网站空间期限查询,网站备案号官网,网站建设上市公司,怎么下载建筑工程网基于WIN10的64位系统演示
一、写在前面
本期开始#xff0c;我们继续学习深度学习图像目标检测系列#xff0c;FCOS#xff08;Fully Convolutional One-Stage Object Detection#xff09;模型。 二、FCOS简介
FCOS#xff08;Fully Convolutional One-Stage Object D…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FCOSFully Convolutional One-Stage Object Detection模型。 二、FCOS简介
FCOSFully Convolutional One-Stage Object Detection是一种无锚框的目标检测方法由 Tian et al. 在 2019 年提出。与传统的基于锚框的目标检测方法如 Faster R-CNN 和 SSD不同FCOS 完全摒弃了锚框的概念使得模型结构更为简洁和高效。
以下是 FCOS 模型的主要特点
1无锚框设计
FCOS 不使用预定义的锚框来生成候选框。相反它直接在特征图上的每个位置进行预测。这消除了与锚框大小和形状相关的超参数简化了模型设计。
2位置编码
对于特征图上的每个位置FCOS 不仅预测类别分数还预测与真实边界框的四个边的距离。这四个距离值为左、右、上、下与目标中心的相对距离。
3训练时的位置限制
为了使每个位置只对特定大小的目标负责FCOS 在训练时为特征图的每个层级引入了一个目标大小的范围。这确保了大的物体由底层的特征图来检测小的物体由高层的特征图来检测。
4中心性偏置
由于物体的中心位置通常包含更明确的语义信息FCOS 引入了一个中心性分支来预测每个位置是否接近物体的中心。这有助于减少检测的假阳性。
5简洁与高效
由于其无锚框的设计FCOS 的结构相对简单计算量较小但在多个标准数据集上的性能与其他一流的目标检测方法相当或更好。 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、FCOS实战
直接上代码
import os
import random
import torch
import torchvision
from torchvision.models.detection import fcos_resnet50_fpn
from torchvision.models.detection.fcos import FCOS_ResNet50_FPN_Weights
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 validif xmin xmax and ymin ymax:boxes.append((xmin, ymin, xmax, ymax))else:print(fWarning: 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_ratio0.8):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, transformNone):self.image_dir image_dirself.annotation_dir annotation_dirself.image_list image_listself.transform transformdef __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 Noneif len(boxes) 0:return Noneboxes torch.as_tensor(boxes, dtypetorch.float32)labels torch.ones((len(boxes),), dtypetorch.int64)iscrowd torch.zeros((len(boxes),), dtypetorch.int64)target {}target[boxes] boxestarget[labels] labelstarget[image_id] torch.tensor([idx])target[iscrowd] iscrowd# Apply transformationsif 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 tensortorchvision.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_fcos_model_for_finetuning(num_classes):# Load an FCOS model with a ResNet-50-FPN backbone without pre-trained weightsmodel fcos_resnet50_fpn(weightsNone, num_classesnum_classes)return model# Function to save the model
def save_model(model, pathfcos_mtb.pth, save_full_modelFalse):if save_full_model:torch.save(model, path)else:torch.save(model.state_dict(), path)print(fModel 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 emptyreturn [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_epochs10):model.train()model.to(device)loss_values []iou_values []for epoch in range(num_epochs):epoch_loss 0.0total_ious 0num_boxes 0for images, targets in train_loader:# Skip batches with placeholder dataif len(targets) 1 and not targets[0]:continue# Skip batches with empty targetsif any(len(target[boxes]) 0 for target in targets):continueimages [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 evaluationwith 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 iounum_boxes 1model.train()avg_loss epoch_loss / len(train_loader)avg_iou total_ious / num_boxes if num_boxes ! 0 else 0loss_values.append(avg_loss)iou_values.append(avg_iou)print(fEpoch {epoch1}/{num_epochs} Loss: {avg_loss} Avg IoU: {avg_iou})# Plotting loss and IoU valuesplt.figure(figsize(12, 5))plt.subplot(1, 2, 1)plt.plot(loss_values, labelTraining Loss)plt.title(Training Loss across Epochs)plt.xlabel(Epochs)plt.ylabel(Loss)plt.subplot(1, 2, 2)plt.plot(iou_values, labelIoU)plt.title(IoU across Epochs)plt.xlabel(Epochs)plt.ylabel(IoU)plt.show()# Save model after trainingsave_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, transformdata_transform)
val_dataset TuberculosisDataset(image_dir, annotation_dir, val_images, transformdata_transform)# Updated DataLoader with new collate function
train_loader DataLoader(train_dataset, batch_size4, shuffleTrue, collate_fncollate_fn)
val_loader DataLoader(val_dataset, batch_size4, shuffleFalse, collate_fncollate_fn)# Model and optimizer
model get_fcos_model_for_finetuning(2)
optimizer torch.optim.Adam(model.parameters(), lr0.001)# Train and validate
train_model(model, train_loader, optimizer, devicecuda, num_epochs100)
validate_model(model, val_loader, devicecuda)#######################################Print Metrics######################################
def calculate_metrics(predictions, ground_truths, iou_threshold0.5):TP 0 # True PositivesFP 0 # False PositivesFN 0 # False Negativestotal_iou 0 # to calculate mean IoUfor 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 boxesfor pred_box in pred_boxes:max_iou 0matched Falsefor gt_box in gt_boxes:iou compute_iou(pred_box, gt_box)if iou max_iou:max_iou iouif iou iou_threshold:matched Truetotal_iou max_iouif matched:TP 1else:FP 1FN len(gt_boxes) - TPprecision TP / (TP FP) if (TP FP) ! 0 else 0recall TP / (TP FN) if (TP FN) ! 0 else 0f1_score (2 * precision * recall) / (precision recall) if (precision recall) ! 0 else 0mean_iou total_iou / (TP FP)return precision, recall, f1_score, mean_ioudef 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_ioutrain_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(fPrecision: {train_precision:.4f}, Recall: {train_recall:.4f}, F1 Score: {train_f1:.4f}, Mean IoU: {train_iou:.4f})print(\nValidation Set Metrics:)
print(fPrecision: {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 pltdef plot_predictions_on_image(model, dataset, device, title):# Select a random image from the datasetidx np.random.randint(5, len(dataset))image, target dataset[idx]img_tensor image.clone().detach().to(device).unsqueeze(0)# Use the model to make predictionsmodel.eval()with torch.no_grad():prediction model(img_tensor)# Inverse normalization for visualizationinv_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 boxesplt.figure(figsize(10, 6))plt.title(title with Ground Truth Boxes)plt.imshow(image)ax plt.gca()# Draw the ground truth boxes in bluefor box in target[boxes]:rect plt.Rectangle((box[0], box[1]), box[2]-box[0], box[3]-box[1],fillFalse, colorblue, linewidth2)ax.add_patch(rect)plt.show()# Plot the image with predicted boxesplt.figure(figsize(10, 6))plt.title(title with Predicted Boxes)plt.imshow(image)ax plt.gca()# Draw the predicted boxes in redfor box in prediction[0][boxes].cpu():rect plt.Rectangle((box[0], box[1]), box[2]-box[0], box[3]-box[1],fillFalse, colorred, linewidth2)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)
这回是从头训练的因此结果不理想
1loss曲线图 2性能指标 3训练的图片测试结果 4验证集的图片测试结果 五、写在后面
这回没有使用预训练模型因为在运行过程中有个问题还没解决因此只能从头训练但默认参数也没达到很好的效果。哪位大佬解决了告诉我一声~
