Open Cli98 opened 1 year ago
Here I want to report for the incorrect documentation for tutorial in Random mosaic
The official documentation for Random mosaic is at here https://mmsegmentation.readthedocs.io/en/latest/tutorials/customize_datasets.html#multi-image-mix-dataset
where the document provides an example for random mosaic usage:
train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='RandomMosaic', prob=1), dict(type='Resize', img_scale=(1024, 512), keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='Normalize', **img_norm_cfg), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']), ] train_dataset = dict( type='MultiImageMixDataset', dataset=dict( classes=classes, palette=palette, type=dataset_type, reduce_zero_label=False, img_dir=data_root + "images/train", ann_dir=data_root + "annotations/train", pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), ] ), pipeline=train_pipeline )
However, the usage is not correct. Because it calls
dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'),
twice, which totally mess up the augmentation. The resulting segmentation got another augmentation in top left ceil of returned mask.
To correct, remove either one function call of
could be enough.
Similar errors show up in issue #1207 https://github.com/open-mmlab/mmsegmentation/issues/1207
@MengzhangLI Can you guys investigate?
Thank you for pointing that out. we are working on fix it
Here I want to report for the incorrect documentation for tutorial in Random mosaic
The official documentation for Random mosaic is at here https://mmsegmentation.readthedocs.io/en/latest/tutorials/customize_datasets.html#multi-image-mix-dataset
where the document provides an example for random mosaic usage:
However, the usage is not correct. Because it calls
twice, which totally mess up the augmentation. The resulting segmentation got another augmentation in top left ceil of returned mask.
To correct, remove either one function call of
could be enough.
Similar errors show up in issue #1207 https://github.com/open-mmlab/mmsegmentation/issues/1207
@MengzhangLI Can you guys investigate?