第98步 深度学习图像目标检测：SSD建模

基于WIN10的64位系统演示

一、写在前面

本期开始，我们继续学习深度学习图像目标检测系列，SSD（Single Shot MultiBox Detector）模型。

二、SSD简介

SSD（Single Shot MultiBox Detector）是一种流行的目标检测算法，由 Wei Liu, Dragomir Anguelov, Dumitru Erhan 等人于 2016 年提出。它是一种单阶段的目标检测算法，与当时流行的两阶段检测器（如 Faster R-CNN）相比，SSD 提供了更快的检测速度，同时仍然具有较高的准确性。

以下是 SSD 的主要特点和组件：

（1）多尺度特征映射：

SSD 从不同的层级提取特征图，这使得它能够有效地检测不同大小的物体。这是通过在多个特征图上执行预测来实现的，其中每个特征图代表不同的尺度。

（2）默认框（或称为先验框、锚框）：

在每个特征图位置，SSD 定义了多个具有不同形状和大小的默认框。这些默认框用于与真实边界框进行匹配，并提供回归目标以调整预测的边界框大小和位置。

（3）单阶段检测器：

与两阶段检测器不同，SSD 在单个前向传递中同时进行边界框回归和类别分类，从而实现了速度和准确性之间的平衡。

（4）损失函数：

SSD 使用了组合损失，包括边界框回归的平滑 L1 损失和类别预测的交叉熵损失。

（5）数据增强：

为了提高模型的性能，SSD 使用了多种数据增强技术，包括随机裁剪、缩放和颜色扭曲等。

（6）模型骨干：

原始的 SSD 使用 VGG-16 作为其骨干网络，但后续的变种如 SSDlite 使用了更轻量级的骨干网络，如 MobileNet。

三、数据源

来源于公共数据，文件设置如下：

大概的任务就是：用一个框框标记出MTB的位置。

四、SSD实战

直接上代码：

import os
import random
import torch
import torchvision
from torchvision.models.detection import ssd300_vgg16
from torchvision.transforms import functional as F
from PIL import Image
from torch.utils.data import DataLoader
import xml.etree.ElementTree as ET
import matplotlib.pyplot as plt
from torchvision import transforms
import albumentations as A
from albumentations.pytorch import ToTensorV2
import numpy as np

# Function to parse XML annotations
def parse_xml(xml_path):
    tree = ET.parse(xml_path)
    root = tree.getroot()

    boxes = []
    for obj in root.findall("object"):
        bndbox = obj.find("bndbox")
        xmin = int(bndbox.find("xmin").text)
        ymin = int(bndbox.find("ymin").text)
        xmax = int(bndbox.find("xmax").text)
        ymax = int(bndbox.find("ymax").text)

        # Check if the bounding box is valid
        if xmin < xmax and ymin < ymax:
            boxes.append((xmin, ymin, xmax, ymax))
        else:
            print(f"Warning: Ignored invalid box in {xml_path} - ({xmin}, {ymin}, {xmax}, {ymax})")

    return boxes

# Function to split data into training and validation sets
def split_data(image_dir, split_ratio=0.8):
    all_images = [f for f in os.listdir(image_dir) if f.endswith(".jpg")]
    random.shuffle(all_images)
    split_idx = int(len(all_images) * split_ratio)
    train_images = all_images[:split_idx]
    val_images = all_images[split_idx:]
    
    return train_images, val_images


# Dataset class for the Tuberculosis dataset
class TuberculosisDataset(torch.utils.data.Dataset):
    def __init__(self, image_dir, annotation_dir, image_list, transform=None):
        self.image_dir = image_dir
        self.annotation_dir = annotation_dir
        self.image_list = image_list
        self.transform = transform

    def __len__(self):
        return len(self.image_list)

    def __getitem__(self, idx):
        image_path = os.path.join(self.image_dir, self.image_list[idx])
        image = Image.open(image_path).convert("RGB")
        
        xml_path = os.path.join(self.annotation_dir, self.image_list[idx].replace(".jpg", ".xml"))
        boxes = parse_xml(xml_path)
        
        # Check for empty bounding boxes and return None
        if len(boxes) == 0:
            return None
        
        boxes = torch.as_tensor(boxes, dtype=torch.float32)
        labels = torch.ones((len(boxes),), dtype=torch.int64)
        iscrowd = torch.zeros((len(boxes),), dtype=torch.int64)
        
        target = {}
        target["boxes"] = boxes
        target["labels"] = labels
        target["image_id"] = torch.tensor([idx])
        target["iscrowd"] = iscrowd
        
        # Apply transformations
        if self.transform:
            image = self.transform(image)
    
        return image, target

# Define the transformations using torchvision
data_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor(),  # Convert PIL image to tensor
    torchvision.transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # Normalize the images
])


# Adjusting the DataLoader collate function to handle None values
def collate_fn(batch):
    batch = list(filter(lambda x: x is not None, batch))
    return tuple(zip(*batch))


def get_ssd_model_for_finetuning(num_classes):
    # Load an SSD model with a VGG16 backbone without pre-trained weights
    model = ssd300_vgg16(pretrained=False, num_classes=num_classes)
    return model

# Function to save the model
def save_model(model, path="RetinaNet_mtb.pth", save_full_model=False):
    if save_full_model:
        torch.save(model, path)
    else:
        torch.save(model.state_dict(), path)
    print(f"Model saved to {path}")

# Function to compute Intersection over Union
def compute_iou(boxA, boxB):
    xA = max(boxA[0], boxB[0])
    yA = max(boxA[1], boxB[1])
    xB = min(boxA[2], boxB[2])
    yB = min(boxA[3], boxB[3])
    
    interArea = max(0, xB - xA + 1) * max(0, yB - yA + 1)
    boxAArea = (boxA[2] - boxA[0] + 1) * (boxA[3] - boxA[1] + 1)
    boxBArea = (boxB[2] - boxB[0] + 1) * (boxB[3] - boxB[1] + 1)
    
    iou = interArea / float(boxAArea + boxBArea - interArea)
    return iou

# Adjusting the DataLoader collate function to handle None values and entirely empty batches
def collate_fn(batch):
    batch = list(filter(lambda x: x is not None, batch))
    if len(batch) == 0:
        # Return placeholder batch if entirely empty
        return [torch.zeros(1, 3, 224, 224)], [{}]
    return tuple(zip(*batch))

#Training function with modifications for collecting IoU and loss
def train_model(model, train_loader, optimizer, device, num_epochs=10):
    model.train()
    model.to(device)
    loss_values = []
    iou_values = []
    for epoch in range(num_epochs):
        epoch_loss = 0.0
        total_ious = 0
        num_boxes = 0
        for images, targets in train_loader:
            # Skip batches with placeholder data
            if len(targets) == 1 and not targets[0]:
                continue
            # Skip batches with empty targets
            if any(len(target["boxes"]) == 0 for target in targets):
                continue
            images = [image.to(device) for image in images]
            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]
            
            loss_dict = model(images, targets)
            losses = sum(loss for loss in loss_dict.values())
            
            optimizer.zero_grad()
            losses.backward()
            optimizer.step()
            
            epoch_loss += losses.item()
            
            # Compute IoU for evaluation
            with torch.no_grad():
                model.eval()
                predictions = model(images)
                for i, prediction in enumerate(predictions):
                    pred_boxes = prediction["boxes"].cpu().numpy()
                    true_boxes = targets[i]["boxes"].cpu().numpy()
                    for pred_box in pred_boxes:
                        for true_box in true_boxes:
                            iou = compute_iou(pred_box, true_box)
                            total_ious += iou
                            num_boxes += 1
                model.train()
        
        avg_loss = epoch_loss / len(train_loader)
        avg_iou = total_ious / num_boxes if num_boxes != 0 else 0
        loss_values.append(avg_loss)
        iou_values.append(avg_iou)
        print(f"Epoch {epoch+1}/{num_epochs} Loss: {avg_loss} Avg IoU: {avg_iou}")
    
    # Plotting loss and IoU values
    plt.figure(figsize=(12, 5))
    plt.subplot(1, 2, 1)
    plt.plot(loss_values, label="Training Loss")
    plt.title("Training Loss across Epochs")
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    
    plt.subplot(1, 2, 2)
    plt.plot(iou_values, label="IoU")
    plt.title("IoU across Epochs")
    plt.xlabel("Epochs")
    plt.ylabel("IoU")
    plt.show()

    # Save model after training
    save_model(model)

# Validation function
def validate_model(model, val_loader, device):
    model.eval()
    model.to(device)
    
    with torch.no_grad():
        for images, targets in val_loader:
            images = [image.to(device) for image in images]
            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]
            model(images)

# Paths to your data
image_dir = "tuberculosis-phonecamera"
annotation_dir = "tuberculosis-phonecamera"

# Split data
train_images, val_images = split_data(image_dir)

# Create datasets and dataloaders
train_dataset = TuberculosisDataset(image_dir, annotation_dir, train_images, transform=data_transform)
val_dataset = TuberculosisDataset(image_dir, annotation_dir, val_images, transform=data_transform)

# Updated DataLoader with new collate function
train_loader = DataLoader(train_dataset, batch_size=4, shuffle=True, collate_fn=collate_fn)
val_loader = DataLoader(val_dataset, batch_size=4, shuffle=False, collate_fn=collate_fn)

# Model and optimizer
model = get_ssd_model_for_finetuning(2)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# Train and validate
train_model(model, train_loader, optimizer, device="cuda", num_epochs=10)
validate_model(model, val_loader, device="cuda")


#######################################Print Metrics######################################
def calculate_metrics(predictions, ground_truths, iou_threshold=0.5):
    TP = 0  # True Positives
    FP = 0  # False Positives
    FN = 0  # False Negatives
    total_iou = 0  # to calculate mean IoU

    for pred, gt in zip(predictions, ground_truths):
        pred_boxes = pred["boxes"].cpu().numpy()
        gt_boxes = gt["boxes"].cpu().numpy()

        # Match predicted boxes to ground truth boxes
        for pred_box in pred_boxes:
            max_iou = 0
            matched = False
            for gt_box in gt_boxes:
                iou = compute_iou(pred_box, gt_box)
                if iou > max_iou:
                    max_iou = iou
                    if iou > iou_threshold:
                        matched = True

            total_iou += max_iou
            if matched:
                TP += 1
            else:
                FP += 1

        FN += len(gt_boxes) - TP

    precision = TP / (TP + FP) if (TP + FP) != 0 else 0
    recall = TP / (TP + FN) if (TP + FN) != 0 else 0
    f1_score = (2 * precision * recall) / (precision + recall) if (precision + recall) != 0 else 0
    mean_iou = total_iou / (TP + FP) if (TP + FP) != 0 else 0

    return precision, recall, f1_score, mean_iou

def evaluate_model(model, dataloader, device):
    model.eval()
    model.to(device)
    all_predictions = []
    all_ground_truths = []

    with torch.no_grad():
        for images, targets in dataloader:
            images = [image.to(device) for image in images]
            predictions = model(images)

            all_predictions.extend(predictions)
            all_ground_truths.extend(targets)

    precision, recall, f1_score, mean_iou = calculate_metrics(all_predictions, all_ground_truths)
    return precision, recall, f1_score, mean_iou


train_precision, train_recall, train_f1, train_iou = evaluate_model(model, train_loader, "cuda")
val_precision, val_recall, val_f1, val_iou = evaluate_model(model, val_loader, "cuda")

print("Training Set Metrics:")
print(f"Precision: {train_precision:.4f}, Recall: {train_recall:.4f}, F1 Score: {train_f1:.4f}, Mean IoU: {train_iou:.4f}")

print("\nValidation Set Metrics:")
print(f"Precision: {val_precision:.4f}, Recall: {val_recall:.4f}, F1 Score: {val_f1:.4f}, Mean IoU: {val_iou:.4f}")

#sheet
header = "| Metric    | Training Set | Validation Set |"
divider = "+----------+--------------+----------------+"

train_metrics = f"| Precision | {train_precision:.4f}      | {val_precision:.4f}          |"
recall_metrics = f"| Recall    | {train_recall:.4f}      | {val_recall:.4f}          |"
f1_metrics = f"| F1 Score  | {train_f1:.4f}      | {val_f1:.4f}          |"
iou_metrics = f"| Mean IoU  | {train_iou:.4f}      | {val_iou:.4f}          |"

print(header)
print(divider)
print(train_metrics)
print(recall_metrics)
print(f1_metrics)
print(iou_metrics)
print(divider)

#######################################Train Set######################################
import numpy as np
import matplotlib.pyplot as plt

def plot_predictions_on_image(model, dataset, device, title):
    # Select a random image from the dataset
    idx = np.random.randint(50, len(dataset))
    image, target = dataset[idx]
    img_tensor = image.clone().detach().to(device).unsqueeze(0)

    # Use the model to make predictions
    model.eval()
    with torch.no_grad():
        prediction = model(img_tensor)

    # Inverse normalization for visualization
    inv_normalize = transforms.Normalize(
        mean=[-0.485/0.229, -0.456/0.224, -0.406/0.225],
        std=[1/0.229, 1/0.224, 1/0.225]
    )
    image = inv_normalize(image)
    image = torch.clamp(image, 0, 1)
    image = F.to_pil_image(image)

    # Plot the image with ground truth boxes
    plt.figure(figsize=(10, 6))
    plt.title(title + " with Ground Truth Boxes")
    plt.imshow(image)
    ax = plt.gca()

    # Draw the ground truth boxes in blue
    for box in target["boxes"]:
        rect = plt.Rectangle(
            (box[0], box[1]), box[2]-box[0], box[3]-box[1],
            fill=False, color='blue', linewidth=2
        )
        ax.add_patch(rect)
    plt.show()

    # Plot the image with predicted boxes
    plt.figure(figsize=(10, 6))
    plt.title(title + " with Predicted Boxes")
    plt.imshow(image)
    ax = plt.gca()

    # Draw the predicted boxes in red
    for box in prediction[0]["boxes"].cpu():
        rect = plt.Rectangle(
            (box[0], box[1]), box[2]-box[0], box[3]-box[1],
            fill=False, color='red', linewidth=2
        )
        ax.add_patch(rect)
    plt.show()

# Call the function for a random image from the train dataset
plot_predictions_on_image(model, train_dataset, "cuda", "Selected from Training Set")


#######################################Val Set######################################

# Call the function for a random image from the validation dataset
plot_predictions_on_image(model, val_dataset, "cuda", "Selected from Validation Set")

需要从头训练的，就不跑了。

结尾我开始摆烂了。