 + 归一化 + Resize到64x64
transform = transforms.Compose([transforms.Resize((64, 64)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])# 加载数据集
trainset = ImageFolder(root='./intel_image_classification/seg_train/seg_train', transform=transform)
testset = ImageFolder(root='./intel_image_classification/seg_test/seg_test', transform=transform)
classes = trainset.classes# 构建CNN模型
class SimpleCNN(nn.Module):def __init__(self):super(SimpleCNN, self).__init__()self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)self.pool = nn.MaxPool2d(2, 2)self.fc1 = nn.Linear(128 * 8 * 8, 512)self.fc2 = nn.Linear(512, 6)def forward(self, x):x = self.pool(F.relu(self.conv1(x))) # 64 -> 32x = self.pool(F.relu(self.conv2(x))) # 32 -> 16x = self.pool(F.relu(self.conv3(x))) # 16 -> 8x = x.view(-1, 128 * 8 * 8)x = F.relu(self.fc1(x))x = self.fc2(x)return x# 创建模型及设备
def create_model():model = SimpleCNN()print("模型已创建")device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")return model.to(device), device# 模型训练函数
def train_model(model, device, trainset, epochs=2):trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True, num_workers=2)criterion = nn.CrossEntropyLoss()optimizer = torch.optim.Adam(model.parameters(), lr=0.001)model.train()for epoch in range(epochs):running_loss = 0.0for i, (inputs, labels) in enumerate(trainloader):inputs, labels = inputs.to(device), labels.to(device)optimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, labels)loss.backward()optimizer.step()running_loss += loss.item()if i % 100 == 99:print(f'[{epoch + 1}, {i + 1}] 损失: {running_loss / 100:.3f}')running_loss = 0.0print("训练完成")# Grad-CAM 实现类
class GradCAM:def __init__(self, model, target_layer):self.model = modelself.target_layer = target_layerself.gradients = Noneself.activations = Noneself.register_hooks()def register_hooks(self):def forward_hook(module, input, output):self.activations = output.detach()def backward_hook(module, grad_input, grad_output):self.gradients = grad_output[0].detach()self.target_layer.register_forward_hook(forward_hook)self.target_layer.register_backward_hook(backward_hook)def generate_cam(self, input_image, target_class=None):model_output = self.model(input_image)if target_class is None:target_class = torch.argmax(model_output, dim=1).item()self.model.zero_grad()one_hot = torch.zeros_like(model_output)one_hot[0, target_class] = 1model_output.backward(gradient=one_hot)gradients = self.gradientsactivations = self.activationsweights = torch.mean(gradients, dim=(2, 3), keepdim=True)cam = torch.sum(weights * activations, dim=1, keepdim=True)cam = F.relu(cam)cam = F.interpolate(cam, size=(64, 64), mode='bilinear', align_corners=False)cam = cam - cam.min()cam = cam / cam.max() if cam.max() > 0 else camreturn cam.cpu().squeeze().numpy(), target_class# 图像张量转换为numpy数组，用于可视化
def tensor_to_np(tensor):img = tensor.cpu().numpy().transpose(1, 2, 0)mean = np.array([0.5, 0.5, 0.5])std = np.array([0.5, 0.5, 0.5])img = std * img + meanimg = np.clip(img, 0, 1)return img# 主函数入口（避免Windows多次导入问题）
if __name__ == "__main__":warnings.filterwarnings("ignore")plt.rcParams["font.family"] = ["SimHei"]plt.rcParams['axes.unicode_minus'] = Falsemodel, device = create_model()# 是否训练模型train_model(model, device, trainset, epochs=20)torch.save(model.state_dict(), 'intel_cnn.pth')model.eval()# Grad-CAM 可视化idx = 300image, label = testset[idx]print(f"选择的图像类别: {classes[label]}")input_tensor = image.unsqueeze(0).to(device)grad_cam = GradCAM(model, model.conv3)heatmap, pred_class = grad_cam.generate_cam(input_tensor)# 可视化图像 + CAMplt.figure(figsize=(12, 4))plt.subplot(1, 3, 1)plt.imshow(tensor_to_np(image))plt.title(f"原始图像: {classes[label]}")plt.axis('off')plt.subplot(1, 3, 2)plt.imshow(heatmap, cmap='jet')plt.title(f"Grad-CAM热力图: {classes[pred_class]}")plt.axis('off')plt.subplot(1, 3, 3)img = tensor_to_np(image)heatmap_resized = np.uint8(255 * heatmap)heatmap_colored = plt.cm.jet(heatmap_resized)[:, :, :3]superimposed_img = heatmap_colored * 0.4 + img * 0.6plt.imshow(superimposed_img)plt.title("叠加热力图")plt.axis('off')plt.tight_layout()plt.savefig('grad_cam_result.png')plt.show()
进阶：分成多个文件：
day43_cnn.py
import torch
import torch.nn as nn
import torch.nn.functional as Fclass SimpleCNN(nn.Module):def __init__(self):super(SimpleCNN, self).__init__()self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)self.pool = nn.MaxPool2d(2, 2)self.fc1 = nn.Linear(128 * 8 * 8, 512)self.fc2 = nn.Linear(512, 6)def forward(self, x):x = self.pool(F.relu(self.conv1(x))) # 64 -> 32x = self.pool(F.relu(self.conv2(x))) # 32 -> 16x = self.pool(F.relu(self.conv3(x))) # 16 -> 8x = x.view(-1, 128 * 8 * 8)x = F.relu(self.fc1(x))x = self.fc2(x)return xday43_dataset.py
from torchvision import transforms
from torchvision.datasets import ImageFoldertransform = transforms.Compose([transforms.Resize((64, 64)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])# 加载数据集
trainset = ImageFolder(root='./intel_image_classification/seg_train/seg_train', transform=transform)
testset = ImageFolder(root='./intel_image_classification/seg_test/seg_test', transform=transform)
classes = trainset.classesday43_train.py
import torch
import torch.nn as nn
import torch.nn.functional as Fdef train_model(model, device, trainset, epochs=2):trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True, num_workers=2)criterion = nn.CrossEntropyLoss()optimizer = torch.optim.Adam(model.parameters(), lr=0.001)model.train()for epoch in range(epochs):running_loss = 0.0for i, (inputs, labels) in enumerate(trainloader):inputs, labels = inputs.to(device), labels.to(device)optimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, labels)loss.backward()optimizer.step()running_loss += loss.item()if i % 100 == 99:print(f'[{epoch + 1}, {i + 1}] 损失: {running_loss / 100:.3f}')running_loss = 0.0print("训练完成")day43_grad_cam.py
import torch
import torch.nn as nn
import torch.nn.functional as F
class GradCAM:def __init__(self, model, target_layer):self.model = modelself.target_layer = target_layerself.gradients = Noneself.activations = Noneself.register_hooks()def register_hooks(self):def forward_hook(module, input, output):self.activations = output.detach()def backward_hook(module, grad_input, grad_output):self.gradients = grad_output[0].detach()self.target_layer.register_forward_hook(forward_hook)self.target_layer.register_backward_hook(backward_hook)def generate_cam(self, input_image, target_class=None):model_output = self.model(input_image)if target_class is None:target_class = torch.argmax(model_output, dim=1).item()self.model.zero_grad()one_hot = torch.zeros_like(model_output)one_hot[0, target_class] = 1model_output.backward(gradient=one_hot)gradients = self.gradientsactivations = self.activationsweights = torch.mean(gradients, dim=(2, 3), keepdim=True)cam = torch.sum(weights * activations, dim=1, keepdim=True)cam = F.relu(cam)cam = F.interpolate(cam, size=(64, 64), mode='bilinear', align_corners=False)cam = cam - cam.min()cam = cam / cam.max() if cam.max() > 0 else camreturn cam.cpu().squeeze().numpy(), target_classday43_main.py
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
import numpy as np
import matplotlib.pyplot as plt
import os
from PIL import Image
import warnings
from day43_grad_cam import *
from day43_cnn import *
from day43_train import *
from day43_dataset import *# 设置随机种子
torch.manual_seed(42)
np.random.seed(42)def create_model():model = SimpleCNN()print("模型已创建")device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")return model.to(device), device# 图像张量转换为numpy数组，用于可视化
def tensor_to_np(tensor):img = tensor.cpu().numpy().transpose(1, 2, 0)mean = np.array([0.5, 0.5, 0.5])std = np.array([0.5, 0.5, 0.5])img = std * img + meanimg = np.clip(img, 0, 1)return imgdef main():warnings.filterwarnings("ignore")plt.rcParams["font.family"] = ["SimHei"]plt.rcParams['axes.unicode_minus'] = Falsemodel, device = create_model()# 是否训练模型train_model(model, device, trainset, epochs=2)torch.save(model.state_dict(), 'intel_cnn.pth')model.eval()# Grad-CAM 可视化idx = 300 # 选择测试集中第102张图片image, label = testset[idx]print(f"选择的图像类别: {classes[label]}")input_tensor = image.unsqueeze(0).to(device)grad_cam = GradCAM(model, model.conv3)heatmap, pred_class = grad_cam.generate_cam(input_tensor)# 可视化图像 + CAMplt.figure(figsize=(12, 4))plt.subplot(1, 3, 1)plt.imshow(tensor_to_np(image))plt.title(f"原始图像: {classes[label]}")plt.axis('off')plt.subplot(1, 3, 2)plt.imshow(heatmap, cmap='jet')plt.title(f"Grad-CAM热力图: {classes[pred_class]}")plt.axis('off')plt.subplot(1, 3, 3)img = tensor_to_np(image)heatmap_resized = np.uint8(255 * heatmap)heatmap_colored = plt.cm.jet(heatmap_resized)[:, :, :3]superimposed_img = heatmap_colored * 0.4 + img * 0.6plt.imshow(superimposed_img)plt.title("叠加热力图")plt.axis('off')plt.tight_layout()plt.savefig('grad_cam_result.png')plt.show()if __name__ == "__main__":main()@浙大疏锦行
)
