ade20k_hparams

ADE20K Semantic segmentation and scene parsing dataset.

Please refer to the ADE20K dataset for more details about this dataset.

Hparams

These classes are used with yahp for YAML-based configuration.

ADE20kDatasetHparams	Defines an instance of the ADE20k dataset for semantic segmentation from a local disk.
StreamingADE20kHparams	DatasetHparams for creating an instance of StreamingADE20k.

class composer.datasets.ade20k_hparams.ADE20kDatasetHparams(use_synthetic=False, synthetic_num_unique_samples=100, synthetic_device='cpu', synthetic_memory_format=MemoryFormat.CONTIGUOUS_FORMAT, drop_last=True, shuffle=True, split='train', base_size=512, min_resize_scale=0.5, max_resize_scale=2.0, final_size=512, ignore_background=True, datadir=None)

Bases: composer.datasets.dataset_hparams.DatasetHparams, composer.datasets.synthetic_hparams.SyntheticHparamsMixin

Defines an instance of the ADE20k dataset for semantic segmentation from a local disk.

Parameters

• split (str) – the dataset split to use either ‘train’, ‘val’, or ‘test’. Default: 'train`.

• base_size (int) – initial size of the image and target before other augmentations. Default: 512.

• min_resize_scale (float) – the minimum value the samples can be rescaled. Default: 0.5.

• max_resize_scale (float) – the maximum value the samples can be rescaled. Default: 2.0.

• final_size (int) – the final size of the image and target. Default: 512.

• ignore_background (bool) – if true, ignore the background class when calculating the training loss. Default: true.

• datadir (str) – The path to the data directory.

class composer.datasets.ade20k_hparams.StreamingADE20kHparams(drop_last=True, shuffle=True, remote='s3://mosaicml-internal-dataset-ade20k/mds/1/', local='/tmp/mds-cache/mds-ade20k/', split='train', base_size=512, min_resize_scale=0.5, max_resize_scale=2.0, final_size=512, ignore_background=True)

Bases: composer.datasets.dataset_hparams.DatasetHparams

DatasetHparams for creating an instance of StreamingADE20k.

Parameters

• remote (str) – Remote directory (S3 or local filesystem) where dataset is stored. Default: 's3://mosaicml-internal-dataset-ade20k/mds/1/`

• local (str) – Local filesystem directory where dataset is cached during operation. Default: '/tmp/mds-cache/mds-ade20k/`

• split (str) – The dataset split to use, either ‘train’ or ‘val’. Default: 'train`.

• base_size (int) – initial size of the image and target before other augmentations. Default: 512.

• min_resize_scale (float) – the minimum value the samples can be rescaled. Default: 0.5.

• max_resize_scale (float) – the maximum value the samples can be rescaled. Default: 2.0.

• final_size (int) – the final size of the image and target. Default: 512.

• ignore_background (bool) – if true, ignore the background class when calculating the training loss. Default: true.