trw.datasets.voc2012
¶
Module Contents¶
Functions¶
|
|
|
Create the VOC2012 segmentation dataset |
- trw.datasets.voc2012._load_image_and_mask(batch, transform, normalize_0_1=True)¶
- trw.datasets.voc2012.default_voc_transforms()¶
- trw.datasets.voc2012.create_segmentation_voc2012_dataset(batch_size=40, root=None, transform_train=default_voc_transforms(), transform_valid=default_voc_transforms(), nb_workers=2)¶
Create the VOC2012 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
- Returns
a datasets with dataset voc2012 and splits train, valid.