scripts.data_preparation.create_lmdb¶
- scripts.data_preparation.create_lmdb.create_lmdb_for_div2k()[source]¶
Create lmdb files for DIV2K dataset.
- Usage:
Before run this script, please run extract_subimages.py. Typically, there are four folders to be processed for DIV2K dataset.
DIV2K_train_HR_sub
DIV2K_train_LR_bicubic/X2_sub
DIV2K_train_LR_bicubic/X3_sub
DIV2K_train_LR_bicubic/X4_sub
Remember to modify opt configurations according to your settings.
- scripts.data_preparation.create_lmdb.create_lmdb_for_reds()[source]¶
Create lmdb files for REDS dataset.
- Usage:
Before run this script, please run
merge_reds_train_val.py. We take two folders for example:train_sharp
train_sharp_bicubic
Remember to modify opt configurations according to your settings.
- scripts.data_preparation.create_lmdb.create_lmdb_for_vimeo90k()[source]¶
Create lmdb files for Vimeo90K dataset.
- Usage:
Remember to modify opt configurations according to your settings.
- scripts.data_preparation.create_lmdb.prepare_keys_div2k(folder_path)[source]¶
Prepare image path list and keys for DIV2K dataset.
- Parameters:
folder_path (str) – Folder path.
- Returns:
Image path list. list[str]: Key list.
- Return type:
list[str]
- scripts.data_preparation.create_lmdb.prepare_keys_reds(folder_path)[source]¶
Prepare image path list and keys for REDS dataset.
- Parameters:
folder_path (str) – Folder path.
- Returns:
Image path list. list[str]: Key list.
- Return type:
list[str]
- scripts.data_preparation.create_lmdb.prepare_keys_vimeo90k(folder_path, train_list_path, mode)[source]¶
Prepare image path list and keys for Vimeo90K dataset.
- Parameters:
folder_path (str) – Folder path.
train_list_path (str) – Path to the official train list.
mode (str) – One of ‘gt’ or ‘lq’.
- Returns:
Image path list. list[str]: Key list.
- Return type:
list[str]