Function mindspore::dataset::DIV2K
Defined in File datasets.h
Function Documentation
Function to create a DIV2KDataset.
Note
The generated dataset has two columns [“hr_image”, “lr_image”].
- Parameters
dataset_dir – [in] The dataset dir to be read.
usage – [in] The type of dataset. Acceptable usages include “train”, “valid” or “all”.
downgrade – [in] The mode of downgrade. Acceptable downgrades include “bicubic”, “unknown”, “mild”, “difficult” or “wild”.
scale – [in] The scale of downgrade. Acceptable scales include 2, 3, 4 or 8.
decode – [in] Decode the images after reading (default=false).
sampler – [in] Shared pointer to a sampler object used to choose samples from the dataset. If sampler is not given, a
RandomSampler
will be used to randomly iterate the entire dataset (default = RandomSampler()).cache – [in] Tensor cache to use (default=nullptr which means no cache is used).
- Returns
Shared pointer to the current DIV2KDataset.
Example/* Define dataset path and MindData object */ std::string dataset_path = "/path/to/div2k_dataset_directory"; std::shared_ptr<Dataset> ds = DIV2K(dataset_path, "train", "bicubic", 2); /* Create iterator to read dataset */ std::shared_ptr<Iterator> iter = ds->CreateIterator(); std::unordered_map<std::string, mindspore::MSTensor> row; iter->GetNextRow(&row); /* Note: In DIV2K dataset, each dictionary has keys "hr_image" and "lr_image" */ auto hr_image = row["hr_image"];