数据集

1. Download and decompress data from the link 百度网盘 请输入提取码 Password: qrlt

2. Transform .h5 format to .mat format "python convertH5tomat.py --data_dir XXX/T2Net/h5

论文：Task Transformer Network for Joint MRI Reconstruction and Super-Resolution (MICCAI 2021)https://arxiv.org/pdf/2106.06742.pdf

 代码链接：GitHub - chunmeifeng/T2Net: 【MICCAI 2021】Task Transformer Network for Joint MRI Reconstruction and Super-Resolution

 使用的是pytorch lighting框架

    def train_dataloader(self):
        return self._create_data_loader(
            self.train_data_transform(), data_partition="train"
        )

    def _create_data_loader(self, data_transform, data_partition, sample_rate=None):

        print('create data loader...', data_partition)
        sample_rate = sample_rate or self.sample_rate
        dataset = IXIdataset(
            data_dir=os.path.join(self.data_path, data_partition),
            # data_dir=self.data_path,
            args=self.ixi_args,
            validtion_flag=data_partition is not 'train'
        )

        is_train = data_partition == "train"

        sampler = None
        if self.use_ddp:
            sampler = DistributedSampler(dataset)

        dataloader = DataLoader(
            dataset=dataset,
            batch_size=self.batch_size,
            num_workers=self.num_workers,
            pin_memory=False,
            drop_last=is_train,
            sampler=sampler,
        )

        return dataloader