This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 48
/
datasets.py
135 lines (113 loc) · 5.02 KB
/
datasets.py
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
# Copyright (c) 2015-present, Facebook, Inc.
# All rights reserved.
"""
Modified from: https://github.com/facebookresearch/deit
"""
import os
import json
from torchvision import datasets, transforms
from torchvision.datasets.folder import ImageFolder, default_loader
from timm.data.constants import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.data import create_transform
class INatDataset(ImageFolder):
def __init__(self, root, train=True, year=2018, transform=None, target_transform=None,
category='name', loader=default_loader):
self.transform = transform
self.loader = loader
self.target_transform = target_transform
self.year = year
# assert category in ['kingdom','phylum','class','order','supercategory','family','genus','name']
path_json = os.path.join(root, f'{"train" if train else "val"}{year}.json')
with open(path_json) as json_file:
data = json.load(json_file)
with open(os.path.join(root, 'categories.json')) as json_file:
data_catg = json.load(json_file)
path_json_for_targeter = os.path.join(root, f"train{year}.json")
with open(path_json_for_targeter) as json_file:
data_for_targeter = json.load(json_file)
targeter = {}
indexer = 0
for elem in data_for_targeter['annotations']:
king = []
king.append(data_catg[int(elem['category_id'])][category])
if king[0] not in targeter.keys():
targeter[king[0]] = indexer
indexer += 1
self.nb_classes = len(targeter)
self.samples = []
for elem in data['images']:
cut = elem['file_name'].split('/')
target_current = int(cut[2])
path_current = os.path.join(root, cut[0], cut[2], cut[3])
categors = data_catg[target_current]
target_current_true = targeter[categors[category]]
self.samples.append((path_current, target_current_true))
# __getitem__ and __len__ inherited from ImageFolder
def build_dataset(is_train, args):
transform = build_transform(is_train, args)
if args.data_set == 'CIFAR100':
dataset = datasets.CIFAR100(args.data_path, train=is_train, transform=transform)
nb_classes = 100
elif args.data_set == 'CIFAR10':
dataset = datasets.CIFAR10(args.data_path, train=is_train, transform=transform)
nb_classes = 10
elif args.data_set == 'IMNET':
root = os.path.join(args.data_path, 'train' if is_train else 'val')
dataset = datasets.ImageFolder(root, transform=transform)
nb_classes = 1000
elif args.data_set == 'INAT':
dataset = INatDataset(args.data_path, train=is_train, year=2018,
category=args.inat_category, transform=transform)
nb_classes = dataset.nb_classes
elif args.data_set == 'INAT19':
dataset = INatDataset(args.data_path, train=is_train, year=2019,
category=args.inat_category, transform=transform)
nb_classes = dataset.nb_classes
elif args.data_set == 'CARS':
root = os.path.join(args.data_path, 'train' if is_train else 'test')
dataset = datasets.ImageFolder(root, transform=transform)
nb_classes = 196
elif args.data_set == 'FLOWERS':
root = os.path.join(args.data_path, 'train' if is_train else 'test')
dataset = datasets.ImageFolder(root, transform=transform)
nb_classes = 102
return dataset, nb_classes
def build_transform(is_train, args):
resize_im = args.input_size > 32
if is_train:
# this should always dispatch to transforms_imagenet_train
transform = create_transform(
input_size=args.input_size,
is_training=True,
color_jitter=args.color_jitter,
auto_augment=args.aa,
interpolation=args.train_interpolation,
re_prob=args.reprob,
re_mode=args.remode,
re_count=args.recount,
)
if not resize_im:
# replace RandomResizedCropAndInterpolation with
# RandomCrop
transform.transforms[0] = transforms.RandomCrop(
args.input_size, padding=4)
return transform
t = []
if args.full_crop:
mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]
transformations = {}
transformations = transforms.Compose(
[transforms.Resize(args.input_size, interpolation=3),
transforms.CenterCrop(args.input_size),
transforms.ToTensor(),
transforms.Normalize(mean, std)])
return transformations
if resize_im:
size = int((256 / 224) * args.input_size)
t.append(
transforms.Resize(size, interpolation=3), # to maintain same ratio w.r.t. 224 images
)
t.append(transforms.CenterCrop(args.input_size))
t.append(transforms.ToTensor())
t.append(transforms.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD))
return transforms.Compose(t)