PyTorch学习笔记(十二) ---- PyTorch目标检测

本文链接：https://blog.csdn.net/john_bh/article/details/106490389

转载请注明作者和出处： http://blog.csdn.net/john_bh/

文章目录

1.定义数据集
2.为 PennFudan 编写自定义数据集
3. 定义模型
- 3.1 PennFudan 数据集的实例分割模型
4.训练和验证完整代码
5.总结

在文中将微调在 Penn-Fudan 数据库中对行人检测和分割的已预先训练的 Mask R-CNN 模型。它包含170个图像和345个行人实例，用它来说明如何在 torchvision 中使用新功能，以便在自定义数据集上训练实例分割模型。

另外，在 references / detection 中，有许多辅助函数来简化训练和评估检测模型。这次学习中，需要使用 references/detection/engine.py ，references/detection/utils.py 和 references/detection/transforms.py，需将它们复制到文件夹下。

1.定义数据集

对于训练对象检测的引用脚本，实例分割和人员关键点检测要求能够轻松支持添加新的自定义数据。数据集应该从标准的类torch.utils.data.Dataset 继承而来，并实现_len和_getitem_。

唯一特性是数据集的__getitem__应该返回： 图像：PIL图像大小(H,W) 目标：包含以下字段的字典

boxes(FloatTensor[N,4])：N边框（bounding boxes）坐标的格式[x0,x1,y0,y1]，取值范围是0到W,0到H。
labels(Int64Tensor[N])：每个边框的标签。
image_id(Int64Tensor[1])：图像识别器，它应该在数据集中的所有图像中是唯一的，并在评估期间使用。
area(Tensor[N])：边框的面积，在使用COCO指标进行评估时使用此项来分隔小、中和大框之间的度量标准得分。
iscrowed(UInt8Tensor[N,H,W])：在评估期间属性设置为iscrowed=True的实例会被忽略。
(可选)masks(UInt8Tesor[N,H,W])：每个对象的分段掩码。
(可选)keypoints (FloatTensor[N, K, 3]：对于N个对象中的每一个，它包含[x，y，visibility]格式的K个关键点，用于定义对象。visibility = 0表示关键点不可见。

请注意，对于数据扩充，翻转关键点的概念取决于数据表示，应该调整 reference/detection/transforms.py 以用于新的关键点表示。

如果你的模型返回上述方法，它们将使其适用于训练和评估，并将使用 pycocotools 的评估脚本。

此外，如果要在训练期间使用宽高比分组（以便每个批次仅包含具有相似宽高比的图像），则建议还实现get_height_and_width方法，该方法返回图像的高度和宽度。如果未提供此方法，将通过__getitem__查询数据集的所有元素，这会将图像加载到内存中，但比提供自定义方法时要慢。

2.为 PennFudan 编写自定义数据集

PennFudan数据集下载连接
文件结构：

PennFudanPed/
PedMasks/
FudanPed00001_mask.png
FudanPed00002_mask.png
FudanPed00003_mask.png
FudanPed00004_mask.png
…
PNGImages/
FudanPed00001.png
FudanPed00002.png
FudanPed00003.png
FudanPed00004.png

在这里插入图片描述

因此每个图像具有相应的分割掩膜，其中每个颜色对应于不同的实例。接下来为这个数据集写一个torch.utils.data.Dataset类

为数据扩充/转换编写辅助函数：

import transforms as T

def get_transform(train):
    transforms = []
    transforms.append(T.ToTensor())
    if train:
        transforms.append(T.RandomHorizontalFlip(0.5))
    return T.Compose(transforms)

3. 定义模型

现在定义一个可以上述数据集执行预测的模型。使用 Mask R-CNN，它基于 Faster R-CNN。Faster R-CNN 是一种模型，可以预测图像中潜在对象的边界框和类别得分。
在这里插入图片描述
Mask R-CNN 在 Faster R-CNN 中添加了一个额外的分支，它还预测每个实例的分割蒙版。

有两种常见情况可能需要修改 torchvision modelzoo 中的一个可用模型。第一个是想要从预先训练的模型开始，然后微调最后一层。另一种是想要用不同的模型替换模型的主干时（例如，用于更快的预测）。

下面是对这两种情况的处理。

微调已经预训练的模型,假设从一个在COCO上已预先训练过的模型开始，并希望为特定类进行微调。这是一种可行的方法：

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

# 在COCO上加载经过预训练的预训练模型
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)

# replace the classifier with a new one, that has
# 将分类器替换为具有用户定义的 num_classes的新分类器
num_classes = 2  # 1 class (person) + background
# 获取分类器的输入参数的数量
in_features = model.roi_heads.box_predictor.cls_score.in_features
# 用新的头部替换预先训练好的头部
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)

修改模型以添加不同的主干

import torchvision
from torchvision.models.detection import FasterRCNN
from torchvision.models.detection.rpn import AnchorGenerator

# 加载预先训练的模型进行分类和返回, 只有功能
backbone = torchvision.models.mobilenet_v2(pretrained=True).features
# FasterRCNN需要知道骨干网中的输出通道数量。对于mobilenet_v2，它是1280，所以需要在这里添加它
backbone.out_channels = 1280

# 让RPN在每个空间位置生成5 x 3个锚点; 具有5种不同的大小和3种不同的宽高比。 
# 有一个元组[元组[int]], 因为每个特征映射可能具有不同的大小和宽高比
anchor_generator = AnchorGenerator(sizes=((32, 64, 128, 256, 512),), aspect_ratios=((0.5, 1.0, 2.0),))

# 定义一下将用于执行感兴趣区域裁剪的特征映射，以及重新缩放后裁剪的大小。 
# 如果主干返回Tensor，则featmap_names应为[0]。更一般地，主干应该返回OrderedDict [Tensor], 并且在featmap_names中，可以选择要使用的功能映射。
roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=[0],output_size=7,sampling_ratio=2)

# 将这些pieces放在FasterRCNN模型中
model = FasterRCNN(backbone, num_classes=2,rpn_anchor_generator=anchor_generator,box_roi_pool=roi_pooler)

3.1 PennFudan 数据集的实例分割模型

因为数据集非常小，所以将遵循上述第一种情况：从预先训练的模型中进行微调。另外还要计算实例分割掩膜，将使用 Mask R-CNN：

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


def get_model_instance_segmentation(num_classes):
    # 加载在COCO上预训练的预训练的实例分割模型
    model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)

    # 获取分类器的输入特征数
    in_features = model.roi_heads.box_predictor.cls_score.in_features
    # 用新的头部替换预先训练好的头部
    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)

    # 现在获取掩膜分类器的输入特征数
    in_features_mask = model.roi_heads.mask_predictor.conv5_mask.in_channels
    hidden_layer = 256
    # 并用新的掩膜预测器替换掩膜预测器
    model.roi_heads.mask_predictor = MaskRCNNPredictor(in_features_mask,
                                                       hidden_layer,
                                                       num_classes)

    return model

这将使模型准备好的自定义数据集上进行训练和评估。

4.训练和验证完整代码

在references/detection/中，有许多辅助函数来简化训练和评估检测模型。在这里，将使用 references/detection/engine.py，references/detection/utils.py和references/detection/transforms.py。只需将它们复制到自己的文件夹并在此处使用它们。

4.1 为数据扩充/转换编写辅助函数：

import transforms as T

def get_transform(train):
    transforms = []
    transforms.append(T.ToTensor())
    if train:
        transforms.append(T.RandomHorizontalFlip(0.5))
    return T.Compose(transforms)

4.2 编写执行训练和验证的主要功能

from engine import train_one_epoch, evaluate
import utils


def main():
    # 在GPU上训练，若无GPU，可选择在CPU上训练
    device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')

    # 我们的数据集只有两个类 - 背景和人
    num_classes = 2
    # 使用我们的数据集和定义的转换
    dataset = PennFudanDataset('PennFudanPed', get_transform(train=True))
    dataset_test = PennFudanDataset('PennFudanPed', get_transform(train=False))

    # 在训练和测试集中拆分数据集
    indices = torch.randperm(len(dataset)).tolist()
    dataset = torch.utils.data.Subset(dataset, indices[:-50])
    dataset_test = torch.utils.data.Subset(dataset_test, indices[-50:])

    # 定义训练和验证数据加载器
    data_loader = torch.utils.data.DataLoader(
        dataset, batch_size=2, shuffle=True, num_workers=4,
        collate_fn=utils.collate_fn)

    data_loader_test = torch.utils.data.DataLoader(
        dataset_test, batch_size=1, shuffle=False, num_workers=4,
        collate_fn=utils.collate_fn)

    # 使用我们的辅助函数获取模型
    model = get_model_instance_segmentation(num_classes)

    # 将我们的模型迁移到合适的设备
    model.to(device)

    # 构造一个优化器
    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)
    # 和学习率调度程序
    lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
                                                   step_size=3,
                                                   gamma=0.1)

    # 训练10个epochs
    num_epochs = 10

    for epoch in range(num_epochs):
        # 训练一个epoch，每10次迭代打印一次
        train_one_epoch(model, optimizer, data_loader, device, epoch, print_freq=10)
        # 更新学习速率
        lr_scheduler.step()
        # 在测试集上评价
        evaluate(model, data_loader_test, device=device)

    print("That's it!")

在第一个epoch训练后可以得到下面的结果：

Epoch: [0] [ 0/60] eta: 0:01:18 lr: 0.000090 loss: 2.5213 (2.5213) loss_classifier: 0.8025 (0.8025) loss_box_reg: 0.2634 (0.2634) loss_mask: 1.4265 (1.4265) loss_objectness: 0.0190 (0.0190) loss_rpn_box_reg: 0.0099 (0.0099) time: 1.3121 data: 0.3024 max mem: 3485
Epoch: [0] [10/60] eta: 0:00:20 lr: 0.000936 loss: 1.3007 (1.5313) loss_classifier: 0.3979 (0.4719) loss_box_reg: 0.2454 (0.2272) loss_mask: 0.6089 (0.7953) loss_objectness: 0.0197 (0.0228) loss_rpn_box_reg: 0.0121 (0.0141) time: 0.4198 data: 0.0298 max mem: 5081
Epoch: [0] [20/60] eta: 0:00:15 lr: 0.001783 loss: 0.7567 (1.1056) loss_classifier: 0.2221 (0.3319) loss_box_reg: 0.2002 (0.2106) loss_mask: 0.2904 (0.5332) loss_objectness: 0.0146 (0.0176) loss_rpn_box_reg: 0.0094 (0.0123) time: 0.3293 data: 0.0035 max mem: 5081
Epoch: [0] [30/60] eta: 0:00:11 lr: 0.002629 loss: 0.4705 (0.8935) loss_classifier: 0.0991 (0.2517) loss_box_reg: 0.1578 (0.1957) loss_mask: 0.1970 (0.4204) loss_objectness: 0.0061 (0.0140) loss_rpn_box_reg: 0.0075 (0.0118) time: 0.3403 data: 0.0044 max mem: 5081
Epoch: [0] [40/60] eta: 0:00:07 lr: 0.003476 loss: 0.3901 (0.7568) loss_classifier: 0.0648 (0.2022) loss_box_reg: 0.1207 (0.1736) loss_mask: 0.1705 (0.3585) loss_objectness: 0.0018 (0.0113) loss_rpn_box_reg: 0.0075 (0.0112) time: 0.3407 data: 0.0044 max mem: 5081
Epoch: [0] [50/60] eta: 0:00:03 lr: 0.004323 loss: 0.3237 (0.6703) loss_classifier: 0.0474 (0.1731) loss_box_reg: 0.1109 (0.1561) loss_mask: 0.1658 (0.3201) loss_objectness: 0.0015 (0.0093) loss_rpn_box_reg: 0.0093 (0.0116) time: 0.3379 data: 0.0043 max mem: 5081
Epoch: [0] [59/60] eta: 0:00:00 lr: 0.005000 loss: 0.2540 (0.6082) loss_classifier: 0.0309 (0.1526) loss_box_reg: 0.0463 (0.1405) loss_mask: 0.1568 (0.2945) loss_objectness: 0.0012 (0.0083) loss_rpn_box_reg: 0.0093 (0.0123) time: 0.3489 data: 0.0042 max mem: 5081
Epoch: [0] Total time: 0:00:21 (0.3570 s / it)
creating index…
index created!
Test: [ 0/50] eta: 0:00:19 model_time: 0.2152 (0.2152) evaluator_time: 0.0133 (0.0133) time: 0.4000 data: 0.1701 max mem: 5081
Test: [49/50] eta: 0:00:00 model_time: 0.0628 (0.0687) evaluator_time: 0.0039 (0.0064) time: 0.0735 data: 0.0022 max mem: 5081
Test: Total time: 0:00:04 (0.0828 s / it)
Averaged stats: model_time: 0.0628 (0.0687) evaluator_time: 0.0039 (0.0064)
Accumulating evaluation results…
DONE (t=0.01s).
Accumulating evaluation results…
DONE (t=0.01s).
IoU metric: bbox
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.606
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.984
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.780
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.313
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.582
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.612
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.270
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.672
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.672
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.650
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.755
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.664
IoU metric: segm
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.704
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.979
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.871
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.325
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.488
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.727
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.316
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.748
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.749
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.650
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.673
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.758

因此，在一个epoch训练之后，我们获得了COCO-style mAP为60.6，并且mask mAP为70.4。经过训练10个epoch后，我得到了以下指标：

IoU metric: bbox
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.799
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.969
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.935
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.349
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.592
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.831
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.324
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.844
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.844
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.400
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.777
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.870
IoU metric: segm
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.761
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.969
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.919
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.341
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.464
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.788
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.303
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.799
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.799
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.400
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.769
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.818

预测结果:
在这里插入图片描述
训练的模型预测了此图像中的9个人物，让我们看看其中的几个，由下图可以看到预测效果很好。

4.3. 完整代码

# Sample code from the TorchVision 0.3 Object Detection Finetuning Tutorial
# http://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

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

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

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


class PennFudanDataset(object):
    def __init__(self, root, transforms):
        self.root = root
        self.transforms = transforms
        # load all image files, sorting them to
        # ensure that they are aligned
        self.imgs = list(sorted(os.listdir(os.path.join(root, "PNGImages"))))
        self.masks = list(sorted(os.listdir(os.path.join(root, "PedMasks"))))

    def __getitem__(self, idx):
        # load images ad 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")
        # note that we haven't converted the mask to RGB,
        # because each color corresponds to a different instance
        # with 0 being background
        mask = Image.open(mask_path)

        mask = np.array(mask)
        # instances are encoded as different colors
        obj_ids = np.unique(mask)
        # first id is the background, so remove it
        obj_ids = obj_ids[1:]

        # split the color-encoded mask into a set
        # of binary masks
        masks = mask == obj_ids[:, None, None]

        # get bounding box coordinates for each mask
        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)
        # there is only one class
        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])
        # suppose all instances are not crowd
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)

        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)

def get_model_instance_segmentation(num_classes):
    # load an instance segmentation model pre-trained pre-trained on COCO
    model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)

    # get number of input features for the classifier
    in_features = model.roi_heads.box_predictor.cls_score.in_features
    # replace the pre-trained head with a new one
    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)

    # now get the number of input features for the mask classifier
    in_features_mask = model.roi_heads.mask_predictor.conv5_mask.in_channels
    hidden_layer = 256
    # and replace the mask predictor with a new one
    model.roi_heads.mask_predictor = MaskRCNNPredictor(in_features_mask,
                                                       hidden_layer,
                                                       num_classes)

    return model


def get_transform(train):
    transforms = []
    transforms.append(T.ToTensor())
    if train:
        transforms.append(T.RandomHorizontalFlip(0.5))
    return T.Compose(transforms)


def main():
    # train on the GPU or on the CPU, if a GPU is not available
    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
    # 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
    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=4,
        collate_fn=utils.collate_fn)

    data_loader_test = torch.utils.data.DataLoader(
        dataset_test, batch_size=1, shuffle=False, num_workers=4,
        collate_fn=utils.collate_fn)

    # get the model using our helper function
    model = get_model_instance_segmentation(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
    lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
                                                   step_size=3,
                                                   gamma=0.1)

    # let's train it for 10 epochs
    num_epochs = 10

    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)

    print("That's it!")
    
if __name__ == "__main__":
    main()