1.FCN是用深度神经网络来做语义分割的奠基性工作。
2.它用转置卷积层来替换CNN最后的全连接层，从而可以实现每个像素的预测。
%matplotlib inline
import torch
import torchvision
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l
使用在ImageNet数据集上预训练的ResNet-18模型来提取图像特征，并将该网络记为pretrained_net。
pretrained_net = torchvision.models.resnet18(pretrained=True)
list(pretrained_net.children())[-3:]
/usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /root/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
100%|██████████| 44.7M/44.7M [00:00<00:00, 66.5MB/s]
[Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
),
AdaptiveAvgPool2d(output_size=(1, 1)),
Linear(in_features=512, out_features=1000, bias=True)]
创建一个全卷积网络net。 它复制了ResNet-18中大部分的预训练层，除了最后的全局平均汇聚层和最接近输出的全连接层。
net = nn.Sequential(*list(pretrained_net.children())[:-2])
给定高度为320和宽度为480的输入，net的前向传播将输入的高和宽减小至原来的1/32
，即10和15。
X = torch.rand(size=(1, 3, 320, 480))
net(X).shape
torch.Size([1, 512, 10, 15])
我们构造一个步幅为32的转置卷积层，并将卷积核的高和宽设为64，填充为16。使用1X1卷积层 将输出通道转换为Pascal VOC2012数据集的类数是21类，将要素地图的高度和宽度增加32倍。
num_classes = 21
net.add_module('final_conv', nn.Conv2d(512, num_classes, kernel_size=1))
net.add_module('transpose_conv', nn.ConvTranspose2d(num_classes, num_classes,
kernel_size=64, padding=16, stride=32))
初始化转置卷积层
双线性插值的上采样可以通过转置卷积层实现，内核由以下bilinear_kernel函数构造。 限于篇幅，我们只给出bilinear_kernel函数的实现，不讨论算法的原理。
def bilinear_kernel(in_channels, out_channels, kernel_size):
factor = (kernel_size + 1) // 2
if kernel_size % 2 == 1:
center = factor - 1
else:
center = factor - 0.5
og = (torch.arange(kernel_size).reshape(-1, 1),
torch.arange(kernel_size).reshape(1, -1))
filt = (1 - torch.abs(og[0] - center) / factor) * \
(1 - torch.abs(og[1] - center) / factor)
weight = torch.zeros((in_channels, out_channels,
kernel_size, kernel_size))
weight[range(in_channels), range(out_channels), :, :] = filt
return weight
我们用双线性插值的上采样实验它由转置卷积层实现。 我们构造一个将输入的高和宽放大2倍的转置卷积层，并将其卷积核用bilinear_kernel函数初始化。
conv_trans = nn.ConvTranspose2d(3, 3, kernel_size=4, padding=1, stride=2,
bias=False)
conv_trans.weight.data.copy_(bilinear_kernel(3, 3, 4));
读取图像X，将上采样的结果记作Y。
img = torchvision.transforms.ToTensor()(d2l.Image.open('catdog.jpg'))
X = img.unsqueeze(0)
Y = conv_trans(X)
out_img = Y[0].permute(1, 2, 0).detach()
转置卷积层将图像的高和宽分别放大了2倍，除了坐标轴大小发生变化，图片不受影响
d2l.set_figsize()
print('input image shape:', img.permute(1, 2, 0).shape)
d2l.plt.imshow(img.permute(1, 2, 0));
print('output image shape:', out_img.shape)
d2l.plt.imshow(out_img);
input image shape: torch.Size([561, 728, 3])
output image shape: torch.Size([1122, 1456, 3])
全卷积网络用双线性插值的上采样初始化转置卷积层。对于1X1卷积层，我们使用Xavier初始化参数
W = bilinear_kernel(num_classes, num_classes, 64)
net.transpose_conv.weight.data.copy_(W);
指定随机裁剪的输出图像的形状为320X480：高和宽都可以被32整除。
batch_size, crop_size = 32, (320, 480)
train_iter, test_iter = d2l.load_data_voc(batch_size, crop_size)
Downloading ../data/VOCtrainval_11-May-2012.tar from http://d2l-data.s3-accelerate.amazonaws.com/VOCtrainval_11-May-2012.tar...
read 1114 examples
/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:558: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(_create_warning_msg(
read 1078 examples
训练
这里的损失函数和准确率计算与图像分类中的并没有本质上的不同，因为我们使用转置卷积层的通道来预测像素的类别，所以需要在损失计算中指定通道维。 此外，模型基于每个像素的预测类别是否正确来计算准确率。
def loss(inputs, targets):
return F.cross_entropy(inputs, targets, reduction='none').mean(1).mean(1)
num_epochs, lr, wd, devices = 5, 0.001, 1e-3, d2l.try_all_gpus()
trainer = torch.optim.SGD(net.parameters(), lr=lr, weight_decay=wd)
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)
loss 0.428, train acc 0.866, test acc 0.851
22.8 examples/sec on [device(type='cuda', index=0)]
预测
将输入图像在各个通道做标准化，并转成卷积神经网络所需要的四维输入格式。
def predict(img):
X = test_iter.dataset.normalize_image(img).unsqueeze(0)
pred = net(X.to(devices[0])).argmax(dim=1)
return pred.reshape(pred.shape[1], pred.shape[2])
为了可视化预测的类别给每个像素，我们将预测类别映射回它们在数据集中的标注颜色。
def label2image(pred):
colormap = torch.tensor(d2l.VOC_COLORMAP, device=devices[0])
X = pred.long()
return colormap[X, :]
读取几张较大的测试图像，并从图像的左上角开始截取形状为320X480的区域用于预测。 对于这些测试图像，我们逐一打印它们截取的区域，再打印预测结果，最后打印标注的类别。
voc_dir = d2l.download_extract('voc2012', 'VOCdevkit/VOC2012')
test_images, test_labels = d2l.read_voc_images(voc_dir, False)
n, imgs = 4, []
for i in range(n):
crop_rect = (0, 0, 320, 480)
X = torchvision.transforms.functional.crop(test_images[i], *crop_rect)
pred = label2image(predict(X))
imgs += [X.permute(1,2,0), pred.cpu(),
torchvision.transforms.functional.crop(
test_labels[i], *crop_rect).permute(1,2,0)]
d2l.show_images(imgs[::3] + imgs[1::3] + imgs[2::3], 3, n, scale=2);
