basicsr.data.video_test_dataset

class basicsr.data.video_test_dataset.VideoRecurrentTestDataset(opt)[source]

Bases: VideoTestDataset

Video test dataset for recurrent architectures, which takes LR video frames as input and output corresponding HR video frames.

Parameters:

  • opt (dict) – Same as VideoTestDataset. Unused opt:

  • padding (str) – Padding mode.

class basicsr.data.video_test_dataset.VideoTestDUFDataset(opt)[source]

Bases: VideoTestDataset

Video test dataset for DUF dataset.

Parameters:

  • opt (dict) – Config for train dataset. Most of keys are the same as VideoTestDataset. It has the following extra keys:

  • use_duf_downsampling (bool) – Whether to use duf downsampling to generate low-resolution frames.

  • scale (bool) – Scale, which will be added automatically.

class basicsr.data.video_test_dataset.VideoTestDataset(opt)[source]

Bases: Dataset

Video test dataset.

Supported datasets: Vid4, REDS4, REDSofficial. More generally, it supports testing dataset with following structures:

dataroot
├── subfolder1
    ├── frame000
    ├── frame001
    ├── ...
├── subfolder2
    ├── frame000
    ├── frame001
    ├── ...
├── ...

For testing datasets, there is no need to prepare LMDB files.

Parameters:

  • opt (dict) – Config for train dataset. It contains the following keys:

  • dataroot_gt (str) – Data root path for gt.

  • dataroot_lq (str) – Data root path for lq.

  • io_backend (dict) – IO backend type and other kwarg.

  • cache_data (bool) – Whether to cache testing datasets.

  • name (str) – Dataset name.

  • meta_info_file (str) – The path to the file storing the list of test folders. If not provided, all the folders in the dataroot will be used.

  • num_frame (int) – Window size for input frames.

  • padding (str) – Padding mode.

class basicsr.data.video_test_dataset.VideoTestVimeo90KDataset(opt)[source]

Bases: Dataset

Video test dataset for Vimeo90k-Test dataset.

It only keeps the center frame for testing. For testing datasets, there is no need to prepare LMDB files.

Parameters:

  • opt (dict) – Config for train dataset. It contains the following keys:

  • dataroot_gt (str) – Data root path for gt.

  • dataroot_lq (str) – Data root path for lq.

  • io_backend (dict) – IO backend type and other kwarg.

  • cache_data (bool) – Whether to cache testing datasets.

  • name (str) – Dataset name.

  • meta_info_file (str) – The path to the file storing the list of test folders. If not provided, all the folders in the dataroot will be used.

  • num_frame (int) – Window size for input frames.

  • padding (str) – Padding mode.