(ECCV 2020) Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection
(ECCV 2020) Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection
Gitee Mirror: https://gitee.com/p_lart/HDFNet
Author: Lart Pang(
[email protected]
)This is a complete, modular and easily modified code base based on PyTorch, which is suitable for the training and testing of significant target detection task model.
@inproceedings{HDFNet-ECCV2020,
author = {Youwei Pang and Lihe Zhang and Xiaoqi Zhao and Huchuan Lu},
title = {Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection},
booktitle = ECCV,
year = {2020}
}
News:
NOTE:
_STEREO
)._STEREO
, two versions of the STEREO dataset are provided.
_STEREO
.[Results & PretrainedParams (j9qu)]
backbone
: Store some code for backbone networks.loss
: The code of the loss function.module
: The code of important modules.network
: The code of the network.output
: It saves all results.utils
: Some instrumental code.
data/*py
: Some files about creating the dataloader.transforms/*py
: Some operations on data augmentation.metric.py
: max/mean/weighted F-measure, S-measure, E-measure and MAE. (NOTE: If you find a problem in this part of the code, please notify me in time, thank you.)misc.py
: Some useful utility functions.tensor_ops.py
: Some operations about tensors.config.py
: Configuration file for model training and testing.train.py
: I think you can understand.test.py
and test.sh
: These files can evaluate the performance of the model on the specified dataset. And the file test.sh
is a simple example about how to configure and run test.py
.I provided conda environment configuration file (hdfnet.yaml), you can refer to the package version information.
And you can try conda env create -f hdfnet.yaml
to create an environment to run our code.
module
.network
and import your model in the network/__init__.py
.config.py
:
datasets_root
arg_config
model
corresponds to the name of the model in network
suffix
: finally, the form of <model>_<suffix>
is used to form the alias of the model of this experiment and all files related to this experiment will be saved to the folder <model>_<suffix>
in output
folderresume
: set it to False
to train normallydata_mode
: set it to RGBD
or RGB
for using RGBD SOD datasets or RGB SOD datasets to train mdoel.lr
, batch_size
and so on...python train.py
If the training process is interrupted, you can use the following strategy to resume the training process.
resume
to True
.train.py
again.There are two ways:
resume
to True
and run the script train.py
again.test.sh
and test.py
. The specific method of use can be obtained by executing this command: python test.py --help
.You can use the toolkit released by us: https://github.com/lartpang/Py-SOD-VOS-EvalToolkit.