trw.datasets.voc
¶
Module Contents¶
Functions¶
|
|
|
Extracted from torchvision |
|
|
|
Create the VOC segmentation dataset |
|
PASCAL VOC detection challenge |
Attributes¶
- trw.datasets.voc._load_image_and_mask(batch, transform, normalize_0_1=True)¶
- trw.datasets.voc._parse_voc_xml(node)¶
Extracted from torchvision
- trw.datasets.voc.OBJECT_CLASS_MAPPING¶
- trw.datasets.voc._load_image_and_bb(batch, transform, normalize_0_1=True)¶
- trw.datasets.voc.default_voc_transforms()¶
- trw.datasets.voc.create_voc_segmentation_dataset(batch_size: int = 40, root: Optional[str] = None, transform_train: Optional[List[trw.transforms.Transform]] = default_voc_transforms(), transform_valid: Optional[List[trw.transforms.Transform]] = None, nb_workers: int = 2, year: typing_extensions.Literal[2007, 2012] = '2012') trw.basic_typing.Datasets ¶
Create the VOC segmentation dataset
- Parameters
batch_size – the number of samples per batch
root – the root of the dataset
transform_train – the transform to apply on each batch of data of the training data
transform_valid – the transform to apply on each batch of data of the validation data
nb_workers – the number of worker process to pre-process the batches
year – the version of the dataset
- Returns
a datasets with dataset voc2012 and splits train, valid.
- trw.datasets.voc.create_voc_detection_dataset(root: str = None, transform_train: Optional[List[trw.transforms.Transform]] = None, transform_valid: Optional[List[trw.transforms.Transform]] = None, nb_workers: int = 2, batch_size: int = 1, data_subsampling_fraction_train: float = 1.0, data_subsampling_fraction_valid: float = 1.0, train_split: str = 'train', valid_split: str = 'val', year: typing_extensions.Literal[2007, 2012] = '2007') trw.basic_typing.Datasets ¶
PASCAL VOC detection challenge
Notes
Batch size is always 1 since we need to sample from the image various anchors, locations depending on the task (so each sample should be post-processed by a custom transform)