Method get_data

datasets/ssl_dataset.py:222–257

get_data returns data (images) and targets (labels) shape of data: B, H, W, C shape of labels: B,

(self, svhn_extra=True)

        self.transform = get_transform(mean[name], std[name], crop_size, train)

    def get_data(self, svhn_extra=True):
        """
        get_data returns data (images) and targets (labels)
        shape of data: B, H, W, C
        shape of labels: B,
        """
        dset = getattr(torchvision.datasets, self.name.upper())
        if 'CIFAR' in self.name.upper():
            dset = dset(self.data_dir, train=self.train, download=True)
            data, targets = dset.data, dset.targets
            return data, targets
        elif self.name.upper() == 'SVHN':
            if self.train:
                if svhn_extra:  # train+extra
                    dset_base = dset(self.data_dir, split='train', download=True)
                    data_b, targets_b = dset_base.data.transpose([0, 2, 3, 1]), dset_base.labels
                    dset_extra = dset(self.data_dir, split='extra', download=True)
                    data_e, targets_e = dset_extra.data.transpose([0, 2, 3, 1]), dset_extra.labels
                    data = np.concatenate([data_b, data_e])
                    targets = np.concatenate([targets_b, targets_e])
                    del data_b, data_e
                    del targets_b, targets_e
                else:  # train_only
                    dset = dset(self.data_dir, split='train', download=True)
                    data, targets = dset.data.transpose([0, 2, 3, 1]), dset.labels
            else:  # test
                dset = dset(self.data_dir, split='test', download=True)
                data, targets = dset.data.transpose([0, 2, 3, 1]), dset.labels
            return data, targets
        elif self.name.upper() == 'STL10':
            split = 'train' if self.train else 'test'
            dset_lb = dset(self.data_dir, split=split, download=True)
            dset_ulb = dset(self.data_dir, split='unlabeled', download=True)
            data, targets = dset_lb.data.transpose([0, 2, 3, 1]), dset_lb.labels.astype(np.int64)
            ulb_data = dset_ulb.data.transpose([0, 2, 3, 1])
            return data, targets, ulb_data

    def get_dset(self, is_ulb=False,
                 strong_transform=None, onehot=False):