def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(), #随机水平翻转
tr.RandomScaleCrop(base_size=self.args.base_size,
crop_size=self.args.crop_size), #随机尺寸裁剪
tr.RandomGaussianBlur(), #随机高斯模糊
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)), #归一化
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
if not self.random_match:
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(),
tr.RandomScaleCrop(base_size=400, crop_size=400, fill=0),
#tr.Remap(self.building_table, self.nonbuilding_table, self.channels)
tr.RandomGaussianBlur(),
#tr.ConvertFromInts(),
#tr.PhotometricDistort(),
tr.Normalize(mean=self.source_dist['mean'],
std=self.source_dist['std']),
tr.ToTensor(),
])
else:
composed_transforms = transforms.Compose([
tr.HistogramMatching(),
tr.RandomHorizontalFlip(),
tr.RandomScaleCrop(base_size=400, crop_size=400, fill=0),
tr.RandomGaussianBlur(),
tr.Normalize(mean=self.source_dist['mean'],
std=self.source_dist['std']),
tr.ToTensor(),
])
return composed_transforms(sample)
from torchvision import datasets, transforms
import torch.utils.data as data
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from PIL import Image
import os
import custom_transforms as trans
img_transform = transforms.Compose([
trans.RandomHorizontalFlip(),
trans.RandomGaussianBlur(),
trans.RandomScaleCrop(700, 512),
trans.Normalize(),
trans.ToTensor()
])
class TrainImageFolder(data.Dataset):
def __init__(self, data_dir):
self.f = open(os.path.join(data_dir, 'train_id.txt'))
self.file_list = self.f.readlines()
self.data_dir = data_dir
def __getitem__(self, index):
img = Image.open(
os.path.join(self.data_dir, 'train_images',
self.file_list[index][:-1] + '.jpg')).convert('RGB')
parse = Image.open(
os.path.join(self.data_dir, 'train_segmentations',
num_workers=4)
for item in dataloader:
train = item['image']
# train = np.array(train) #?
print(train.shape)
print('sample {} images to calculate'.format(train.shape[0]))
mean = np.mean(train.numpy(), axis=(0, 2, 3))
std = np.std(train.numpy(), axis=(0, 2, 3))
return mean, std
if __name__ == '__main__':
trs = tf.Compose([
tr.RandomHorizontalFlip(),
tr.RandomScaleCrop(base_size=512, crop_size=512),
tr.RandomGaussianBlur(), #高斯模糊
tr.Normalize(mean=LungDataset.mean, std=LungDataset.std),
tr.ToTensor()
])
dataset = LungDataset(root_dir=r'D:\code\U-net',
transforms=trs,
train=True)
# dataset = LungDataset(root_dir=r'D:\code\U-net', transforms = False , train=True)
# print(dataset.get_mean_std())
for item in dataset:
# print(item['label'].shape)
# plt.imshow(image, cmap='gray')
# print(item['image'])
print(item['image'].min(), item['image'].max(), item['label'].min(),
item['label'].max())