소스코드 원본 링크 : https://pytorch.org/tutorials/beginner/data_loading_tutorial.html
Import packages and modules
from __future__ import print_function, division
import os
import torch
import pandas as pd
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
# Ignore warnings
import warnings
warnings.filterwarnings("ignore")
plt.ion() # interactive mode
Read and Reshape
landmarks_frame = pd.read_csv('faces/face_landmarks.csv')
n = 65
img_name = landmarks_frame.iloc[n, 0]
landmarks = landmarks_frame.iloc[n, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)
print('Image name: {}'.format(img_name))
print('Landmarks shape: {}'.format(landmarks.shape))
print('First 4 Landmarks: {}'.format(landmarks[:4]))
csv파일을 읽은 후 적절하게 데이터 set을 변환해준다.
show_landmarks
def show_landmarks(image, landmarks):
"""Show image with landmarks"""
plt.imshow(image)
plt.scatter(landmarks[:, 0], landmarks[:, 1], s=10, marker='.', c='r')
plt.pause(0.001) # pause a bit so that plots are updated
plt.figure()
show_landmarks(io.imread(os.path.join('faces/', img_name)),
landmarks)
plt.show()
랜드마크를 이미지에 표시해주는 함수이다.
데이터 클래스
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
위에서 다뤘던 코드들을 클래스의 메소드에서 처리할 수 있도록 통합하였다.
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()
break
얼굴 이미지와 랜드마크를 보여주는 코드이다. shape을 print해서 size를 확인해보면 모든 이미지는 랜드마크 (68,2) shape을 갖는다. 하지만 이미지는 shape에서 height, width가 다르기 때문에 학습을 위해 같게 만들어줘야한다.
Rescale, RandomCrop, ToTensor
class 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)}
Rescale, RandomCrop은 각각 __init__과 __call__을 갖는다. __call__은 클래스를 함수처럼 호출시킬 수 있다. __init__에서 tuple인지 int인지 체크하고 output_size를 결정한다. Rescale은 간단하지만 RandomCrop에서 landmarks = landmarks - [left, top] 하는 이유는 Crop 후에 랜드마크의 좌표도 옮겨주어야 하기 때문이다. ToTensor에서 numpy -> torch 로 변환할 때 이미지 transpose 처리를 해야 하는 것을 잊지 말자.
scale = Rescale(256)
crop = RandomCrop(128)
composed = transforms.Compose([Rescale(256),
RandomCrop(224)])
# Apply each of the above transforms on sample.
fig = plt.figure()
sample = face_dataset[65]
for i, tsfrm in enumerate([scale, crop, composed]):
transformed_sample = tsfrm(sample)
ax = plt.subplot(1, 3, i + 1)
plt.tight_layout()
ax.set_title(type(tsfrm).__name__)
show_landmarks(**transformed_sample)
plt.show()
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
Using DataLoader
지금까지 데이터를 읽어 들이고 선처리 하는 등 별 문제가 없어보였다. 하지만 우리는 3가지에 대해 더 다뤄야한다.
- Batching the data
- Shuffling the data
- Load the data in parallel using multiprocessing workers
이 3가지를 쉽게 다루기 위해서 DataLoader를 사용할 것이다.
dataloader = DataLoader(transformed_dataset, batch_size=4,
shuffle=True, num_workers=4)
# Helper function to show a batch
def show_landmarks_batch(sample_batched):
"""Show image with landmarks for a batch of samples."""
images_batch, landmarks_batch = \
sample_batched['image'], sample_batched['landmarks']
batch_size = len(images_batch)
im_size = images_batch.size(2)
grid = utils.make_grid(images_batch)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
for i in range(batch_size):
plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size,
landmarks_batch[i, :, 1].numpy(),
s=10, marker='.', c='r')
plt.title('Batch from dataloader')
for i_batch, sample_batched in enumerate(dataloader):
print(i_batch, sample_batched['image'].size(),
sample_batched['landmarks'].size())
# observe 4th batch and stop.
if i_batch == 3:
plt.figure()
show_landmarks_batch(sample_batched)
plt.axis('off')
plt.ioff()
plt.show()
break
import torch
from torchvision import transforms, datasets
data_transform = transforms.Compose([
transforms.RandomSizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
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)