DeepLearning-语义分割数据处理实例
作者:互联网
数据集:Pascal VOC2012, 参考材料:动手学深度学习
以下示例实现了对数据的预读取,处理等操作
import os
from random import shuffle
from turtle import width
import torch
import torchvision
from d2l import torch as d2l
voc_dir = "./dataset/VOC2012/"# 数据读取
def read_voc_images(voc_dir, is_train=True):
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)
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
#@save
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]
y = voc_label_indices(train_labels[0], voc_colormap2label())
def voc_rand_crop(feature, labek, height, weight):
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]
#@save
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=d2l.get_dataloader_workers())
for X, Y in train_iter:
print(X.shape)
print(Y.shape)
break
标签:features,voc,self,语义,crop,128,train,DeepLearning,数据处理 来源: https://www.cnblogs.com/cjjcn/p/16180065.html