2. pytorch读数据
可以numpy读数据，然后torch.from_numpy转化成torch数据。pytorch中提供了torchvision包可以读入常用的图像数据集CIFAR10,MNIST,也有针对于这些图像的简单变换。
import torchvision.datasets
import torch.utils.data.DataLoader
import torchvision.transforms as transforms读图像常用的包有 opencv、scikit-image、matplot等
import cv2
import matplotlib.pyplot as plt
import skimage读文件常用的包有pandas(解析cvs文件)…
import pandas as pd2.1 数据集类
在pytorch中，用torch.utils.data.Dataset描述数据集类，在使用自己的数据时，需要重写len_和_getitem两个方法。数据集一般用dict封装，以faceLandmark为例，构造函数__init读取的是图像的索引，len则返回数据集的长度，getitem则把数据集封装成dict类型，用来读取某个特定的图像
class FaceLandmarksDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, csv_file, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.landmarks_frame = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.landmarks_frame)
def __getitem__(self, idx):
img_name = os.path.join(self.root_dir,
self.landmarks_frame.iloc[idx, 0])
image = io.imread(img_name)
landmarks = self.landmarks_frame.iloc[idx, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)
sample = {'image': image, 'landmarks': landmarks}
if self.transform:
sample = self.transform(sample)
return sample定义好数据类之后，读取数据时只要实例化这个类即可，如下表示实例化类并显示前四幅图像
face_dataset = FaceLandmarksDataset(csv_file='faces/face_landmarks.csv',
root_dir='faces/')
fig = plt.figure()
for i in range(len(face_dataset)):
sample = face_dataset[i]
print(i, sample['image'].shape, sample['landmarks'].shape)
ax = plt.subplot(1, 4, i + 1)
plt.tight_layout()
ax.set_title('Sample #{}'.format(i))
ax.axis('off')
show_landmarks(**sample)
if i == 3:
plt.show()
break2.2图像数据的变换
图像调整大小主要借助skimage包中的transform来实现：
img=transform.resize(old_image,(new_h,new_w))这里，我们可以用别人写好的用于变换的类：
lass Rescale(object):
"""Rescale the image in a sample to a given size.
Args:
output_size (tuple or int): Desired output size. If tuple, output is
matched to output_size. If int, smaller of image edges is matched
to output_size keeping aspect ratio the same.
"""
def __init__(self, output_size):
assert isinstance(output_size, (int, tuple))
self.output_size = output_size
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
h, w = image.shape[:2]
if isinstance(self.output_size, int):
if h > w:
new_h, new_w = self.output_size * h / w, self.output_size
else:
new_h, new_w = self.output_size, self.output_size * w / h
else:
new_h, new_w = self.output_size
new_h, new_w = int(new_h), int(new_w)
img = transform.resize(image, (new_h, new_w))
# h and w are swapped for landmarks because for images,
# x and y axes are axis 1 and 0 respectively
landmarks = landmarks * [new_w / w, new_h / h]
return {'image': img, 'landmarks': landmarks}
class RandomCrop(object):
"""Crop randomly the image in a sample.
Args:
output_size (tuple or int): Desired output size. If int, square crop
is made.
"""
def __init__(self, output_size):
assert isinstance(output_size, (int, tuple))
if isinstance(output_size, int):
self.output_size = (output_size, output_size)
else:
assert len(output_size) == 2
self.output_size = output_size
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
h, w = image.shape[:2]
new_h, new_w = self.output_size
top = np.random.randint(0, h - new_h)
left = np.random.randint(0, w - new_w)
image = image[top: top + new_h,
left: left + new_w]
landmarks = landmarks - [left, top]
return {'image': image, 'landmarks': landmarks}
class ToTensor(object):
"""Convert ndarrays in sample to Tensors."""
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
# swap color axis because
# numpy image: H x W x C
# torch image: C X H X W
image = image.transpose((2, 0, 1))
return {'image': torch.from_numpy(image),
'landmarks': torch.from_numpy(landmarks)}调整图像数据的格式主要用np中的transpose来实现,注意在numpy 中图像以H x W x C的格式存储，在torch中，图像用C x H x W存储。另外torchvision中的transfomrs.Compose可以把一系列变换组合起来，变换后的数据集可以实例化为：
transformed_dataset = FaceLandmarksDataset(csv_file='faces/face_landmarks.csv',
root_dir='faces/',
transform=transforms.Compose([
Rescale(256),
RandomCrop(224),
ToTensor()
]))
for i in range(len(transformed_dataset)):
sample = transformed_dataset[i]
print(i, sample['image'].size(), sample['landmarks'].size())
if i == 3:
break当然,torchvision也提供了现成的transforms，如下：
import torch
from torchvision import transforms, datasets
data_transform = transforms.Compose([
transforms.RandomSizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5])
])
hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',
transform=data_transform)
dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,
batch_size=4, shuffle=True,
num_workers=4)这种变换的方式最常见，
==transforms.Compose==
就是把各种变换组合，
==transforms.RandomSizeCrop(224)==
就是随机剪切，最最重要的==transforms.ToTensor()==
就是把形状为[H, W, C]的取值为[0,255]的numpy.ndarray，转换成形状为[C, H, W]，取值为[0, 1.0]的torch.FloadTensor。
还原时，使用==torch.clamp(0,1)==
最后
==transforms.Normalize==是最常见的归一化手段，把图像从[0,1]转化成[-1,1 ]
2.3 读数据
我们可以写个循环每次实例化一个数据类，然后把实例出来的图片放入网络，但这样做就忽略了深度学习中常用的Batch, shuffling 和multiprocessing.这些问题可以用pytorch 中的Dataloader来解决。导入data loader 包
import torch.utils.data.DataLoaderDataLoarder接受一个Dataset类，可以定义batch size shuffle，以及线程个数
dataloader = DataLoader(transformed_dataset, batch_size=4,shuffle=True, num_workers=4)2.4 读写模型
训练好的模型可以保存参数或者整个模型，设model为某个模型的实例，保存参数可用以下语句
torch.save(model.state_dict(),'./pretrained/model.pth')读取的时候则是
model.load_state_dict(torch.load('./pretrained/model.pth'))
