trw.datasets.voc2012

Module Contents

Functions

_load_image_and_mask(batch, transform, normalize_0_1=True)

default_voc_transforms()

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
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.