From 4a0409ded4ab31f27f6f65c7f2daf3c180bee145 Mon Sep 17 00:00:00 2001 From: Yangyq213 <985558237@qq.com> Date: Wed, 12 Jun 2024 22:01:27 +0800 Subject: [PATCH] add TSP6K --- README.md | 1 + README_zh-CN.md | 1 + configs/_base_/datasets/tsp6k.py | 65 +++++++++++++++++++ configs/_base_/datasets/tsp6k_1024x1024.py | 29 +++++++++ configs/_base_/datasets/tsp6k_769x769.py | 29 +++++++++ ...abv3plus_r50b-d8_4xb2_80k_tsp6k_769x769.py | 12 ++++ docs/en/user_guides/2_dataset_prepare.md | 27 ++++++++ docs/zh_cn/user_guides/2_dataset_prepare.md | 28 ++++++++ mmseg/datasets/__init__.py | 3 +- mmseg/datasets/tsp6k.py | 27 ++++++++ tools/dataset_converters/tsp6k.py | 48 ++++++++++++++ 11 files changed, 269 insertions(+), 1 deletion(-) create mode 100644 configs/_base_/datasets/tsp6k.py create mode 100644 configs/_base_/datasets/tsp6k_1024x1024.py create mode 100644 configs/_base_/datasets/tsp6k_769x769.py create mode 100644 configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2_80k_tsp6k_769x769.py create mode 100644 mmseg/datasets/tsp6k.py create mode 100644 tools/dataset_converters/tsp6k.py diff --git a/README.md b/README.md index 79ecdb7111..1274026bb1 100644 --- a/README.md +++ b/README.md @@ -340,6 +340,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
  • BDD100K
  • NYU
  • HSIDrive20
    • +
  • TSP6K
    • diff --git a/README_zh-CN.md b/README_zh-CN.md index e047759b08..7a8c11811e 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -329,6 +329,7 @@ MMSegmentation v1.x 在 0.x 版本的基础上有了显著的提升，提供了
  • BDD100K
  • NYU
  • HSIDrive20
    • +
  • TSP6K
    • diff --git a/configs/_base_/datasets/tsp6k.py b/configs/_base_/datasets/tsp6k.py new file mode 100644 index 0000000000..d9b060d4e0 --- /dev/null +++ b/configs/_base_/datasets/tsp6k.py @@ -0,0 +1,65 @@ +# dataset settings +dataset_type = 'TSP6KDataset' +data_root = 'data/TSP6K/' +crop_size = (512, 1024) +train_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='LoadAnnotations'), + dict( + type='RandomResize', + scale=(2048, 1024), + ratio_range=(0.5, 2.0), + keep_ratio=True), + dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75), + dict(type='RandomFlip', prob=0.5), + dict(type='PhotoMetricDistortion'), + dict(type='PackSegInputs') +] +test_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='Resize', scale=(2048, 1024), keep_ratio=True), + # add loading annotation after ``Resize`` because ground truth + # does not need to do resize data transform + dict(type='LoadAnnotations'), + dict(type='PackSegInputs') +] +img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75] +tta_pipeline = [ + dict(type='LoadImageFromFile', backend_args=None), + dict( + type='TestTimeAug', + transforms=[ + [ + dict(type='Resize', scale_factor=r, keep_ratio=True) + for r in img_ratios + ], + [ + dict(type='RandomFlip', prob=0., direction='horizontal'), + dict(type='RandomFlip', prob=1., direction='horizontal') + ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')] + ]) +] +train_dataloader = dict( + batch_size=2, + num_workers=2, + persistent_workers=True, + sampler=dict(type='InfiniteSampler', shuffle=True), + dataset=dict( + type=dataset_type, + data_root=data_root, + data_prefix=dict(img_path='image/train', seg_map_path='label/train'), + pipeline=train_pipeline)) +val_dataloader = dict( + batch_size=1, + num_workers=4, + persistent_workers=True, + sampler=dict(type='DefaultSampler', shuffle=False), + dataset=dict( + type=dataset_type, + data_root=data_root, + data_prefix=dict(img_path='image/val', seg_map_path='label/val'), + pipeline=test_pipeline)) +test_dataloader = val_dataloader + +val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU']) +test_evaluator = val_evaluator diff --git a/configs/_base_/datasets/tsp6k_1024x1024.py b/configs/_base_/datasets/tsp6k_1024x1024.py new file mode 100644 index 0000000000..68f6c7d3c5 --- /dev/null +++ b/configs/_base_/datasets/tsp6k_1024x1024.py @@ -0,0 +1,29 @@ +_base_ = './tsp6k.py' +crop_size = (1024, 1024) +train_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='LoadAnnotations'), + dict( + type='RandomResize', + scale=(2048, 1024), + ratio_range=(0.5, 2.0), + keep_ratio=True), + dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75), + dict(type='RandomFlip', prob=0.5), + dict(type='PhotoMetricDistortion'), + dict(type='PackSegInputs') +] +test_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='Resize', scale=(2048, 1024), keep_ratio=True), + # add loading annotation after ``Resize`` because ground truth + # does not need to do resize data transform + dict(type='LoadAnnotations'), + dict(type='PackSegInputs') +] +train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) +val_dataloader = dict(dataset=dict(pipeline=test_pipeline)) +test_dataloader = val_dataloader + +val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU']) +test_evaluator = val_evaluator diff --git a/configs/_base_/datasets/tsp6k_769x769.py b/configs/_base_/datasets/tsp6k_769x769.py new file mode 100644 index 0000000000..4d2dc7e64f --- /dev/null +++ b/configs/_base_/datasets/tsp6k_769x769.py @@ -0,0 +1,29 @@ +_base_ = './tsp6k.py' +crop_size = (769, 769) +train_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='LoadAnnotations'), + dict( + type='RandomResize', + scale=(2049, 1025), + ratio_range=(0.5, 2.0), + keep_ratio=True), + dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75), + dict(type='RandomFlip', prob=0.5), + dict(type='PhotoMetricDistortion'), + dict(type='PackSegInputs') +] +test_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='Resize', scale=(2049, 1025), keep_ratio=True), + # add loading annotation after ``Resize`` because ground truth + # does not need to do resize data transform + dict(type='LoadAnnotations'), + dict(type='PackSegInputs') +] +train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) +val_dataloader = dict(dataset=dict(pipeline=test_pipeline)) +test_dataloader = val_dataloader + +val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU']) +test_evaluator = val_evaluator diff --git a/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2_80k_tsp6k_769x769.py b/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2_80k_tsp6k_769x769.py new file mode 100644 index 0000000000..3af4fa585c --- /dev/null +++ b/configs/deeplabv3plus/deeplabv3plus_r50b-d8_4xb2_80k_tsp6k_769x769.py @@ -0,0 +1,12 @@ +_base_ = [ + '../_base_/models/deeplabv3_r50-d8.py', + '../_base_/datasets/tsp6k_769x769.py', '../_base_/default_runtime.py', + '../_base_/schedules/schedule_80k.py' +] +crop_size = (769, 769) +data_preprocessor = dict(size=crop_size) +model = dict( + data_preprocessor=data_preprocessor, + decode_head=dict(align_corners=True, num_classes=21), + auxiliary_head=dict(align_corners=True, num_classes=21), + test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513))) diff --git a/docs/en/user_guides/2_dataset_prepare.md b/docs/en/user_guides/2_dataset_prepare.md index 3f94a94289..7088c28c3a 100644 --- a/docs/en/user_guides/2_dataset_prepare.md +++ b/docs/en/user_guides/2_dataset_prepare.md @@ -214,6 +214,13 @@ mmsegmentation │ │ │ ├── train │ │ │ ├── validation │ │ │ ├── test +│ ├── TSP6K +│ │ ├── image +│ │ | ├── train +│ │ │ ├── val +│ │ ├── label +│ │ | ├── train +│ │ │ ├── val ``` ## Download dataset via MIM @@ -804,3 +811,23 @@ mmsegmentation │ ├── HSI_Drive_v2_0_release_notes_Python_version.md │ ├── image_numbering.pdf ``` + +## TSP6K + +- The TSP6K dataset can be downloaded from [here](https://drive.google.com/file/d/1yDCL8vLOYcRuInCPUij3_pmq9yPk7KQj/view?usp=sharing). + +- Then, unzip `TSP6K_release.zip` and the contents of original datasets include: + +```none +├── TSP6K_release +│ ├── release +│ │ ├── image +│ │ ├── label_trainval +│ │ ├── split +``` + +- To organize the data into the required format, run the following command in your terminal: + + ```bash + python tools/dataset_converters/tsp6k.py /path/to/TSP6K_release/release + ``` diff --git a/docs/zh_cn/user_guides/2_dataset_prepare.md b/docs/zh_cn/user_guides/2_dataset_prepare.md index e32303a0bd..4d830f221d 100644 --- a/docs/zh_cn/user_guides/2_dataset_prepare.md +++ b/docs/zh_cn/user_guides/2_dataset_prepare.md @@ -214,6 +214,14 @@ mmsegmentation │ │ │ ├── train │ │ │ ├── validation │ │ │ ├── test +│ │ │ ├── test +│ ├── TSP6K +│ │ ├── image +│ │ | ├── train +│ │ │ ├── val +│ │ ├── label +│ │ | ├── train +│ │ │ ├── val ``` ## 用 MIM 下载数据集 @@ -800,3 +808,23 @@ mmsegmentation │ ├── HSI_Drive_v2_0_release_notes_Python_version.md │ ├── image_numbering.pdf ``` + +## TSP6K + +- 您可以从以下位置下载TSP6K数据集 [here](https://drive.google.com/file/d/1yDCL8vLOYcRuInCPUij3_pmq9yPk7KQj/view?usp=sharing)。 + +- 下载后，解压文件 `TSP6K_release.zip` 然后会得到如下内容： + +```none +├── TSP6K_release +│ ├── release +│ │ ├── image +│ │ ├── label_trainval +│ │ ├── split +``` + +- 请在命令行中运行以下指令来把数据结构组织成需要的格式： + + ```bash + python tools/dataset_converters/tsp6k.py /path/to/TSP6K_release/release + ``` diff --git a/mmseg/datasets/__init__.py b/mmseg/datasets/__init__.py index f8ad750d76..f69b46e063 100644 --- a/mmseg/datasets/__init__.py +++ b/mmseg/datasets/__init__.py @@ -39,6 +39,7 @@ RandomMosaic, RandomRotate, RandomRotFlip, Rerange, ResizeShortestEdge, ResizeToMultiple, RGB2Gray, SegRescale) +from .tsp6k import TSP6KDataset from .voc import PascalVOCDataset # yapf: enable @@ -61,5 +62,5 @@ 'MapillaryDataset_v2', 'Albu', 'LEVIRCDDataset', 'LoadMultipleRSImageFromFile', 'LoadSingleRSImageFromFile', 'ConcatCDInput', 'BaseCDDataset', 'DSDLSegDataset', 'BDD100KDataset', - 'NYUDataset', 'HSIDrive20Dataset' + 'NYUDataset', 'HSIDrive20Dataset', 'TSP6KDataset' ] diff --git a/mmseg/datasets/tsp6k.py b/mmseg/datasets/tsp6k.py new file mode 100644 index 0000000000..c17958839f --- /dev/null +++ b/mmseg/datasets/tsp6k.py @@ -0,0 +1,27 @@ +# Copyright (c) OpenMMLab. All rights reserved. +from mmseg.registry import DATASETS +from .basesegdataset import BaseSegDataset + + +@DATASETS.register_module() +class TSP6KDataset(BaseSegDataset): + """TSP6K dataset.""" + METAINFO = dict( + classes=('road', 'sidewalk', 'building', 'wall', 'railing', + 'vegetation', 'terrain', 'sky', 'person', 'rider', 'car', + 'truck', 'bus', 'motorcycle', 'bicycle', 'indication line', + 'lane line', 'crosswalk', 'pole', 'traffic light', + 'traffic sign'), + palette=[[[128, 64, 128], [244, 35, 232], [70, 70, 70], [80, 90, 40], + [180, 165, 180], [107, 142, 35], [152, 251, 152], + [70, 130, 180], [255, 0, 0], [255, 100, 0], [0, 0, 142], + [0, 0, 70], [0, 60, 100], [0, 0, 230], [119, 11, 32], + [250, 170, 160], [250, 200, 160], [250, 240, 180], + [153, 153, 153], [250, 170, 30], [220, 220, 0]]]) + + def __init__(self, + img_suffix='.jpg', + seg_map_suffix='_sem.png', + **kwargs) -> None: + super().__init__( + img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs) diff --git a/tools/dataset_converters/tsp6k.py b/tools/dataset_converters/tsp6k.py new file mode 100644 index 0000000000..2b59cd9335 --- /dev/null +++ b/tools/dataset_converters/tsp6k.py @@ -0,0 +1,48 @@ +# Copyright (c) OpenMMLab. All rights reserved. +import argparse +import os.path as osp +import shutil + +from mmengine.utils import mkdir_or_exist + + +def parse_args(): + parser = argparse.ArgumentParser( + description='Convert TSP6K dataset to mmsegmentation format') + parser.add_argument('raw_data', help='the path of raw data') + parser.add_argument( + '-o', '--out_dir', help='output path', default='./data/TSP6K') + args = parser.parse_args() + return args + + +def main(): + args = parse_args() + + mkdir_or_exist(args.out_dir) + for subdir in ['label/val', 'image/val', 'label/train', 'image/train']: + mkdir_or_exist(osp.join(args.out_dir, subdir)) + + splits = ['train', 'val'] + + for split in splits: + split_path = osp.join(args.raw_data, f'split/{split}.txt') + with open(split_path) as split_read: + image_names = [line[:-1] for line in split_read.readlines()] + for image_name in image_names: + ori_label_path = osp.join(args.raw_data, + f'label_trainval/{image_name}_sem.png') + tar_label_path = osp.join(args.out_dir, + f'label/{split}/{image_name}_sem.png') + shutil.copy(ori_label_path, tar_label_path) + + ori_img_path = osp.join(args.raw_data, f'image/{image_name}.jpg') + tar_img_path = osp.join(args.out_dir, + f'image/{split}/{image_name}.jpg') + shutil.copy(ori_img_path, tar_img_path) + + print('Done!') + + +if __name__ == '__main__': + main()