[Feature] LIP dataset (#2187)

* [WIP] LIP dataset

* wip

* keep473

* lip dataset prepare

* add ut and test data

docs/en/user_guides/2_dataset_prepare.md

@@ -351,7 +351,8 @@ The dataset is a Large-scale Dataset for Instance Segmentation (also have segman
 
 You may need to follow the following structure for dataset preparation after downloading iSAID dataset.
 
-```
+```none
+├── data
 │   ├── iSAID
 │   │   ├── train
 │   │   │   ├── images
@@ -376,3 +377,40 @@ python tools/dataset_converters/isaid.py /path/to/iSAID
 ```
 
 In our default setting (`patch_width`=896, `patch_height`=896, `overlap_area`=384), it will generate 33978 images for training and 11644 images for validation.
+
+## LIP(Look Into Person) dataset
+
+This dataset could be download from [this page](https://lip.sysuhcp.com/overview.php).
+
+Please run the following commands to unzip dataset.
+
+```shell
+unzip LIP.zip
+cd LIP
+unzip TrainVal_images.zip
+unzip TrainVal_parsing_annotations.zip
+cd TrainVal_parsing_annotations
+unzip TrainVal_parsing_annotations.zip
+mv train_segmentations ../
+mv val_segmentations ../
+cd ..
+```
+
+The contents of  LIP datasets include:
+
+```none
+├── data
+│   ├── LIP
+│   │   ├── train_images
+│   │   │   ├── 1000_1234574.jpg
+│   │   │   ├── ...
+│   │   ├── train_segmentations
+│   │   │   ├── 1000_1234574.png
+│   │   │   ├── ...
+│   │   ├── val_images
+│   │   │   ├── 100034_483681.jpg
+│   │   │   ├── ...
+│   │   ├── val_segmentations
+│   │   │   ├── 100034_483681.png
+│   │   │   ├── ...
+```

mmseg/datasets/__init__.py

@@ -11,6 +11,7 @@ from .drive import DRIVEDataset
 from .hrf import HRFDataset
 from .isaid import iSAIDDataset
 from .isprs import ISPRSDataset
+from .lip import LIPDataset
 from .loveda import LoveDADataset
 from .night_driving import NightDrivingDataset
 from .pascal_context import PascalContextDataset, PascalContextDataset59
@@ -35,5 +36,5 @@ __all__ = [
     'RandomCutOut', 'RandomMosaic', 'PackSegInputs', 'ResizeToMultiple',
     'LoadImageFromNDArray', 'LoadBiomedicalImageFromFile',
     'LoadBiomedicalAnnotation', 'LoadBiomedicalData', 'GenerateEdge',
-    'DecathlonDataset'
+    'DecathlonDataset', 'LIPDataset'
 ]

mmseg/datasets/lip.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from mmseg.registry import DATASETS
+from .basesegdataset import BaseSegDataset
+
+
+@DATASETS.register_module()
+class LIPDataset(BaseSegDataset):
+    """LIP dataset.
+
+    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is fixed to
+    '.png'.
+    """
+    METAINFO = dict(
+        classes=('Background', 'Hat', 'Hair', 'Glove', 'Sunglasses',
+                 'UpperClothes', 'Dress', 'Coat', 'Socks', 'Pants',
+                 'Jumpsuits', 'Scarf', 'Skirt', 'Face', 'Left-arm',
+                 'Right-arm', 'Left-leg', 'Right-leg', 'Left-shoe',
+                 'Right-shoe'),
+        palette=(
+            [0, 0, 0],
+            [128, 0, 0],
+            [255, 0, 0],
+            [0, 85, 0],
+            [170, 0, 51],
+            [255, 85, 0],
+            [0, 0, 85],
+            [0, 119, 221],
+            [85, 85, 0],
+            [0, 85, 85],
+            [85, 51, 0],
+            [52, 86, 128],
+            [0, 128, 0],
+            [0, 0, 255],
+            [51, 170, 221],
+            [0, 255, 255],
+            [85, 255, 170],
+            [170, 255, 85],
+            [255, 255, 0],
+            [255, 170, 0],
+        ))
+
+    def __init__(self, **kwargs) -> None:
+        super().__init__(img_suffix='.jpg', seg_map_suffix='.png', **kwargs)

mmseg/utils/class_names.py

@@ -265,6 +265,26 @@ def stare_palette():
     return [[120, 120, 120], [6, 230, 230]]
 
 
+def lip_classes():
+    """LIP class names for external use."""
+    return [
+        'background', 'hat', 'hair', 'glove', 'sunglasses', 'upperclothes',
+        'dress', 'coat', 'socks', 'pants', 'jumpsuits', 'scarf', 'skirt',
+        'face', 'leftArm', 'rightArm', 'leftLeg', 'rightLeg', 'leftShoe',
+        'rightShoe'
+    ]
+
+
+def lip_palette():
+    """LIP palette for external use."""
+    return [
+        'Background', 'Hat', 'Hair', 'Glove', 'Sunglasses', 'UpperClothes',
+        'Dress', 'Coat', 'Socks', 'Pants', 'Jumpsuits', 'Scarf', 'Skirt',
+        'Face', 'Left-arm', 'Right-arm', 'Left-leg', 'Right-leg', 'Left-shoe',
+        'Right-shoe'
+    ]
+
+
 dataset_aliases = {
     'cityscapes': ['cityscapes'],
     'ade': ['ade', 'ade20k'],
@@ -278,7 +298,8 @@ dataset_aliases = {
         'coco_stuff164k'
     ],
     'isaid': ['isaid', 'iSAID'],
-    'stare': ['stare', 'STARE']
+    'stare': ['stare', 'STARE'],
+    'lip': ['LIP', 'lip']
 }
 
 

tests/test_datasets/test_dataset.py

@@ -8,8 +8,8 @@ import pytest
 
 from mmseg.datasets import (ADE20KDataset, BaseSegDataset, CityscapesDataset,
                             COCOStuffDataset, DecathlonDataset, ISPRSDataset,
-                            LoveDADataset, PascalVOCDataset, PotsdamDataset,
-                            iSAIDDataset)
+                            LIPDataset, LoveDADataset, PascalVOCDataset,
+                            PotsdamDataset, iSAIDDataset)
 from mmseg.registry import DATASETS
 from mmseg.utils import get_classes, get_palette
 
@@ -259,6 +259,25 @@ def test_decathlon():
     assert len(test_dataset) == 3
 
 
+def test_lip():
+    data_root = osp.join(osp.dirname(__file__), '../data/pseudo_lip_dataset')
+    # train load training dataset
+    train_dataset = LIPDataset(
+        pipeline=[],
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='train_images', seg_map_path='train_segmentations'))
+    assert len(train_dataset) == 1
+
+    # test load training dataset
+    test_dataset = LIPDataset(
+        pipeline=[],
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='val_images', seg_map_path='val_segmentations'))
+    assert len(test_dataset) == 1
+
+
 @pytest.mark.parametrize('dataset, classes', [
     ('ADE20KDataset', ('wall', 'building')),
     ('CityscapesDataset', ('road', 'sidewalk')),