Image-Classification-Pytorch/dataset.py at main · Daisy-Zhang/Image-Classification-Pytorch · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
import os
import sys

import numpy
import torch
import torchvision.transforms as transforms
import torchvision.datasets as datasets
from torch.utils.data import DataLoader
from torch.utils.data import Dataset

import conf
from utils import image_preprocess

def get_imagefolder_train_loader():
    train_dir = './data/ImageFolder/train'

    normalize = transforms.Normalize(mean = [0.485, 0.456, 0.406],
                                     std = [0.229, 0.224, 0.225])

    train_dataset = datasets.ImageFolder(
        train_dir,
        transforms.Compose([
            transforms.RandomResizedCrop(conf.IMAGE_SIZE),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            normalize,
        ])
    )

    train_loader = torch.utils.data.DataLoader(
        train_dataset,
        batch_size = conf.TRAINING_BATCH_SIZE,
        shuffle = True,
        num_workers = conf.NUM_WORKERS,
        pin_memory = True
    )

    return train_loader

def get_imagefoler_val_loader():
    val_dir = './data/ImageFolder/test'

    normalize = transforms.Normalize(mean = [0.485, 0.456, 0.406],
                                     std = [0.229, 0.224, 0.225])

    val_dataset = datasets.ImageFolder(
            val_dir,
            transforms.Compose([
            transforms.Resize(int(conf.IMAGE_SIZE / 0.875)),
            transforms.CenterCrop(conf.IMAGE_SIZE),
            transforms.ToTensor(),
            normalize,
        ])
    )

    val_loader = torch.utils.data.DataLoader(
        val_dataset,
        batch_size = conf.VAL_BATCH_SIZE,
        shuffle = False,
        num_workers = conf.NUM_WORKERS,
        pin_memory = True
    )

    return val_loader

class MyDataset(Dataset):
    def __init__(self, filename, image_dir, resize_height = 256, resize_width = 256, repeat = 1):
        self.image_label_list = self.read_file(filename)
        self.image_dir = image_dir
        self.len = len(self.image_label_list)
        self.repeat = repeat
        self.resize_height = resize_height
        self.resize_width = resize_width

        self.toTensor = transforms.ToTensor()

    def __getitem__(self, i):
        index = i % self.len
        image_name, label = self.image_label_list[index]
        image_path = os.path.join(self.image_dir, image_name)
        img = self.load_data(image_path, self.resize_height, self.resize_width, normalization = False)
        img = self.data_preproccess(img)
        label = numpy.array(label)
        return img, label.squeeze()

    def __len__(self):
        if self.repeat == None:
            data_len = 10000000
        else:
            data_len = len(self.image_label_list) * self.repeat
        return data_len

    def read_file(self, filename):
        image_label_list = []
        with open(filename, 'r') as f:
            lines = f.readlines()
            for line in lines:
                content = line.rstrip().split(' ')
                name = content[0]
                labels = []
                for value in content[1:]:
                    labels.append(int(value))
                image_label_list.append((name, labels))
        return image_label_list

    def load_data(self, path, resize_height, resize_width, normalization):
        image = image_preprocess(path, resize_height, resize_width, normalization)
        return image

    def data_preproccess(self, data):
        data = self.toTensor(data)
        return data

def get_custom_train_loader():
    data_dir = './data/Custom/train/images/'
    txt_dir = './data/Custom/train/metadata.txt'

    my_dataset = MyDataset(txt_dir, data_dir)

    train_loader = torch.utils.data.DataLoader(
        my_dataset,
        batch_size = conf.TRAINING_BATCH_SIZE,
        shuffle = True,
        num_workers = conf.NUM_WORKERS
    )

    return train_loader

def get_custom_val_loader():
    data_dir = './data/Custom/test/images/'
    txt_dir = './data/Custom/test/metadata.txt'

    my_dataset = MyDataset(txt_dir, data_dir)

    val_loader = torch.utils.data.DataLoader(
        my_dataset,
        batch_size = conf.VAL_BATCH_SIZE,
        shuffle = False,
        num_workers = conf.NUM_WORKERS
    )

    return val_loader