Hugging Face's logo

timm documentation

Data

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.9.16).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Data

timm.data.create_dataset

< >

( name: str root: Optional = None split: str = 'validation' search_split: bool = True class_map: dict = None load_bytes: bool = False is_training: bool = False download: bool = False batch_size: int = 1 num_samples: Optional = None seed: int = 42 repeats: int = 0 input_img_mode: str = 'RGB' **kwargs )

Dataset factory method

In parentheses after each arg are the type of dataset supported for each arg, one of:

  • folder - default, timm folder (or tar) based ImageDataset
  • torch - torchvision based datasets
  • HFDS - Hugging Face Datasets
  • TFDS - Tensorflow-datasets wrapper in IterabeDataset interface via IterableImageDataset
  • WDS - Webdataset
  • all - any of the above

timm.data.create_loader

< >

( dataset: Union input_size: Union batch_size: int is_training: bool = False no_aug: bool = False re_prob: float = 0.0 re_mode: str = 'const' re_count: int = 1 re_split: bool = False train_crop_mode: Optional = None scale: Optional = None ratio: Optional = None hflip: float = 0.5 vflip: float = 0.0 color_jitter: float = 0.4 color_jitter_prob: Optional = None grayscale_prob: float = 0.0 gaussian_blur_prob: float = 0.0 auto_augment: Optional = None num_aug_repeats: int = 0 num_aug_splits: int = 0 interpolation: str = 'bilinear' mean: Tuple = (0.485, 0.456, 0.406) std: Tuple = (0.229, 0.224, 0.225) num_workers: int = 1 distributed: bool = False crop_pct: Optional = None crop_mode: Optional = None crop_border_pixels: Optional = None collate_fn: Optional = None pin_memory: bool = False fp16: bool = False img_dtype: dtype = torch.float32 device: device = device(type='cuda') use_prefetcher: bool = True use_multi_epochs_loader: bool = False persistent_workers: bool = True worker_seeding: str = 'all' tf_preprocessing: bool = False )

timm.data.create_transform

< >

( input_size: Union = 224 is_training: bool = False no_aug: bool = False train_crop_mode: Optional = None scale: Optional = None ratio: Optional = None hflip: float = 0.5 vflip: float = 0.0 color_jitter: Union = 0.4 color_jitter_prob: Optional = None grayscale_prob: float = 0.0 gaussian_blur_prob: float = 0.0 auto_augment: Optional = None interpolation: str = 'bilinear' mean: Tuple = (0.485, 0.456, 0.406) std: Tuple = (0.229, 0.224, 0.225) re_prob: float = 0.0 re_mode: str = 'const' re_count: int = 1 re_num_splits: int = 0 crop_pct: Optional = None crop_mode: Optional = None crop_border_pixels: Optional = None tf_preprocessing: bool = False use_prefetcher: bool = False separate: bool = False )

timm.data.resolve_data_config

< >

( args = None pretrained_cfg = None model = None use_test_size = False verbose = False )

←Models Optimizers→