46语义分割和数据集
"""
图像分割将图像划分为若干组成区域,这类问题的方法通常利用图像中像素之间的相关性。
它在训练时不需要有关图像像素的标签信息,在预测时也无法保证分割出的区域具有我们希望得到的语义。
图像分割可能会将狗分为两个区域:一个覆盖以黑色为主的嘴和眼睛,另一个覆盖以黄色为主的其余部分身体。
实例分割也叫同时检测并分割(simultaneous detection and segmentation),
它研究如何识别图像中各个目标实例的像素级区域。
与语义分割不同,实例分割不仅需要区分语义,还要区分不同的目标实例。
例如,如果图像中有两条狗,则实例分割需要区分像素属于的两条狗中的哪一条。
"""
import os
import torch
import torchvision
from d2l import torch as d2l
import matplotlib.pyplot as plt
voc_dir = '../data/VOCdevkit/VOC2012'
def read_voc_images(voc_dir, is_train=True):
"""将所有输入的图像和标签读入内存"""
txt_fname = os.path.join(voc_dir, 'ImageSets', 'Segmentation',
'train.txt' if is_train else 'val.txt')
mode = torchvision.io.image.ImageReadMode.RGB
with open(txt_fname, 'r') as f:
images = f.read().split()
features, labels = [], []
for i, fname in enumerate(images):
features.append(torchvision.io.read_image(
os.path.join(voc_dir, 'JPEGImages', f'{fname}.jpg')))
labels.append(torchvision.io.read_image(
os.path.join(voc_dir, 'SegmentationClass', f'{fname}.png'),
mode))
return features, labels
train_features, train_labels = read_voc_images(voc_dir, True)
n = 5
imgs = train_features[0:n] + train_labels[0:n]
imgs = [img.permute(1,2,0) for img in imgs]
d2l.show_images(imgs, 2, n)
plt.show()
VOC_COLORMAP = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
[0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
[64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0],
[64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128],
[0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0],
[0, 64, 128]]
VOC_CLASSES = ['background', 'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair', 'cow',
'diningtable', 'dog', 'horse', 'motorbike', 'person',
'potted plant', 'sheep', 'sofa', 'train', 'tv/monitor']
def voc_colormap2label():
"""构建从RGB到VOC类别索引的映射"""
colormap2label = torch.zeros(256 ** 3, dtype=torch.long)
for i, colormap in enumerate(VOC_COLORMAP):
colormap2label[
(colormap[0] * 256 + colormap[1]) * 256 + colormap[2]] = i
return colormap2label
def voc_label_indices(colormap, colormap2label):
"""将VOC标签中的RGB值映射到它们的类别索引"""
colormap = colormap.permute(1, 2, 0).numpy().astype('int32')
idx = ((colormap[:, :, 0] * 256 + colormap[:, :, 1]) * 256
+ colormap[:, :, 2])
return colormap2label[idx]
"""
tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 1, 1]])
aeroplane
"""
def voc_rand_crop(feature, label, height, width):
"""随机裁剪特征和标签图像"""
rect = torchvision.transforms.RandomCrop.get_params(
feature, (height, width))
feature = torchvision.transforms.functional.crop(feature, *rect)
label = torchvision.transforms.functional.crop(label, *rect)
return feature, label
imgs = []
for _ in range(n):
imgs += voc_rand_crop(train_features[0], train_labels[0], 200, 300)
imgs = [img.permute(1, 2, 0) for img in imgs]
d2l.show_images(imgs[::2] + imgs[1::2], 2, n)
"""
imgs = [0, 1, 2, 3, 4, 5]
result = imgs[::2] + imgs[1::2]
# imgs[::2] 返回 [0, 2, 4]
# imgs[1::2] 返回 [1, 3, 5]
# result 将这两个子列表连接起来,返回 [0, 2, 4, 1, 3, 5]
"""
plt.show()
class VOCSegDataset(torch.utils.data.Dataset):
"""一个用于加载VOC数据集的自定义数据集"""
def __init__(self, is_train, crop_size, voc_dir):
self.transform = torchvision.transforms.Normalize(
mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
self.crop_size = crop_size
features, labels = read_voc_images(voc_dir, is_train=is_train)
self.features = [self.normalize_image(feature)
for feature in self.filter(features)]
self.labels = self.filter(labels)
self.colormap2label = voc_colormap2label()
print('read ' + str(len(self.features)) + ' examples')
def normalize_image(self, img):
return self.transform(img.float() / 255)
def filter(self, imgs):
return [img for img in imgs if (
img.shape[1] >= self.crop_size[0] and
img.shape[2] >= self.crop_size[1])]
def __getitem__(self, idx):
feature, label = voc_rand_crop(self.features[idx], self.labels[idx],
*self.crop_size)
return (feature, voc_label_indices(label, self.colormap2label))
def __len__(self):
return len(self.features)
crop_size = (320, 480)
voc_train = VOCSegDataset(True, crop_size, voc_dir)
voc_test = VOCSegDataset(False, crop_size, voc_dir)
batch_size = 64
train_iter = torch.utils.data.DataLoader(voc_train, batch_size, shuffle=True,
drop_last=True,
num_workers=0)
for X, Y in train_iter:
print(X.shape)
print(Y.shape)
break
def load_data_voc(batch_size, crop_size):
"""加载VOC语义分割数据集"""
voc_dir = '../data/VOCdevkit/VOC2012'
num_workers = 4
train_iter = torch.utils.data.DataLoader(
VOCSegDataset(True, crop_size, voc_dir), batch_size,
shuffle=True, drop_last=True, num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(
VOCSegDataset(False, crop_size, voc_dir), batch_size,
drop_last=True, num_workers=num_workers)
return train_iter, test_iter