语义分割系列18-FPN(pytorch实现)

FPN:《Panoptic Feature Pyramid Networks》

发布于2019CVPR

FPN在实例分割中取得巨大成功(Mask R-Cnn)后,进军语义分割,结果发现FPN在语义分割中能够提供轻巧的网络结构、快速的分割速度、精确的分割结果。于是,作者提出了Panoptic FPN来完成语义分割任务。


论文

FPN在实例分割网络中扮演了及其重要的角色,作者思考后将其引入语义分割领域,同时也对原始的FPN做了对应的修改。

语义分割系列18-FPN(pytorch实现)_第1张图片

FPN-Semantic segmentation branch

语义分割系列18-FPN(pytorch实现)_第2张图片

为了实现从FPN中输出语义结果的功能,作者将FPN金字塔每一层的输出合并为单个输出,已最深层为例,1/32的特征图,经过3次卷积和2倍上采样后,输出为1/4大小的特征图。其余层也经过类似的方法生成类似的结果,然后相加成一个输出。经过卷积和上采样后生成语义结果。

与Unet直接将各对应层的结果在通道上相加不同,FPN在每一层的连接中间加了卷积和上采样,这样主干网络的下采样层也可以获得更自由的结果,更加灵活。


模型复现

主干网络Resnet50

import torch
import torch.nn as nn

class BasicBlock(nn.Module):
    expansion: int = 4
    def __init__(self, inplanes, planes, stride = 1, downsample = None, groups = 1,
        base_width = 64, dilation = 1, norm_layer = None):
        
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError("BasicBlock only supports groups=1 and base_width=64")
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = nn.Conv2d(inplanes, planes ,kernel_size=3, stride=stride, 
                               padding=dilation,groups=groups, bias=False,dilation=dilation)
        
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(planes, planes ,kernel_size=3, stride=stride, 
                               padding=dilation,groups=groups, bias=False,dilation=dilation)
        
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample= None,
        groups = 1, base_width = 64, dilation = 1, norm_layer = None,):
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.0)) * groups
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, stride=1, bias=False)
        self.bn1 = norm_layer(width)
        self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride, bias=False, padding=dilation, dilation=dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = nn.Conv2d(width, planes * self.expansion, kernel_size=1, stride=1, bias=False)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)
        return out


class ResNet(nn.Module):
    def __init__(
        self,block, layers,num_classes = 1000, zero_init_residual = False, groups = 1,
        width_per_group = 64, replace_stride_with_dilation = None, norm_layer = None):
        super(ResNet, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer
        self.inplanes = 64
        self.dilation = 2
        if replace_stride_with_dilation is None:
            # each element in the tuple indicates if we should replace
            # the 2x2 stride with a dilated convolution instead
            replace_stride_with_dilation = [False, False, False]
            
        if len(replace_stride_with_dilation) != 3:
            raise ValueError(
                "replace_stride_with_dilation should be None "
                f"or a 3-element tuple, got {replace_stride_with_dilation}"
            )
        self.groups = groups
        self.base_width = width_per_group
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = norm_layer(self.inplanes)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dilate=replace_stride_with_dilation[0])
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dilate=replace_stride_with_dilation[1])
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dilate=replace_stride_with_dilation[2])
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        # Zero-initialize the last BN in each residual branch,
        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)  # type: ignore[arg-type]
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)  # type: ignore[arg-type]

    def _make_layer(
        self,
        block,
        planes,
        blocks,
        stride = 1,
        dilate = False,
    ):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        if dilate:
            self.dilation *= stride
            stride = stride
            
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes,  planes * block.expansion, kernel_size=1, stride=stride, bias=False),
                norm_layer(planes * block.expansion))

        layers = []
        layers.append(
            block(
                self.inplanes, planes, stride, downsample, self.groups, self.base_width, previous_dilation, norm_layer
            )
        )
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(
                block(
                    self.inplanes,
                    planes,
                    groups=self.groups,
                    base_width=self.base_width,
                    dilation=self.dilation,
                    norm_layer=norm_layer,
                )
            )
        return nn.Sequential(*layers)

    def _forward_impl(self, x):
        out = []
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)
        x = self.layer1(x)
        out.append(x)
        x = self.layer2(x)
        out.append(x)
        x = self.layer3(x)
        out.append(x)
        x = self.layer4(x)
        out.append(x)
        
        return out

    def forward(self, x) :
        return self._forward_impl(x)
    def _resnet(block, layers, pretrained_path = None, **kwargs,):
        model = ResNet(block, layers, **kwargs)
        if pretrained_path is not None:
            model.load_state_dict(torch.load(pretrained_path),  strict=False)
        return model
    
    def resnet50(pretrained_path=None, **kwargs):
        return ResNet._resnet(Bottleneck, [3, 4, 6, 3],pretrained_path,**kwargs)
    
    def resnet101(pretrained_path=None, **kwargs):
        return ResNet._resnet(Bottleneck, [3, 4, 23, 3],pretrained_path,**kwargs)

FPN

import numpy as np
import torch.nn as nn

class FPNHead(nn.Module):
    def __init__(self, feature_strides=[4, 8, 16, 32], in_channels=[256, 512, 1024, 2048], channels=256, align_corners=True):
        super(FPNHead, self).__init__()
        self.in_channels = in_channels
        self.channels = channels
        self.align_corners = align_corners
        assert len(feature_strides) == len(self.in_channels)
        assert min(feature_strides) == feature_strides[0]
        self.feature_strides = feature_strides

        self.scale_heads = nn.ModuleList()
        for i in range(len(feature_strides)):
            head_length = max(
                1,
                int(np.log2(feature_strides[i]) - np.log2(feature_strides[0])))
            scale_head = []
            
            for k in range(head_length):
                scale_head.append(
                    nn.Conv2d(
                        self.in_channels[i] if k == 0 else self.channels,
                        self.channels,
                        3,
                        padding=1))
                if feature_strides[i] != feature_strides[0]:
                    scale_head.append(
                        nn.Upsample(
                            scale_factor=2,
                            mode='bilinear',
                            align_corners=self.align_corners))
            self.scale_heads.append(nn.Sequential(*scale_head))

    def forward(self, inputs):
        x = inputs[-len(inputs):]
        output = self.scale_heads[0](x[0])
        for i in range(1, len(self.feature_strides)):
            # non inplace
            output = output + nn.functional.interpolate(
                self.scale_heads[i](x[i]),
                size=output.shape[2:],
                mode='bilinear',
                align_corners=self.align_corners)

        return output

FPNNet

import torch
import torch.nn as nn

class FPNNet(nn.Module):
    def __init__(self, num_classes):
        super(FPNNet, self).__init__()
        self.num_classes = num_classes
        self.backbone = ResNet.resnet50(replace_stride_with_dilation=[1,2,4])
        self.Head = FPNHead()
        self.cls_seg = nn.Sequential(
            nn.Upsample(scale_factor=4,
                            mode='bilinear',
                            align_corners=True),
            nn.Conv2d(256, 256, 3, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.Conv2d(256, num_classes, 3, padding=1)
        )
        
    def forward(self, x):   
        x = self.backbone(x)
        x = self.Head(x)
        x = self.cls_seg(x)
        return x
        

Dataset-Camvid

# 导入库
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch import optim
from torch.utils.data import Dataset, DataLoader, random_split
from tqdm import tqdm
import warnings
warnings.filterwarnings("ignore")
import os.path as osp
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
import albumentations as A
from albumentations.pytorch.transforms import ToTensorV2
 
torch.manual_seed(17)
# 自定义数据集CamVidDataset
class CamVidDataset(torch.utils.data.Dataset):
    """CamVid Dataset. Read images, apply augmentation and preprocessing transformations.
    
    Args:
        images_dir (str): path to images folder
        masks_dir (str): path to segmentation masks folder
        class_values (list): values of classes to extract from segmentation mask
        augmentation (albumentations.Compose): data transfromation pipeline 
            (e.g. flip, scale, etc.)
        preprocessing (albumentations.Compose): data preprocessing 
            (e.g. noralization, shape manipulation, etc.)
    """
    
    def __init__(self, images_dir, masks_dir):
        self.transform = A.Compose([
            A.Resize(224, 224),
            A.HorizontalFlip(),
            A.VerticalFlip(),
            A.Normalize(),
            ToTensorV2(),
        ]) 
        self.ids = os.listdir(images_dir)
        self.images_fps = [os.path.join(images_dir, image_id) for image_id in self.ids]
        self.masks_fps = [os.path.join(masks_dir, image_id) for image_id in self.ids]
 
    
    def __getitem__(self, i):
        # read data
        image = np.array(Image.open(self.images_fps[i]).convert('RGB'))
        mask = np.array( Image.open(self.masks_fps[i]).convert('RGB'))
        image = self.transform(image=image,mask=mask)
        
        return image['image'], image['mask'][:,:,0]
        
    def __len__(self):
        return len(self.ids)
    
    
# 设置数据集路径
DATA_DIR = r'database/camvid/camvid/' # 根据自己的路径来设置
x_train_dir = os.path.join(DATA_DIR, 'train_images')
y_train_dir = os.path.join(DATA_DIR, 'train_labels')
x_valid_dir = os.path.join(DATA_DIR, 'valid_images')
y_valid_dir = os.path.join(DATA_DIR, 'valid_labels')
    
train_dataset = CamVidDataset(
    x_train_dir, 
    y_train_dir, 
)
val_dataset = CamVidDataset(
    x_valid_dir, 
    y_valid_dir, 
)
 
train_loader = DataLoader(train_dataset, batch_size=8, shuffle=True,drop_last=True)
val_loader = DataLoader(val_dataset, batch_size=8, shuffle=True,drop_last=True)

Train

model = FPNNet(num_classes=33).cuda()
#载入预训练模型
#model.load_state_dict(torch.load(r"checkpoints/Unet++_25.pth"),strict=False)

from d2l import torch as d2l
from tqdm import tqdm
import pandas as pd
#损失函数选用多分类交叉熵损失函数
lossf = nn.CrossEntropyLoss(ignore_index=255)
#选用adam优化器来训练
optimizer = optim.SGD(model.parameters(), lr=0.1)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=50, gamma=0.5, last_epoch=-1)

#训练50轮
epochs_num = 100
def train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs,scheduler,
               devices=d2l.try_all_gpus()):
    timer, num_batches = d2l.Timer(), len(train_iter)
    animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0, 1],
                            legend=['train loss', 'train acc', 'test acc'])
    net = nn.DataParallel(net, device_ids=devices).to(devices[0])
    
    loss_list = []
    train_acc_list = []
    test_acc_list = []
    epochs_list = []
    time_list = []
    
    for epoch in range(num_epochs):
        # Sum of training loss, sum of training accuracy, no. of examples,
        # no. of predictions
        metric = d2l.Accumulator(4)
        for i, (features, labels) in enumerate(train_iter):
            timer.start()
            l, acc = d2l.train_batch_ch13(
                net, features, labels.long(), loss, trainer, devices)
            metric.add(l, acc, labels.shape[0], labels.numel())
            timer.stop()
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(epoch + (i + 1) / num_batches,
                             (metric[0] / metric[2], metric[1] / metric[3],
                              None))
        test_acc = d2l.evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
        scheduler.step()
        print(f"epoch {epoch+1} --- loss {metric[0] / metric[2]:.3f} ---  train acc {metric[1] / metric[3]:.3f} --- test acc {test_acc:.3f} --- cost time {timer.sum()}")
        
        #---------保存训练数据---------------
        df = pd.DataFrame()
        loss_list.append(metric[0] / metric[2])
        train_acc_list.append(metric[1] / metric[3])
        test_acc_list.append(test_acc)
        epochs_list.append(epoch+1)
        time_list.append(timer.sum())
        
        df['epoch'] = epochs_list
        df['loss'] = loss_list
        df['train_acc'] = train_acc_list
        df['test_acc'] = test_acc_list
        df['time'] = time_list
        df.to_excel("savefile/FPNNet_camvid.xlsx")
        #----------------保存模型-------------------
        if np.mod(epoch+1, 5) == 0:
            torch.save(model.state_dict(), f'checkpoints/FPNNet_{epoch+1}.pth')
train_ch13(model, train_loader, val_loader, lossf, optimizer, epochs_num,scheduler)

Result

语义分割系列18-FPN(pytorch实现)_第3张图片

 

你可能感兴趣的:(语义分割,pytorch,深度学习,人工智能,计算机视觉,神经网络)