[Feature] Support Delving into High-Quality Synthetic Face Occlusion …

…Segmentation Datasets (open-mmlab#2194)

add custom dataset

add face occlusion dataset

add config file for occlusion face

fix format

update prepare.md

formatting

formatting

fix typo error for doc

update downloading process

Update dataset_prepare.md

PR fix version to original repository. change to original repository.

configs/_base_/datasets/occlude_face.py

@@ -0,0 +1,78 @@
+dataset_type = 'FaceOccludedDataset'
+data_root = 'data/occlusion-aware-face-dataset'
+crop_size = (512, 512)
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations'),
+ dict(type='Resize', img_scale=(512, 512)),
+ dict(type='RandomFlip', prob=0.5),
+ dict(type='RandomRotate', degree=(-30, 30), prob=0.5),
+ dict(type='PhotoMetricDistortion'),
+ dict(
+ type='Normalize',
+ mean=[123.675, 116.28, 103.53],
+ std=[58.395, 57.12, 57.375],
+ to_rgb=True),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(512, 512),
+ img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+ flip=True,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='ResizeToMultiple', size_divisor=32),
+ dict(type='RandomFlip'),
+ dict(
+ type='Normalize',
+ mean=[123.675, 116.28, 103.53],
+ std=[58.395, 57.12, 57.375],
+ to_rgb=True),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img'])
+ ])
+]
+
+dataset_train_A = dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='NatOcc_hand_sot/img',
+ ann_dir='NatOcc_hand_sot/mask',
+ split='train.txt',
+ pipeline=train_pipeline)
+
+dataset_train_B = dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='NatOcc_object/img',
+ ann_dir='NatOcc_object/mask',
+ split='train.txt',
+ pipeline=train_pipeline)
+
+dataset_train_C = dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='RandOcc/img',
+ ann_dir='RandOcc/mask',
+ split='train.txt',
+ pipeline=train_pipeline)
+
+dataset_valid = dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='RealOcc/image',
+ ann_dir='RealOcc/mask',
+ split='RealOcc/split/val.txt',
+ pipeline=test_pipeline)
+
+data = dict(
+ samples_per_gpu=2,
+ workers_per_gpu=2,
+ train=[dataset_train_A, dataset_train_B, dataset_train_C],
+ val=dataset_valid)

configs/deeplabv3plus/deeplabv3plus_r101_512x512_C-CM+C-WO-NatOcc-SOT.py

@@ -0,0 +1,63 @@
+# +
+_base_ = '../_base_/datasets/occlude_face.py'
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+ type='EncoderDecoder',
+ pretrained='open-mmlab:https://resnet101_v1c',
+ backbone=dict(
+ type='ResNetV1c',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ dilations=(1, 1, 2, 4),
+ strides=(1, 2, 1, 1),
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ norm_eval=False,
+ style='pytorch',
+ contract_dilation=True),
+ decode_head=dict(
+ type='DepthwiseSeparableASPPHead',
+ in_channels=2048,
+ in_index=3,
+ channels=512,
+ dilations=(1, 12, 24, 36),
+ c1_in_channels=256,
+ c1_channels=48,
+ dropout_ratio=0.1,
+ num_classes=2,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ align_corners=False,
+ loss_decode=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000)),
+ auxiliary_head=dict(
+ type='FCNHead',
+ in_channels=1024,
+ in_index=2,
+ channels=256,
+ num_convs=1,
+ concat_input=False,
+ dropout_ratio=0.1,
+ num_classes=2,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ align_corners=False,
+ loss_decode=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+ train_cfg=dict(),
+ test_cfg=dict(mode='whole'))
+log_config = dict(
+ interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+lr_config = dict(policy='poly', power=0.9, min_lr=0.0001, by_epoch=False)
+runner = dict(type='IterBasedRunner', max_iters=30000)
+checkpoint_config = dict(by_epoch=False, interval=400)
+evaluation = dict(
+ interval=400, metric=['mIoU', 'mDice', 'mFscore'], pre_eval=True)
+auto_resume = False

mmseg/datasets/__init__.py

@@ -9,6 +9,7 @@
 from .dataset_wrappers import MultiImageMixDataset
 from .decathlon import DecathlonDataset
 from .drive import DRIVEDataset
+from .face import FaceOccludedDataset
 from .hrf import HRFDataset
 from .isaid import iSAIDDataset
 from .isprs import ISPRSDataset
@@ -51,5 +52,5 @@
  'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
  'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip',
  'SynapseDataset', 'REFUGEDataset', 'MapillaryDataset_v1',
- 'MapillaryDataset_v2'
+ 'MapillaryDataset_v2', 'FaceOccludedDataset'
 ]

mmseg/datasets/face.py

@@ -0,0 +1,23 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os.path as osp
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class FaceOccludedDataset(CustomDataset):
+ """Face Occluded dataset.
+
+ Args:
+ split (str): Split txt file for Pascal VOC.
+ """
+
+ CLASSES = ('background', 'face')
+
+ PALETTE = [[0, 0, 0], [128, 0, 0]]
+
+ def __init__(self, split, **kwargs):
+ super(FaceOccludedDataset, self).__init__(
+ img_suffix='.jpg', seg_map_suffix='.png', split=split, **kwargs)
+ assert osp.exists(self.img_dir) and self.split is not None