基于WIN10的64位系统演示

一、写在前面

由于不少模型使用的是Pytorch，因此这一期补上基于Pytorch实现CNN可视化的教程和代码，以SqueezeNet模型为例。

二、CNN可视化实战

继续使用胸片的数据集：肺结核病人和健康人的胸片的识别。其中，肺结核病人700张，健康人900张，分别存入单独的文件夹中。

（a）SqueezeNet建模

######################################导入包###################################
# 导入必要的包
import copy
import torch
import torchvision
import torchvision.transforms as transforms
from torchvision import models
from torch.utils.data import DataLoader
from torch import optim, nn
from torch.optim import lr_scheduler
import os
import matplotlib.pyplot as plt
import warnings
import numpy as np

warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

# 设置GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


################################导入数据集#####################################
import torch
from torchvision import datasets, transforms
import os

# 数据集路径
data_dir = "./MTB"

# 图像的大小
img_height = 100
img_width = 100

# 数据预处理
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(img_height),
        transforms.RandomHorizontalFlip(),
        transforms.RandomVerticalFlip(),
        transforms.RandomRotation(0.2),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize((img_height, img_width)),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# 加载数据集
full_dataset = datasets.ImageFolder(data_dir)

# 获取数据集的大小
full_size = len(full_dataset)
train_size = int(0.7 * full_size)  # 假设训练集占80%
val_size = full_size - train_size  # 验证集的大小

# 随机分割数据集
torch.manual_seed(0)  # 设置随机种子以确保结果可重复
train_dataset, val_dataset = torch.utils.data.random_split(full_dataset, [train_size, val_size])

# 将数据增强应用到训练集
train_dataset.dataset.transform = data_transforms['train']

# 创建数据加载器
batch_size = 32
train_dataloader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4)
val_dataloader = torch.utils.data.DataLoader(val_dataset, batch_size=batch_size, shuffle=True, num_workers=4)

dataloaders = {'train': train_dataloader, 'val': val_dataloader}
dataset_sizes = {'train': len(train_dataset), 'val': len(val_dataset)}
class_names = full_dataset.classes


###############################定义ShuffleNet模型################################
# 定义SqueezeNet模型
model = models.squeezenet1_1(pretrained=True)  # 这里以SqueezeNet 1.1版本为例
num_ftrs = model.classifier[1].in_channels

# 根据分类任务修改最后一层
model.classifier[1] = nn.Conv2d(num_ftrs, len(class_names), kernel_size=(1,1))

# 修改模型最后的输出层为我们需要的类别数
model.num_classes = len(class_names)

model = model.to(device)

# 打印模型摘要
print(model)

#############################编译模型#########################################
# 定义损失函数
criterion = nn.CrossEntropyLoss()

# 定义优化器
optimizer = optim.Adam(model.parameters())

# 定义学习率调度器
exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

# 开始训练模型
num_epochs = 20

# 初始化记录器
train_loss_history = []
train_acc_history = []
val_loss_history = []
val_acc_history = []

for epoch in range(num_epochs):
    print('Epoch {}/{}'.format(epoch, num_epochs - 1))
    print('-' * 10)

    # 每个epoch都有一个训练和验证阶段
    for phase in ['train', 'val']:
        if phase == 'train':
            model.train()  # 设置模型为训练模式
        else:
            model.eval()   # 设置模型为评估模式

        running_loss = 0.0
        running_corrects = 0

        # 遍历数据
        for inputs, labels in dataloaders[phase]:
            inputs = inputs.to(device)
            labels = labels.to(device)

            # 零参数梯度
            optimizer.zero_grad()

            # 前向
            with torch.set_grad_enabled(phase == 'train'):
                outputs = model(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)

                # 只在训练模式下进行反向和优化
                if phase == 'train':
                    loss.backward()
                    optimizer.step()

            # 统计
            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)

        epoch_loss = running_loss / dataset_sizes[phase]
        epoch_acc = (running_corrects.double() / dataset_sizes[phase]).item()

        # 记录每个epoch的loss和accuracy
        if phase == 'train':
            train_loss_history.append(epoch_loss)
            train_acc_history.append(epoch_acc)
        else:
            val_loss_history.append(epoch_loss)
            val_acc_history.append(epoch_acc)

        print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))

    print()

# 保存模型
torch.save(model.state_dict(), 'squeezenet.pth')

（b）可视化卷积神经网络的中间输出

import torch
from torchvision import models, transforms
import matplotlib.pyplot as plt
from torch import nn
from PIL import Image

# 定义图像的大小
img_height = 100
img_width = 100

# 1. 加载模型
model = models.squeezenet1_1(pretrained=False) 
num_ftrs = model.classifier[1].in_channels
num_classes = 2 
model.classifier[1] = nn.Conv2d(num_ftrs, num_classes, kernel_size=(1,1))
model.num_classes = num_classes
model.load_state_dict(torch.load('squeezenet.pth')) 
model.eval()
model = model.to('cuda' if torch.cuda.is_available() else 'cpu')

# 2. 加载图片并进行预处理
img = Image.open('./MTB/Tuberculosis/Tuberculosis-203.png')
transform = transforms.Compose([
    transforms.Resize((img_height, img_width)),
    transforms.Grayscale(num_output_channels=3),  
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
img_tensor = transform(img).unsqueeze(0)
img_tensor = img_tensor.to('cuda' if torch.cuda.is_available() else 'cpu')

# 3. 提取前N层的输出
N = 25
activations = []
x = img_tensor
for i, layer in enumerate(model.features):
    x = layer(x)
    if i < N:
        activations.append(x)

# 4. 将每个中间激活的所有通道可视化，但最多只显示前9个通道
max_channels_to_show = 9
for i, activation in enumerate(activations):
    num_channels = min(max_channels_to_show, activation.shape[1])
    fig, axs = plt.subplots(1, num_channels, figsize=(num_channels*2, 2))
    for j in range(num_channels):
        axs[j].imshow(activation[0, j].detach().cpu().numpy(), cmap='viridis')
        axs[j].axis('off')
    plt.tight_layout()
    plt.show()

# 清空当前图像
plt.clf()

结果输出如下：

由于SqueezeNet只有13层，所以即使我们在代码中要求输出25层，那也只能输出13层。从第一层到最后一层，可以看到逐渐抽象化。

（c）可视化过滤器

import matplotlib.pyplot as plt

def visualize_filters(model):
    # 获取第一个卷积层的权重
    first_conv_layer = model.features[0]
    weights = first_conv_layer.weight.data.cpu().numpy()
    
    # 取绝对值以便于观察所有权重
    weights = np.abs(weights)
    
    # 归一化权重
    weights -= weights.min()
    weights /= weights.max()
    
    # 计算子图网格大小
    num_filters = weights.shape[0]
    num_cols = 12
    num_rows = num_filters // num_cols
    if num_filters % num_cols != 0:
        num_rows += 1
    
    # 创建子图
    fig, axs = plt.subplots(num_rows, num_cols, figsize=(num_cols*2, num_rows*2))
    
    # 绘制过滤器
    for filter_index, ax in enumerate(axs.flat):
        if filter_index < num_filters:
            ax.imshow(weights[filter_index].transpose(1, 2, 0))
        ax.axis('off')
    
    plt.tight_layout()
    plt.show()

# 调用函数来显示过滤器
visualize_filters(model)

这个更加抽象：

（d）Grad-CAM绘制特征热力图

import torch
from torchvision import models, transforms
from torch.nn import functional as F
from torch.autograd import Variable
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import matplotlib.cm as cm

# 模型路径
model_path = 'squeezenet.pth'

# 图像路径
image_path = './MTB/Tuberculosis/Tuberculosis-203.png'

# 加载模型
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 创建一个SqueezeNet模型
model = models.squeezenet1_1(pretrained=False)

# 修改最后一层为二分类
model.classifier[1] = torch.nn.Conv2d(512, 2, kernel_size=(1,1), stride=(1,1))

# 这行代码用于在模型全连接层输出后添加一个softmax函数，使得模型输出可以解释为概率
model.num_classes = 2

model = model.to(device)
model.load_state_dict(torch.load(model_path))
model.eval()

class GradCAM:
    def __init__(self, model, target_layer):
        self.model = model
        self.target_layer = target_layer
        self.feature = None
        self.gradient = None

        # 定义钩子
        self.hooks = self.target_layer.register_forward_hook(self.save_feature_map)
        self.hooks = self.target_layer.register_backward_hook(self.save_gradient)

    # 保存feature
    def save_feature_map(self, module, input, output):
        self.feature = output

    # 保存梯度
    def save_gradient(self, module, grad_in, grad_out):
        self.gradient = grad_out[0]

    # 计算权重
    def compute_weight(self):
        return F.adaptive_avg_pool2d(self.gradient, 1)

    def remove_hooks(self):
        self.hooks.remove()

    def __call__(self, inputs, index=None):
        self.model.zero_grad()

        output = self.model(inputs)
        if index == None:
            index = np.argmax(output.cpu().data.numpy())

        target = output[0][index]
        target.backward()

        weight = self.compute_weight()
        cam = weight * self.feature
        cam = cam.cpu().data.numpy()
        cam = np.sum(cam, axis=1)
        cam = np.maximum(cam, 0)

        # 归一化处理
        cam -= np.min(cam)
        cam /= np.max(cam)

        self.remove_hooks()

        return cam

# 图像处理
img = Image.open(image_path).convert("RGB")
img_transforms = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
img_tensor = img_transforms(img)
img_tensor = img_tensor.unsqueeze(0).to(device)

# 获取预测类别
outputs = model(img_tensor)
_, pred = torch.max(outputs, 1)
pred_class = pred.item()

# 获取最后一个卷积层
target_layer = model.features[12]

# Grad-CAM
grad_cam = GradCAM(model=model, target_layer=target_layer)
# 获取输入图像的Grad-CAM图像
cam_img = grad_cam(img_tensor, index=pred_class)

# 重新调整尺寸以匹配原始图像
cam_img = Image.fromarray(np.uint8(255 * cam_img[0]))
cam_img = cam_img.resize((img.width, img.height), Image.BICUBIC)

# 将CAM图像转换为Heatmap
cmap = cm.get_cmap('jet')
cam_img = cmap(np.float32(cam_img))

# 将RGBA图像转换为RGB
cam_img = Image.fromarray(np.uint8(cam_img[:, :, :3] * 255))
cam_img = Image.blend(img, cam_img, alpha=0.5)

# 显示图像
plt.imshow(cam_img)
plt.axis('off')  # 不显示坐标轴
plt.show()

print(pred_class)

输出如下，分别是第一、二、六、十二层的卷积层的输出：