datasets.py

# Copyright IBM All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

"""
Mostly copy-paste from https://github.com/facebookresearch/deit/blob/main/datasets.py
"""

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


def is_valid_file(path):
    base_path = os.path.basename(path)
    in21k_filter_list = ['n09894445_7463.JPEG','n10368624_12550.JPEG','n04257684_9033.JPEG','n02368116_318.JPEG','n10585217_8484.JPEG','n06470073_47249.JPEG','n02487347_1956.JPEG','n07930062_4147.JPEG','n09620794_5529.JPEG','n10721819_1131.JPEG','n10316360_4246.JPEG','n12353203_3849.JPEG','n01896844_997.JPEG','n09224725_3995.JPEG','n10175248_583.JPEG','n09789566_3522.JPEG','n09359803_8155.JPEG','n01678043_6448.JPEG','n04135315_8814.JPEG','n04135315_9318.JPEG','n03957420_8296.JPEG','n03957420_33553.JPEG','n03957420_30695.JPEG','n04427559_2974.JPEG','n02597972_5463.JPEG','n12630763_8018.JPEG','n02428089_710.JPEG']

    if base_path in in21k_filter_list:
        return False
    else:
        return True


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 == 'CIFAR10':
        dataset = datasets.CIFAR10(args.data_path, train=is_train, transform=transform)
        nb_classes = 10
    elif args.data_set == 'CIFAR100':
        dataset = datasets.CIFAR100(args.data_path, train=is_train, transform=transform)
        nb_classes = 100
    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 == 'IMNET21K':
        root = os.path.join(args.data_path, 'train' if is_train else 'val')
        dataset = datasets.ImageFolder(root, transform=transform, is_valid_file=is_valid_file)
        nb_classes = 21841

    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 resize_im:
        size = int(args.crop_ratio * 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)