目标检测(pytorch官方教程)

1. 定义数据集

https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

数据集和相关的代码都在官网都可以下载到，一切准备工作完成之后，第一步就是构建数据集：

import os
import numpy as np
import torch
from PIL import Image
from torch.utils.data import Dataset, DataLoader
from torchvision.io import read_image
from torchvision.ops import masks_to_boxes
import torchvision

import os
import numpy as np
import torch
from PIL import Image

class PennFudanDataset(Dataset):

    def __init__(self, root, transforms=None):
        self.root = root  # 图片的根目录
        self.transforms = transforms  # 对图片做转换的函数
        # load all image files, sorting them to
        # ensure that they are aligned
        self.imgs = list(sorted(os.listdir(os.path.join(root, "PNGImages"))))  # 存放图片文件名的列表
        self.masks = list(sorted(os.listdir(os.path.join(root, "PedMasks"))))  # 存放mask文件的列表

    def __getitem__(self, idx):
        # load images and masks
        img_path = os.path.join(self.root, "PNGImages", self.imgs[idx])
        mask_path = os.path.join(self.root, "PedMasks", self.masks[idx])
        img = Image.open(img_path).convert("RGB")  # 读取图片并转换为RGB模式

        mask = Image.open(mask_path)  # mask不需要转换为RGB模式，因为mask的每个像素值都代表了一种实例

        mask = np.array(mask)  # 将mask转为array

        obj_ids = np.unique(mask)  # 去重之后的每个像素值代表了一种实例

        obj_ids = obj_ids[1:]  # 0代表背景，因此去除

        masks = mask == obj_ids[:, None, None]  # [n_masks, h, w], 构建mask的列表，每个mask的高宽和图片一致，每个mask只有实例部分值为True

        # 构建锚框
        num_objs = len(obj_ids)
        boxes = []
        for i in range(num_objs):
            pos = np.where(masks[i])
            xmin = np.min(pos[1])
            xmax = np.max(pos[1])
            ymin = np.min(pos[0])
            ymax = np.max(pos[0])
            boxes.append([xmin, ymin, xmax, ymax])

        boxes = torch.as_tensor(boxes, dtype=torch.float32)
        # 本例中只有一种类别
        labels = torch.ones((num_objs,), dtype=torch.int64)

        masks = torch.as_tensor(masks, dtype=torch.uint8)

        image_id = torch.tensor([idx])
        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])  # 计算锚框面积
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)  # iscrowd为True时，在测试阶段将会被跳过，这里假定都是False

        target = {
    
    }
        target["boxes"] = boxes
        target["labels"] = labels
        target["masks"] = masks
        target["image_id"] = image_id
        target["area"] = area
        target["iscrowd"] = iscrowd

        if self.transforms is not None:
            img, target = self.transforms(img, target)

        return img, target

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

数据转换函数如下所示，这里需要对照官网下载正确版本的包，下错了会报错：

from engine import train_one_epoch, evaluate
import utils
import transforms as T


def get_transform(train):
    transforms = []
    # converts the image, a PIL image, into a PyTorch Tensor
    transforms.append(T.ToTensor())
    if train:
        # during training, randomly flip the training images
        # and ground-truth for data augmentation
        transforms.append(T.RandomHorizontalFlip(0.5))
    return T.Compose(transforms)

2. 定义模型

加载预训练模型，并重新定义分类器

import torchvision
from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
from torchvision.models.detection.mask_rcnn import MaskRCNNPredictor


def get_instance_segmentation_model(num_classes):
    # 加载预训练模型
    model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)


    # 获取输入至分类器的特征数
    in_features = model.roi_heads.box_predictor.cls_score.in_features
    # 替换成自己重新定义的分类器
    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)

    # 获取mask分类器的输入特征数
    in_features_mask = model.roi_heads.mask_predictor.conv5_mask.in_channels
    hidden_layer = 256
    # 替换mask分类器
    model.roi_heads.mask_predictor = MaskRCNNPredictor(in_features_mask,
                                                       hidden_layer,
                                                       num_classes)

    return model

3. 训练

# use our dataset and defined transformations
dataset = PennFudanDataset('PennFudanPed', get_transform(train=True))
dataset_test = PennFudanDataset('PennFudanPed', get_transform(train=False))

# split the dataset in train and test set
torch.manual_seed(1)
indices = torch.randperm(len(dataset)).tolist()
dataset = torch.utils.data.Subset(dataset, indices[:-50])
dataset_test = torch.utils.data.Subset(dataset_test, indices[-50:])

# define training and validation data loaders
data_loader = torch.utils.data.DataLoader(
    dataset, batch_size=2, shuffle=True, num_workers=0,
    collate_fn=utils.collate_fn)

data_loader_test = torch.utils.data.DataLoader(
    dataset_test, batch_size=1, shuffle=False, num_workers=0,
    collate_fn=utils.collate_fn)

device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')

# our dataset has two classes only - background and person
num_classes = 2

# get the model using our helper function
model = get_instance_segmentation_model(num_classes)
# move model to the right device
model.to(device)

# construct an optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.005,
                            momentum=0.9, weight_decay=0.0005)

# and a learning rate scheduler which decreases the learning rate by
# 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
                                               step_size=3,
                                               gamma=0.1)

from torch.optim.lr_scheduler import StepLR
num_epochs = 5

for epoch in range(num_epochs):
    # train for one epoch, printing every 10 iterations
    train_one_epoch(model, optimizer, data_loader, device, epoch, print_freq=10)
    # update the learning rate
    lr_scheduler.step()
    # evaluate on the test dataset
    evaluate(model, data_loader_test, device=device)