## Motivation Add REFUGE datasets Old PR: https://github.com/open-mmlab/mmsegmentation/pull/2420 --------- Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>pull/2569/head
Andrew Lau
GitHub
parent
7ac0888d9f
commit
49b062e365
|
|
@ -0,0 +1,90 @@
|
|||
# dataset settings
|
||||
dataset_type = 'REFUGEDataset'
|
||||
data_root = 'data/REFUGE'
|
||||
train_img_scale = (2056, 2124)
|
||||
val_img_scale = (1634, 1634)
|
||||
test_img_scale = (1634, 1634)
|
||||
crop_size = (512, 512)
|
||||
|
||||
train_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(type='LoadAnnotations', reduce_zero_label=False),
|
||||
dict(
|
||||
type='RandomResize',
|
||||
scale=train_img_scale,
|
||||
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')
|
||||
]
|
||||
val_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(type='Resize', scale=val_img_scale, keep_ratio=True),
|
||||
# add loading annotation after ``Resize`` because ground truth
|
||||
# does not need to do resize data transform
|
||||
dict(type='LoadAnnotations', reduce_zero_label=False),
|
||||
dict(type='PackSegInputs')
|
||||
]
|
||||
test_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(type='Resize', scale=test_img_scale, keep_ratio=True),
|
||||
# add loading annotation after ``Resize`` because ground truth
|
||||
# does not need to do resize data transform
|
||||
dict(type='LoadAnnotations', reduce_zero_label=False),
|
||||
dict(type='PackSegInputs')
|
||||
]
|
||||
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
|
||||
tta_pipeline = [
|
||||
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
|
||||
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=4,
|
||||
num_workers=4,
|
||||
persistent_workers=True,
|
||||
sampler=dict(type='InfiniteSampler', shuffle=True),
|
||||
dataset=dict(
|
||||
type=dataset_type,
|
||||
data_root=data_root,
|
||||
data_prefix=dict(
|
||||
img_path='images/training', seg_map_path='annotations/training'),
|
||||
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='images/validation',
|
||||
seg_map_path='annotations/validation'),
|
||||
pipeline=val_pipeline))
|
||||
test_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='images/test', seg_map_path='annotations/test'),
|
||||
pipeline=val_pipeline))
|
||||
|
||||
val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
|
||||
test_evaluator = val_evaluator
|
||||
|
|
@ -145,6 +145,15 @@ mmsegmentation
|
|||
│ │ ├── ann_dir
|
||||
│ │ │ ├── train
|
||||
│ │ │ ├── val
|
||||
│ ├── REFUGE
|
||||
│ │ ├── images
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
│ │ ├── annotations
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
```
|
||||
|
||||
### Cityscapes
|
||||
|
|
@ -330,7 +339,7 @@ For Potsdam dataset, please run the following command to download and re-organiz
|
|||
python tools/dataset_converters/potsdam.py /path/to/potsdam
|
||||
```
|
||||
|
||||
In our default setting, it will generate 3,456 images for training and 2,016 images for validation.
|
||||
In our default setting, it will generate 3456 images for training and 2016 images for validation.
|
||||
|
||||
### ISPRS Vaihingen
|
||||
|
||||
|
|
@ -383,7 +392,7 @@ You may need to follow the following structure for dataset preparation after dow
|
|||
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 33,978 images for training and 11,644 images for validation.
|
||||
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
|
||||
|
||||
|
|
@ -436,7 +445,7 @@ cd ./RawData/Training
|
|||
|
||||
Then create `train.txt` and `val.txt` to split dataset.
|
||||
|
||||
According to TransUNet, the following is the data set division.
|
||||
According to TransUnet, the following is the data set division.
|
||||
|
||||
train.txt
|
||||
|
||||
|
|
@ -500,7 +509,45 @@ Then, use this command to convert synapse dataset.
|
|||
python tools/dataset_converters/synapse.py --dataset-path /path/to/synapse
|
||||
```
|
||||
|
||||
In our default setting, it will generate 2,211 2D images for training and 1,568 2D images for validation.
|
||||
|
||||
Noted that MMSegmentation default evaluation metric (such as mean dice value) is calculated on 2D slice image,
|
||||
which is not comparable to results of 3D scan in some paper such as [TransUNet](https://arxiv.org/abs/2102.04306).
|
||||
|
||||
### REFUGE
|
||||
|
||||
Register in [REFUGE Challenge](https://refuge.grand-challenge.org) and download [REFUGE dataset](https://refuge.grand-challenge.org/REFUGE2Download).
|
||||
|
||||
Then, unzip `REFUGE2.zip` and the contents of original datasets include:
|
||||
|
||||
```none
|
||||
├── REFUGE2
|
||||
│ ├── REFUGE2
|
||||
│ │ ├── Annotation-Training400.zip
|
||||
│ │ ├── REFUGE-Test400.zip
|
||||
│ │ ├── REFUGE-Test-GT.zip
|
||||
│ │ ├── REFUGE-Training400.zip
|
||||
│ │ ├── REFUGE-Validation400.zip
|
||||
│ │ ├── REFUGE-Validation400-GT.zip
|
||||
│ ├── __MACOSX
|
||||
```
|
||||
|
||||
Please run the following command to convert REFUGE dataset:
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/refuge.py --raw_data_root=/path/to/refuge/REFUGE2/REFUGE2
|
||||
```
|
||||
|
||||
The script will make directory structure below:
|
||||
|
||||
```none
|
||||
│ ├── REFUGE
|
||||
│ │ ├── images
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
│ │ ├── annotations
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
```
|
||||
|
||||
It includes 400 images for training, 400 images for validation and 400 images for testing which is the same as REFUGE 2018 dataset.
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
## 准备数据集（待更新）
|
||||
|
||||
推荐用软链接, 将数据集根目录链接到 `$MMSEGMENTATION/data` 里. 如果您的文件夹结构是不同的, 您也许可以试着修改配置文件里对应的路径.
|
||||
推荐用软链接，将数据集根目录链接到 `$MMSEGMENTATION/data` 里。如果您的文件夹结构是不同的，您也许可以试着修改配置文件里对应的路径。
|
||||
|
||||
```none
|
||||
mmsegmentation
|
||||
|
|
@ -126,51 +126,60 @@ mmsegmentation
|
|||
│ │ ├── ann_dir
|
||||
│ │ │ ├── train
|
||||
│ │ │ ├── val
|
||||
│ ├── REFUGE
|
||||
│ │ ├── images
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
│ │ ├── annotations
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
```
|
||||
|
||||
### Cityscapes
|
||||
|
||||
注册成功后, 数据集可以在 [这里](https://www.cityscapes-dataset.com/downloads/) 下载.
|
||||
注册成功后，数据集可以在 [这里](https://www.cityscapes-dataset.com/downloads/) 下载。
|
||||
|
||||
通常情况下, `**labelTrainIds.png` 被用来训练 cityscapes.
|
||||
通常情况下，`**labelTrainIds.png` 被用来训练 cityscapes。
|
||||
基于 [cityscapesscripts](https://github.com/mcordts/cityscapesScripts),
|
||||
我们提供了一个 [脚本](https://github.com/open-mmlab/mmsegmentation/blob/master/tools/convert_datasets/cityscapes.py),
|
||||
去生成 `**labelTrainIds.png`.
|
||||
去生成 `**labelTrainIds.png`。
|
||||
|
||||
```shell
|
||||
# --nproc 8 意味着有 8 个进程用来转换,它也可以被忽略.
|
||||
# --nproc 8 意味着有 8 个进程用来转换，它也可以被忽略。
|
||||
python tools/convert_datasets/cityscapes.py data/cityscapes --nproc 8
|
||||
```
|
||||
|
||||
### Pascal VOC
|
||||
|
||||
Pascal VOC 2012 可以在 [这里](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar) 下载.
|
||||
此外, 许多最近在 Pascal VOC 数据集上的工作都会利用增广的数据, 它们可以在 [这里](http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz) 找到.
|
||||
Pascal VOC 2012 可以在 [这里](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar) 下载。
|
||||
此外，许多最近在 Pascal VOC 数据集上的工作都会利用增广的数据，它们可以在 [这里](http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz) 找到。
|
||||
|
||||
如果您想使用增广后的 VOC 数据集, 请运行下面的命令来将数据增广的标注转成正确的格式.
|
||||
如果您想使用增广后的 VOC 数据集，请运行下面的命令来将数据增广的标注转成正确的格式。
|
||||
|
||||
```shell
|
||||
# --nproc 8 意味着有 8 个进程用来转换,它也可以被忽略.
|
||||
# --nproc 8 意味着有 8 个进程用来转换，它也可以被忽略。
|
||||
python tools/convert_datasets/voc_aug.py data/VOCdevkit data/VOCdevkit/VOCaug --nproc 8
|
||||
```
|
||||
|
||||
关于如何拼接数据集 (concatenate) 并一起训练它们, 更多细节请参考 [拼接连接数据集](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/tutorials/customize_datasets.md#%E6%8B%BC%E6%8E%A5%E6%95%B0%E6%8D%AE%E9%9B%86) .
|
||||
关于如何拼接数据集 (concatenate) 并一起训练它们，更多细节请参考 [拼接连接数据集](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/tutorials/customize_datasets.md#%E6%8B%BC%E6%8E%A5%E6%95%B0%E6%8D%AE%E9%9B%86) 。
|
||||
|
||||
### ADE20K
|
||||
|
||||
ADE20K 的训练集和验证集可以在 [这里](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip) 下载.
|
||||
您还可以在 [这里](http://data.csail.mit.edu/places/ADEchallenge/release_test.zip) 下载验证集.
|
||||
ADE20K 的训练集和验证集可以在 [这里](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip) 下载。
|
||||
您还可以在 [这里](http://data.csail.mit.edu/places/ADEchallenge/release_test.zip) 下载验证集。
|
||||
|
||||
### Pascal Context
|
||||
|
||||
Pascal Context 的训练集和验证集可以在 [这里](http://host.robots.ox.ac.uk/pascal/VOC/voc2010/VOCtrainval_03-May-2010.tar) 下载.
|
||||
注册成功后, 您还可以在 [这里](http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2010test.tar) 下载验证集.
|
||||
Pascal Context 的训练集和验证集可以在 [这里](http://host.robots.ox.ac.uk/pascal/VOC/voc2010/VOCtrainval_03-May-2010.tar) 下载。
|
||||
注册成功后，您还可以在 [这里](http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2010test.tar) 下载验证集。
|
||||
|
||||
为了从原始数据集里切分训练集和验证集, 您可以在 [这里](https://codalabuser.blob.core.windows.net/public/trainval_merged.json)
|
||||
下载 trainval_merged.json.
|
||||
为了从原始数据集里切分训练集和验证集， 您可以在 [这里](https://codalabuser.blob.core.windows.net/public/trainval_merged.json)
|
||||
下载 trainval_merged.json。
|
||||
|
||||
如果您想使用 Pascal Context 数据集,
|
||||
请安装 [细节](https://github.com/zhanghang1989/detail-api) 然后再运行如下命令来把标注转换成正确的格式.
|
||||
如果您想使用 Pascal Context 数据集，
|
||||
请安装 [细节](https://github.com/zhanghang1989/detail-api) 然后再运行如下命令来把标注转换成正确的格式。
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/pascal_context.py data/VOCdevkit data/VOCdevkit/VOC2010/trainval_merged.json
|
||||
|
|
@ -178,64 +187,64 @@ python tools/convert_datasets/pascal_context.py data/VOCdevkit data/VOCdevkit/VO
|
|||
|
||||
### CHASE DB1
|
||||
|
||||
CHASE DB1 的训练集和验证集可以在 [这里](https://staffnet.kingston.ac.uk/~ku15565/CHASE_DB1/assets/CHASEDB1.zip) 下载.
|
||||
CHASE DB1 的训练集和验证集可以在 [这里](https://staffnet.kingston.ac.uk/~ku15565/CHASE_DB1/assets/CHASEDB1.zip) 下载。
|
||||
|
||||
为了将 CHASE DB1 数据集转换成 MMSegmentation 的格式,您需要运行如下命令:
|
||||
为了将 CHASE DB1 数据集转换成 MMSegmentation 的格式，您需要运行如下命令：
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/chase_db1.py /path/to/CHASEDB1.zip
|
||||
```
|
||||
|
||||
这个脚本将自动生成正确的文件夹结构.
|
||||
这个脚本将自动生成正确的文件夹结构。
|
||||
|
||||
### DRIVE
|
||||
|
||||
DRIVE 的训练集和验证集可以在 [这里](https://drive.grand-challenge.org/) 下载.
|
||||
在此之前, 您需要注册一个账号, 当前 '1st_manual' 并未被官方提供, 因此需要您从其他地方获取.
|
||||
DRIVE 的训练集和验证集可以在 [这里](https://drive.grand-challenge.org/) 下载。
|
||||
在此之前，您需要注册一个账号，当前 '1st_manual' 并未被官方提供，因此需要您从其他地方获取。
|
||||
|
||||
为了将 DRIVE 数据集转换成 MMSegmentation 格式, 您需要运行如下命令:
|
||||
为了将 DRIVE 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/drive.py /path/to/training.zip /path/to/test.zip
|
||||
```
|
||||
|
||||
这个脚本将自动生成正确的文件夹结构.
|
||||
这个脚本将自动生成正确的文件夹结构。
|
||||
|
||||
### HRF
|
||||
|
||||
首先, 下载 [healthy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy.zip) [glaucoma.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma.zip), [diabetic_retinopathy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy.zip), [healthy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy_manualsegm.zip), [glaucoma_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma_manualsegm.zip) 以及 [diabetic_retinopathy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy_manualsegm.zip).
|
||||
首先，下载 [healthy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy.zip) [glaucoma.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma.zip), [diabetic_retinopathy.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy.zip), [healthy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/healthy_manualsegm.zip), [glaucoma_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/glaucoma_manualsegm.zip) 以及 [diabetic_retinopathy_manualsegm.zip](https://www5.cs.fau.de/fileadmin/research/datasets/fundus-images/diabetic_retinopathy_manualsegm.zip) 。
|
||||
|
||||
为了将 HRF 数据集转换成 MMSegmentation 格式, 您需要运行如下命令:
|
||||
为了将 HRF 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/hrf.py /path/to/healthy.zip /path/to/healthy_manualsegm.zip /path/to/glaucoma.zip /path/to/glaucoma_manualsegm.zip /path/to/diabetic_retinopathy.zip /path/to/diabetic_retinopathy_manualsegm.zip
|
||||
```
|
||||
|
||||
这个脚本将自动生成正确的文件夹结构.
|
||||
这个脚本将自动生成正确的文件夹结构。
|
||||
|
||||
### STARE
|
||||
|
||||
首先, 下载 [stare-images.tar](http://cecas.clemson.edu/~ahoover/stare/probing/stare-images.tar), [labels-ah.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-ah.tar) 和 [labels-vk.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-vk.tar).
|
||||
首先，下载 [stare-images.tar](http://cecas.clemson.edu/~ahoover/stare/probing/stare-images.tar), [labels-ah.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-ah.tar) 和 [labels-vk.tar](http://cecas.clemson.edu/~ahoover/stare/probing/labels-vk.tar) 。
|
||||
|
||||
为了将 STARE 数据集转换成 MMSegmentation 格式, 您需要运行如下命令:
|
||||
为了将 STARE 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/stare.py /path/to/stare-images.tar /path/to/labels-ah.tar /path/to/labels-vk.tar
|
||||
```
|
||||
|
||||
这个脚本将自动生成正确的文件夹结构.
|
||||
这个脚本将自动生成正确的文件夹结构。
|
||||
|
||||
### Dark Zurich
|
||||
|
||||
因为我们只支持在此数据集上测试模型, 所以您只需下载[验证集](https://data.vision.ee.ethz.ch/csakarid/shared/GCMA_UIoU/Dark_Zurich_val_anon.zip).
|
||||
因为我们只支持在此数据集上测试模型，所以您只需下载[验证集](https://data.vision.ee.ethz.ch/csakarid/shared/GCMA_UIoU/Dark_Zurich_val_anon.zip) 。
|
||||
|
||||
### Nighttime Driving
|
||||
|
||||
因为我们只支持在此数据集上测试模型,所以您只需下载[测试集](http://data.vision.ee.ethz.ch/daid/NighttimeDriving/NighttimeDrivingTest.zip).
|
||||
因为我们只支持在此数据集上测试模型，所以您只需下载[测试集](http://data.vision.ee.ethz.ch/daid/NighttimeDriving/NighttimeDrivingTest.zip) 。
|
||||
|
||||
### LoveDA
|
||||
|
||||
可以从 Google Drive 里下载 [LoveDA数据集](https://drive.google.com/drive/folders/1ibYV0qwn4yuuh068Rnc-w4tPi0U0c-ti?usp=sharing).
|
||||
可以从 Google Drive 里下载 [LoveDA数据集](https://drive.google.com/drive/folders/1ibYV0qwn4yuuh068Rnc-w4tPi0U0c-ti?usp=sharing) 。
|
||||
|
||||
或者它还可以从 [zenodo](https://zenodo.org/record/5706578#.YZvN7SYRXdF) 下载, 您需要运行如下命令:
|
||||
|
||||
|
|
@ -248,46 +257,46 @@ wget https://zenodo.org/record/5706578/files/Val.zip
|
|||
wget https://zenodo.org/record/5706578/files/Test.zip
|
||||
```
|
||||
|
||||
对于 LoveDA 数据集,请运行以下命令下载并重新组织数据集:
|
||||
对于 LoveDA 数据集，请运行以下命令下载并重新组织数据集
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/loveda.py /path/to/loveDA
|
||||
```
|
||||
|
||||
请参照 [这里](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/inference.md) 来使用训练好的模型去预测 LoveDA 测试集并且提交到官网.
|
||||
请参照 [这里](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/inference.md) 来使用训练好的模型去预测 LoveDA 测试集并且提交到官网。
|
||||
|
||||
关于 LoveDA 的更多细节可以在[这里](https://github.com/Junjue-Wang/LoveDA) 找到.
|
||||
关于 LoveDA 的更多细节可以在[这里](https://github.com/Junjue-Wang/LoveDA) 找到。
|
||||
|
||||
### ISPRS Potsdam
|
||||
|
||||
[Potsdam](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-potsdam/)
|
||||
数据集是一个有着2D 语义分割内容标注的城市遥感数据集.
|
||||
数据集可以从挑战[主页](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/) 获得.
|
||||
需要其中的 `2_Ortho_RGB.zip` 和 `5_Labels_all_noBoundary.zip`.
|
||||
数据集是一个有着2D 语义分割内容标注的城市遥感数据集。
|
||||
数据集可以从挑战[主页](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/) 获得。
|
||||
需要其中的 '2_Ortho_RGB.zip' 和 '5_Labels_all_noBoundary.zip'。
|
||||
|
||||
对于 Potsdam 数据集,请运行以下命令下载并重新组织数据集
|
||||
对于 Potsdam 数据集，请运行以下命令下载并重新组织数据集
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/potsdam.py /path/to/potsdam
|
||||
```
|
||||
|
||||
使用我们默认的配置, 将生成 3,456 张图片的训练集和 2,016 张图片的验证集.
|
||||
使用我们默认的配置， 将生成 3456 张图片的训练集和 2016 张图片的验证集。
|
||||
|
||||
### ISPRS Vaihingen
|
||||
|
||||
[Vaihingen](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-vaihingen/)
|
||||
数据集是一个有着2D 语义分割内容标注的城市遥感数据集.
|
||||
数据集是一个有着2D 语义分割内容标注的城市遥感数据集。
|
||||
|
||||
数据集可以从挑战 [主页](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/).
|
||||
需要其中的 'ISPRS_semantic_labeling_Vaihingen.zip' 和 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip'.
|
||||
需要其中的 'ISPRS_semantic_labeling_Vaihingen.zip' 和 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip'。
|
||||
|
||||
对于 Vaihingen 数据集, 请运行以下命令下载并重新组织数据集
|
||||
对于 Vaihingen 数据集，请运行以下命令下载并重新组织数据集
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/vaihingen.py /path/to/vaihingen
|
||||
```
|
||||
|
||||
使用我们默认的配置 (`clip_size`=512, `stride_size`=256), 将生成 344 张图片的训练集和 398 张图片的验证集.
|
||||
使用我们默认的配置 (`clip_size`=512, `stride_size`=256)， 将生成 344 张图片的训练集和 398 张图片的验证集。
|
||||
|
||||
### iSAID
|
||||
|
||||
|
|
@ -297,7 +306,7 @@ iSAID 数据集(训练集/验证集)的注释可以从 [iSAID](https://captain-w
|
|||
|
||||
该数据集是一个大规模的实例分割(也可以用于语义分割)的遥感数据集.
|
||||
|
||||
下载后, 在数据集转换前, 您需要将数据集文件夹调整成如下格式.
|
||||
下载后，在数据集转换前，您需要将数据集文件夹调整成如下格式.
|
||||
|
||||
```
|
||||
│ ├── iSAID
|
||||
|
|
@ -404,3 +413,41 @@ python tools/dataset_converters/synapse.py --dataset-path /path/to/synapse
|
|||
使用我们默认的配置, 将生成 2,211 张 2D 图片的训练集和 1,568 张图片的验证集.
|
||||
|
||||
需要注意的是 MMSegmentation 默认的评价指标 (例如平均 Dice 值) 都是基于每帧 2D 图片计算的, 这与基于每套 3D 图片计算评价指标的 [TransUNet](https://arxiv.org/abs/2102.04306) 是不同的.
|
||||
|
||||
### REFUGE
|
||||
|
||||
在[官网](https://refuge.grand-challenge.org)注册后, 下载 [REFUGE 数据集](https://refuge.grand-challenge.org/REFUGE2Download) `REFUGE2.zip` , 解压后的内容如下:
|
||||
|
||||
```none
|
||||
├── REFUGE2
|
||||
│ ├── REFUGE2
|
||||
│ │ ├── Annotation-Training400.zip
|
||||
│ │ ├── REFUGE-Test400.zip
|
||||
│ │ ├── REFUGE-Test-GT.zip
|
||||
│ │ ├── REFUGE-Training400.zip
|
||||
│ │ ├── REFUGE-Validation400.zip
|
||||
│ │ ├── REFUGE-Validation400-GT.zip
|
||||
│ ├── __MACOSX
|
||||
```
|
||||
|
||||
运行如下命令，就可以按照 REFUGE2018 挑战赛划分数据集的标准将数据集切分成训练集、验证集、测试集:
|
||||
|
||||
```shell
|
||||
python tools/convert_datasets/refuge.py --raw_data_root=/path/to/refuge/REFUGE2/REFUGE2
|
||||
```
|
||||
|
||||
这个脚本将自动生成下面的文件夹结构：
|
||||
|
||||
```none
|
||||
│ ├── REFUGE
|
||||
│ │ ├── images
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
│ │ ├── annotations
|
||||
│ │ │ ├── training
|
||||
│ │ │ ├── validation
|
||||
│ │ │ ├── test
|
||||
```
|
||||
|
||||
其中包括 400 张图片的训练集, 400 张图片的验证集和 400 张图片的测试集.
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@ from .loveda import LoveDADataset
|
|||
from .night_driving import NightDrivingDataset
|
||||
from .pascal_context import PascalContextDataset, PascalContextDataset59
|
||||
from .potsdam import PotsdamDataset
|
||||
from .refuge import REFUGEDataset
|
||||
from .stare import STAREDataset
|
||||
from .synapse import SynapseDataset
|
||||
# yapf: disable
|
||||
|
|
@ -48,5 +49,5 @@ __all__ = [
|
|||
'DecathlonDataset', 'LIPDataset', 'ResizeShortestEdge',
|
||||
'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
|
||||
'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip',
|
||||
'SynapseDataset'
|
||||
'SynapseDataset', 'REFUGEDataset'
|
||||
]
|
||||
|
|
|
|||
|
|
@ -0,0 +1,28 @@
|
|||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import mmengine.fileio as fileio
|
||||
|
||||
from mmseg.registry import DATASETS
|
||||
from .basesegdataset import BaseSegDataset
|
||||
|
||||
|
||||
@DATASETS.register_module()
|
||||
class REFUGEDataset(BaseSegDataset):
|
||||
"""REFUGE dataset.
|
||||
|
||||
In segmentation map annotation for REFUGE, 0 stands for background, which
|
||||
is not included in 2 categories. ``reduce_zero_label`` is fixed to True.
|
||||
The ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is fixed to
|
||||
'.png'.
|
||||
"""
|
||||
METAINFO = dict(
|
||||
classes=('background', ' Optic Cup', 'Optic Disc'),
|
||||
palette=[[120, 120, 120], [6, 230, 230], [56, 59, 120]])
|
||||
|
||||
def __init__(self, **kwargs) -> None:
|
||||
super().__init__(
|
||||
img_suffix='.png',
|
||||
seg_map_suffix='.png',
|
||||
reduce_zero_label=False,
|
||||
**kwargs)
|
||||
assert fileio.exists(
|
||||
self.data_prefix['img_path'], backend_args=self.backend_args)
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 2.8 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 287 KiB |
|
|
@ -8,7 +8,8 @@ import pytest
|
|||
from mmseg.datasets import (ADE20KDataset, BaseSegDataset, CityscapesDataset,
|
||||
COCOStuffDataset, DecathlonDataset, ISPRSDataset,
|
||||
LIPDataset, LoveDADataset, PascalVOCDataset,
|
||||
PotsdamDataset, SynapseDataset, iSAIDDataset)
|
||||
PotsdamDataset, REFUGEDataset, SynapseDataset,
|
||||
iSAIDDataset)
|
||||
from mmseg.registry import DATASETS
|
||||
from mmseg.utils import get_classes, get_palette
|
||||
|
||||
|
|
@ -232,6 +233,19 @@ def test_synapse():
|
|||
assert len(test_dataset) == 2
|
||||
|
||||
|
||||
def test_refuge():
|
||||
test_dataset = REFUGEDataset(
|
||||
pipeline=[],
|
||||
data_prefix=dict(
|
||||
img_path=osp.join(
|
||||
osp.dirname(__file__),
|
||||
'../data/pseudo_refuge_dataset/img_dir'),
|
||||
seg_map_path=osp.join(
|
||||
osp.dirname(__file__),
|
||||
'../data/pseudo_refuge_dataset/ann_dir')))
|
||||
assert len(test_dataset) == 1
|
||||
|
||||
|
||||
def test_isaid():
|
||||
test_dataset = iSAIDDataset(
|
||||
pipeline=[],
|
||||
|
|
|
|||
|
|
@ -0,0 +1,110 @@
|
|||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import argparse
|
||||
import os
|
||||
import os.path as osp
|
||||
import tempfile
|
||||
import zipfile
|
||||
|
||||
import mmcv
|
||||
import numpy as np
|
||||
from mmengine.utils import mkdir_or_exist
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Convert REFUGE dataset to mmsegmentation format')
|
||||
parser.add_argument('--raw_data_root', help='the root path of raw data')
|
||||
|
||||
parser.add_argument('--tmp_dir', help='path of the temporary directory')
|
||||
parser.add_argument('-o', '--out_dir', help='output path')
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def extract_img(root: str,
|
||||
cur_dir: str,
|
||||
out_dir: str,
|
||||
mode: str = 'train',
|
||||
file_type: str = 'img') -> None:
|
||||
"""_summary_
|
||||
|
||||
Args:
|
||||
Args:
|
||||
root (str): root where the extracted data is saved
|
||||
cur_dir (cur_dir): dir where the zip_file exists
|
||||
out_dir (str): root dir where the data is saved
|
||||
|
||||
mode (str, optional): Defaults to 'train'.
|
||||
file_type (str, optional): Defaults to 'img',else to 'mask'.
|
||||
"""
|
||||
zip_file = zipfile.ZipFile(cur_dir)
|
||||
zip_file.extractall(root)
|
||||
for cur_dir, dirs, files in os.walk(root):
|
||||
# filter child dirs and directories with "Illustration" and "MACOSX"
|
||||
if len(dirs) == 0 and \
|
||||
cur_dir.split('\\')[-1].find('Illustration') == -1 and \
|
||||
cur_dir.find('MACOSX') == -1:
|
||||
|
||||
file_names = [
|
||||
file for file in files
|
||||
if file.endswith('.jpg') or file.endswith('.bmp')
|
||||
]
|
||||
for filename in sorted(file_names):
|
||||
img = mmcv.imread(osp.join(cur_dir, filename))
|
||||
|
||||
if file_type == 'annotations':
|
||||
img = img[:, :, 0]
|
||||
img[np.where(img == 0)] = 1
|
||||
img[np.where(img == 128)] = 2
|
||||
img[np.where(img == 255)] = 0
|
||||
mmcv.imwrite(
|
||||
img,
|
||||
osp.join(out_dir, file_type, mode,
|
||||
osp.splitext(filename)[0] + '.png'))
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
|
||||
raw_data_root = args.raw_data_root
|
||||
if args.out_dir is None:
|
||||
out_dir = osp.join('./data', 'REFUGE')
|
||||
|
||||
else:
|
||||
out_dir = args.out_dir
|
||||
|
||||
print('Making directories...')
|
||||
mkdir_or_exist(out_dir)
|
||||
mkdir_or_exist(osp.join(out_dir, 'images'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'images', 'training'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'images', 'validation'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'images', 'test'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'annotations'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'annotations', 'training'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'annotations', 'validation'))
|
||||
mkdir_or_exist(osp.join(out_dir, 'annotations', 'test'))
|
||||
|
||||
print('Generating images and annotations...')
|
||||
# process data from the child dir on the first rank
|
||||
cur_dir, dirs, files = list(os.walk(raw_data_root))[0]
|
||||
print('====================')
|
||||
|
||||
files = list(filter(lambda x: x.endswith('.zip'), files))
|
||||
|
||||
with tempfile.TemporaryDirectory(dir=args.tmp_dir) as tmp_dir:
|
||||
for file in files:
|
||||
# search data folders for training,validation,test
|
||||
mode = list(
|
||||
filter(lambda x: file.lower().find(x) != -1,
|
||||
['training', 'test', 'validation']))[0]
|
||||
file_root = osp.join(tmp_dir, file[:-4])
|
||||
file_type = 'images' if file.find('Anno') == -1 and file.find(
|
||||
'GT') == -1 else 'annotations'
|
||||
extract_img(file_root, osp.join(cur_dir, file), out_dir, mode,
|
||||
file_type)
|
||||
|
||||
print('Done!')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Loading…
Reference in New Issue