Dss Pytorch

⭐️ PyTorch implement of Deeply Supervised Salient Object Detection with Short Connection
Alternatives To Dss Pytorch
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
3 hours ago35May 21, 2022276agpl-3.0Python
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Mmdetection24,3851912 hours ago37June 01, 2022798apache-2.0Python
OpenMMLab Detection Toolbox and Benchmark
Deep Learning For Image Processing14,599
3 months ago28gpl-3.0Python
deep learning for image processing including classification and object-detection etc.
a day ago6agpl-3.0Python
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
3 hours ago2September 08, 2022490mitTypeScript
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
5 hours ago752agpl-3.0Python
NEW - YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
11 days ago3April 22, 2022647apache-2.0Python
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Pytorch Grad Cam7,414114 days ago25May 20, 202271mitPython
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
a month agoapache-2.0
Techniques for deep learning with satellite & aerial imagery
4 hours ago235apache-2.0Python
AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data
Alternatives To Dss Pytorch
Select To Compare

Alternative Project Comparisons


PyTorch implement of Deeply Supervised Salient Object Detection with Short Connection

The official caffe version: DSS



The information of Loss:

Example output:

Note: here the "blur boundary" caused by bad combine method

Different connection output:

Some difference

  1. The original paper use:$Z=h(\sum_{i=2}^4 f_mR^{(m)})$,here we use $Z=h(\sum_{i=1}^6 f_mR^{(m)})$ in inference stage

Results Reproduct

Dataset (MSRA-B) Paper Here (v1) Only Fusion (v1) Here (v2) Only Fusion (v2) Here(v2 700)
MAE (without CRF) 0.043 0.054 0.052 0.068 0.052 0.051
F_beta (without CRF) 0.920 0.910 0.914 0.912 0.910 0.918
MAE (with CRF) 0.028 0.047 0.048 0.047 0.049 0.047
F_beta (with CRF) 0.927 0.916 0.917 0.915 0.918 0.923


  1. v1 means use average fusion , v2 means use learnable fusion
  2. You can try to use other "inference stragedy"(I think other combine can get better results --- here use sout-2+sout-3+sout-4+fusion --- you can just change self.select
  3. v2 700 means training with 700 epochs. (I use pre-trained model by 500 epochs:so the optimizer is a little differnt to direct 700 eopch)


1. Clone the repository

git clone [email protected]:AceCoooool/DSS-pytorch.git
cd DSS-pytorch/

2. Download the dataset

Download the MSRA-B dataset. (If you can not find this dataset, email to me --- I am not sure whether it's legal to put it on BaiDuYun)

# file construction
  --- annotation
      --- xxx.png
      --- xxx.png
  --- image
      --- xxx.jpg
      --- xxx.jpg
  --- test_cvpr2013.txt
  --- train_cvpr2013.txt
  --- valid_cvpr2013.txt
  --- test_cvpr2013_debug.txt
  --- train_cvpr2013_debug.txt
  --- valid_cvpr2013_debug.txt

3. Get pre-trained vgg

cd tools/
python extract_vgg.py
cd ..

4. Demo

pleease see demo.ipynb


  1. default choose: download and copy the pretrained model to weights directory

5. Train

python main.py --mode='train' --train_path='you_data' --label_path='you_label' --batch_size=8 --visdom=True --train_file='you_file'


  1. --val=True add the validation (but your need to add the --val_path, --val_file and --val_label)
  2. you_data, you_label means your training data root. (connect to the step 2)
  3. If you Download the data to youhome/data/MSRA-B(you can not "implicity" the path)

6. Test

python main.py --mode='test' --test_path='you_data' --test_label='your_label' --use_crf=False --model='your_trained_model' --test_file='you_file'


  1. only support bath_size=1
  2. --use_crf=True:means use CRF post-process
Popular Pytorch Projects
Popular Object Detection Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Jupyter Notebook
Object Detection