[Feature] Add SOD datasets

configs/_base_/datasets/duts.py

@@ -0,0 +1,56 @@
+# dataset settings
+dataset_type = 'DUTSDataset'
+data_root = 'data/DUTS'
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+img_scale = (352, 352)
+crop_size = (320, 320)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations'),
+ dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
+ dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+ dict(type='RandomFlip', prob=0.5),
+ dict(type='PhotoMetricDistortion'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=img_scale,
+ # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img'])
+ ])
+]
+
+data = dict(
+ samples_per_gpu=4,
+ workers_per_gpu=4,
+ train=dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='images/training',
+ ann_dir='annotations/training',
+ pipeline=train_pipeline),
+ val=dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='images/validation',
+ ann_dir='annotations/validation',
+ pipeline=test_pipeline),
+ test=dict(
+ type=dataset_type,
+ data_root=data_root,
+ img_dir='images/validation',
+ ann_dir='annotations/validation',
+ pipeline=test_pipeline))

docs/dataset_prepare.md

@@ -108,6 +108,28 @@ mmsegmentation
 | | └── leftImg8bit
 | | | └── test
 | | | └── night
+| ├── DUTS
+│ │ ├── images
+│ │ │ ├── training
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── training
+│ │ │ ├── validation
+| ├── DUT-OMRON
+│ │ ├── images
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── validation
+| ├── ECSSD
+│ │ ├── images
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── validation
+| ├── HKU-IS
+│ │ ├── images
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── validation
 ```
 
 ### Cityscapes
@@ -253,3 +275,49 @@ Since we only support test models on this dataset, you may only download [the va
 ### Nighttime Driving
 
 Since we only support test models on this dataset, you may only download [the test set](http://data.vision.ee.ethz.ch/daid/NighttimeDriving/NighttimeDrivingTest.zip).
+
+### DUTS
+
+First，download [DUTS-TR.zip](http://saliencydetection.net/duts/download/DUTS-TR.zip) and [DUTS-TE.zip](http://saliencydetection.net/duts/download/DUTS-TE.zip) .
+
+To convert DUTS dataset to MMSegmentation format, you should run the following command:
+
+```shell
+python tools/convert_datasets/duts.py /path/to/DUTS-TR.zip /path/to/DUTS-TE.zip
+```
+
+### DUT-OMRON
+
+In salient object detection (SOD), DUT-OMRON is used for evaluation.
+
+First，download [DUT-OMRON-image.zip](http://saliencydetection.net/dut-omron/download/DUT-OMRON-image.zip) and [DUT-OMRON-gt-pixelwise.zip.zip](http://saliencydetection.net/dut-omron/download/DUT-OMRON-gt-pixelwise.zip.zip) .
+
+To convert DUT-OMRON dataset to MMSegmentation format, you should run the following command:
+
+```shell
+python tools/convert_datasets/dut_omron.py /path/to/DUT-OMRON-image.zip /path/to/DUT-OMRON-gt-pixelwise.zip.zip
+```
+
+### ECSSD
+
+In salient object detection (SOD), ECSSD is used for evaluation.
+
+First，download [images.zip](https://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/data/ECSSD/images.zip) and [ground_truth_mask.zip](https://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/data/ECSSD/ground_truth_mask.zip) .
+
+To convert ECSSD dataset to MMSegmentation format, you should run the following command:
+
+```shell
+python tools/convert_datasets/ecssd.py /path/to/images.zip /path/to/ground_truth_mask.zip
+```
+
+### HKU-IS
+
+In salient object detection (SOD), HKU-IS is used for evaluation.
+
+First，download [HKU-IS.rar](https://sites.google.com/site/ligb86/mdfsaliency/).
+
+To convert HKU-IS dataset to MMSegmentation format, you should run the following command:
+
+```shell
+python tools/convert_datasets/hku_is.py /path/to/HKU-IS.rar
+```

docs_zh-CN/dataset_prepare.md

@@ -89,6 +89,28 @@ mmsegmentation
 | | └── leftImg8bit
 | | | └── test
 | | | └── night
+| ├── DUTS
+│ │ ├── images
+│ │ │ ├── training
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── training
+│ │ │ ├── validation
+| ├── DUT-OMRON
+│ │ ├── images
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── validation
+| ├── ECSSD
+│ │ ├── images
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── validation
+| ├── HKU-IS
+│ │ ├── images
+│ │ │ ├── validation
+│ │ ├── annotations
+│ │ │ ├── validation
 ```
 
 ### Cityscapes
@@ -195,3 +217,49 @@ python tools/convert_datasets/stare.py /path/to/stare-images.tar /path/to/labels
 ### 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)。
+
+### DUTS
+
+首先，下载 [DUTS-TR.zip](http://saliencydetection.net/duts/download/DUTS-TR.zip) 和 [DUTS-TE.zip](http://saliencydetection.net/duts/download/DUTS-TE.zip) 。
+
+为了将 DUTS 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
+
+```shell
+python tools/convert_datasets/duts.py /path/to/DUTS-TR.zip /path/to/DUTS-TE.zip
+```
+
+### DUT-OMRON
+
+显著性检测（SOD）任务中 DUT-OMRON 仅作为测试集。
+
+首先，下载 [DUT-OMRON-image.zip](http://saliencydetection.net/dut-omron/download/DUT-OMRON-image.zip) 和 [DUT-OMRON-gt-pixelwise.zip.zip](http://saliencydetection.net/dut-omron/download/DUT-OMRON-gt-pixelwise.zip.zip) 。
+
+为了将 DUT-OMRON 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
+
+```shell
+python tools/convert_datasets/dut_omron.py /path/to/DUT-OMRON-image.zip /path/to/DUT-OMRON-gt-pixelwise.zip.zip
+```
+
+### ECSSD
+
+显著性检测（SOD）任务中 ECSSD 仅作为测试集。
+
+首先，下载 [images.zip](https://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/data/ECSSD/images.zip) 和 [ground_truth_mask.zip](https://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/data/ECSSD/ground_truth_mask.zip) 。
+
+为了将 ECSSD 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
+
+```shell
+python tools/convert_datasets/ecssd.py /path/to/images.zip /path/to/ground_truth_mask.zip
+```
+
+### HKU-IS
+
+显著性检测（SOD）任务中 HKU-IS 仅作为测试集。
+
+首先，下载 [HKU-IS.rar](https://sites.google.com/site/ligb86/mdfsaliency/) 。
+
+为了将 HKU-IS 数据集转换成 MMSegmentation 格式，您需要运行如下命令：
+
+```shell
+python tools/convert_datasets/hku_is.py /path/to/HKU-IS.rar
+```

mmseg/apis/test.py

@@ -38,6 +38,7 @@ def single_gpu_test(model,
  efficient_test=False,
  opacity=0.5,
  pre_eval=False,
+ return_logit=False,
  format_only=False,
  format_args={}):
  """Test with single GPU by progressive mode.
@@ -88,7 +89,8 @@ def single_gpu_test(model,
 
  for batch_indices, data in zip(loader_indices, data_loader):
  with torch.no_grad():
- result = model(return_loss=False, **data)
+ result = model(
+ return_loss=False, return_logit=return_logit, **data)
 
  if efficient_test:
  result = [np2tmp(_, tmpdir='.efficient_test') for _ in result]
@@ -99,7 +101,8 @@ def single_gpu_test(model,
  if pre_eval:
  # TODO: adapt samples_per_gpu > 1.
  # only samples_per_gpu=1 valid now
- result = dataset.pre_eval(result, indices=batch_indices)
+ result = dataset.pre_eval(
+ result, return_logit, indices=batch_indices)
 
  results.extend(result)
 
@@ -142,6 +145,7 @@ def multi_gpu_test(model,
  gpu_collect=False,
  efficient_test=False,
  pre_eval=False,
+ return_logit=False,
  format_only=False,
  format_args={}):
  """Test model with multiple gpus by progressive mode.
@@ -204,7 +208,11 @@ def multi_gpu_test(model,
 
  for batch_indices, data in zip(loader_indices, data_loader):
  with torch.no_grad():
- result = model(return_loss=False, rescale=True, **data)
+ result = model(
+ return_loss=False,
+ return_logit=return_logit,
+ rescale=True,
+ **data)
 
  if efficient_test:
  result = [np2tmp(_, tmpdir='.efficient_test') for _ in result]
@@ -215,7 +223,8 @@ def multi_gpu_test(model,
  if pre_eval:
  # TODO: adapt samples_per_gpu > 1.
  # only samples_per_gpu=1 valid now
- result = dataset.pre_eval(result, indices=batch_indices)
+ result = dataset.pre_eval(
+ result, return_logit, indices=batch_indices)
 
  results.extend(result)
 

mmseg/core/evaluation/__init__.py

@@ -2,10 +2,11 @@
 from .class_names import get_classes, get_palette
 from .eval_hooks import DistEvalHook, EvalHook
 from .metrics import (eval_metrics, intersect_and_union, mean_dice,
- mean_fscore, mean_iou, pre_eval_to_metrics)
+ mean_fscore, mean_iou, pre_eval_to_metrics,
+ pre_eval_to_sod_metrics, eval_sod_metrics, calc_sod_metrics)
 
 __all__ = [
  'EvalHook', 'DistEvalHook', 'mean_dice', 'mean_iou', 'mean_fscore',
  'eval_metrics', 'get_classes', 'get_palette', 'pre_eval_to_metrics',
- 'intersect_and_union'
+ 'intersect_and_union', 'calc_sod_metrics', 'eval_sod_metrics', 'pre_eval_to_sod_metrics'
 ]

mmseg/core/evaluation/eval_hooks.py

@@ -30,9 +30,11 @@ def __init__(self,
  by_epoch=False,
  efficient_test=False,
  pre_eval=False,
+ return_logit=False,
  **kwargs):
  super().__init__(*args, by_epoch=by_epoch, **kwargs)
  self.pre_eval = pre_eval
+ self.return_logit = return_logit
  if efficient_test:
  warnings.warn(
  'DeprecationWarning: ``efficient_test`` for evaluation hook '
@@ -47,7 +49,11 @@ def _do_evaluate(self, runner):
 
  from mmseg.apis import single_gpu_test
  results = single_gpu_test(
- runner.model, self.dataloader, show=False, pre_eval=self.pre_eval)
+ runner.model,
+ self.dataloader,
+ show=False,
+ pre_eval=self.pre_eval,
+ return_logit=self.return_logit)
  runner.log_buffer.clear()
  runner.log_buffer.output['eval_iter_num'] = len(self.dataloader)
  key_score = self.evaluate(runner, results)
@@ -77,9 +83,11 @@ def __init__(self,
  by_epoch=False,
  efficient_test=False,
  pre_eval=False,
+ return_logit=False,
  **kwargs):
  super().__init__(*args, by_epoch=by_epoch, **kwargs)
  self.pre_eval = pre_eval
+ self.return_logit = return_logit
  if efficient_test:
  warnings.warn(
  'DeprecationWarning: ``efficient_test`` for evaluation hook '
@@ -115,7 +123,8 @@ def _do_evaluate(self, runner):
  self.dataloader,
  tmpdir=tmpdir,
  gpu_collect=self.gpu_collect,
- pre_eval=self.pre_eval)
+ pre_eval=self.pre_eval,
+ return_logit=self.return_logit)
 
  runner.log_buffer.clear()