目錄

 

自己認為的：

參考別人的：

對應於（自己認為的）那部分的程式碼 

---

自己認為的：

在下面的程式碼中，用到了類，其中類中的__init__(self, output_size)和__call__（self, output_size）函式，介紹一下。

當我一遍一遍的debug的時候，scale = Rescale(256)中的256賦值output_size，進行的是初始化。而沒有呼叫__call__（）。

scale = Rescale(256)
crop = RandomCrop(128)

在下面程式碼的時候，採用enumerate來返回的sample_batched（等價於Rescale和RandomCrop的類例項）來呼叫__call__（）

for i_batch, sample_batched in enumerate(dataloader):
    print(i_batch, sample_batched['image'].size(),
          sample_batched['landmarks'].size())

所以一個類例項也可以成為類似函式這樣能直接呼叫的物件，只要定義的時候有__call__()方法就可以。

參考別人的：

連結：https://www.cnblogs.com/lyu454978790/p/8630215.html

具體看下這裡：

>>>class Reader():

　　　　def __init__(self,name,nationality):

　　　　　　self.name = name

　　　　　　self.nationality = nationality

　　　　def __call__(self):

　　　　　　print('Reader: %s    Nationality: %s' % (self.name, self.nationality))

>>>r = Reader('Annie','Chinese')

>>>r()

Reader:Annie  Nationality: Chinese

__call__()方法還可以帶引數

定義一個可以直接呼叫類例項的Reader類，並可統計讀者數量

>>>class Reader():

　　　　count = 0

　　　　def __init__(self,name,nationality):
　　　　　　self.name = name
　　　　　　self.nationality = nationality
　　　　　　Reader.count += 1

　　　　def __call__(self, behave):
　　　　　　print('Reader: %s' % self.name)
　　　　　　print('Nationality: %s' % self.nationality)
　　　　　　print('%s is being %s.' % (self.name, behave))
　　　　　　print('The total number of readers is %s.' % Reader.count)

>>>a = Reader('Annie','Chinese')

>>>a('Nice')

Reader: Annie

Nationality: Chinese

Annie is being Nice.

The total number of readers is 1.

>>>b = Reader('Adam','American')

>>>b('Silly')

Reader: Adam

Nationality: American

Adam is being Silly.

The total number of readers is 2.      #自動增加

程式碼連結：https://pytorch.apachecn.org/docs/1.4/5.html

對應於（自己認為的）那部分的程式碼 

main函式

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
from Rescale import Rescale,RandomCrop,ToTensor
# Ignore warnings
import warnings

from FaceLandmarksDataset import FaceLandmarksDataset

warnings.filterwarnings("ignore")

plt.ion()   # interactive mode
landmarks_frame = pd.read_csv('./data/faces/face_landmarks.csv')

n = 65
img_name = landmarks_frame.iloc[n, 0]
landmarks = landmarks_frame.iloc[n, 1:]
landmarks = np.asarray(landmarks)
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]))
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('data/faces/', img_name)),
               landmarks)
plt.show()

face_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv',
                                    root_dir='data/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

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='data/faces/face_landmarks.csv',
                                           root_dir='data/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
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_border_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 + (i + 1) * grid_border_size,
                    landmarks_batch[i, :, 1].numpy() + grid_border_size,
                    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

類函式 

import torch
from skimage import io, transform

import numpy as np

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)}