Data

Tools

Indexes

Applications

Experiments

Open Source Science

ttp

Implement of the paper "Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection"

https://github.com/kyanchen/ttp

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Implement of the paper "Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection"

Basic Info
  • Host: GitHub
  • Owner: KyanChen
  • License: apache-2.0
  • Language: Python
  • Default Branch: release
  • Homepage:
  • Size: 28.6 MB
Statistics
  • Stars: 80
  • Watchers: 3
  • Forks: 4
  • Open Issues: 7
  • Releases: 0
Created about 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection



Project Page      arXiv      HFSpace      PDF


GitHub stars license arXiv Hugging Face Spaces



English | [简体中文](README_zh-CN.md)

Introduction

The repository is the code implementation of the paper Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection, based on MMSegmentation and Open-CD projects.

The current branch has been tested under PyTorch 2.x and CUDA 12.1, supports Python 3.7+, and is compatible with most CUDA versions.

If you find this project helpful, please give us a star ⭐️, your support is our greatest motivation.

Main Features - Consistent API interface and usage with MMSegmentation - Open sourced the TTP model in the paper - Tested with AMP training method - Supports multiple dataset extensions

Update Log

🌟 2023.12.23 Released the TTP project code, which is completely consistent with the API interface and usage of MMSegmentation.

🌟 2023.12.30 Released the model trained on Levir-CD.

🌟 2024.02.10 This project has been included in the Open-CD project.

Table of Contents

Installation

Dependencies

  • Linux or Windows
  • Python 3.7+, recommended 3.10
  • PyTorch 2.0 or higher, recommended 2.1
  • CUDA 11.7 or higher, recommended 12.1
  • MMCV 2.0 or higher, recommended 2.1

Environment Installation

We recommend using Miniconda for installation. The following command will create a virtual environment named ttp and install PyTorch and MMCV.

Note: If you have experience with PyTorch and have already installed it, you can skip to the next section. Otherwise, you can follow these steps to prepare.

**Step 0**: Install [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/index.html). **Step 1**: Create a virtual environment named `ttp` and activate it. ```shell conda create -n ttp python=3.10 -y conda activate ttp ``` **Step 2**: Install [PyTorch2.1.x](https://pytorch.org/get-started/locally/). Linux/Windows: ```shell pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu121 ``` Or ```shell conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia ``` **Step 3**: Install [MMCV2.1.x](https://mmcv.readthedocs.io/en/latest/get_started/installation.html). ```shell pip install -U openmim mim install mmcv==2.1.0 ``` **Step 4**: Install other dependencies. ```shell pip install -U wandb einops importlib peft==0.8.2 scipy ftfy prettytable torchmetrics==1.3.1 transformers==4.38.1 ```

Install TTP

Download or clone the TTP repository.

shell git clone git@github.com:KyanChen/TTP.git cd TTP

Dataset Preparation

### Levir-CD Change Detection Dataset #### Dataset Download - Image and label download address: [Levir-CD](https://chenhao.in/LEVIR/). #### Organization Method You can also choose other sources to download the data, but you need to organize the dataset in the following format: ``` ${DATASET_ROOT} # Dataset root directory, for example: /home/username/data/levir-cd ├── train │ ├── A │ ├── B │ └── label ├── val │ ├── A │ ├── B │ └── label └── test ├── A ├── B └── label ``` Note: In the project folder, we provide a folder named `data`, which contains an example of the organization method of the above dataset. ### Other Datasets If you want to use other datasets, you can refer to [MMSegmentation documentation](https://mmsegmentation.readthedocs.io/zh-cn/latest/user_guides/2_dataset_prepare.html) to prepare the datasets.

Model Training

TTP Model

Config File and Main Parameter Parsing

We provide the configuration files of the TTP model used in the paper, which can be found in the configs/TTP folder. The Config file is completely consistent with the API interface and usage of MMSegmentation. Below we provide an analysis of some of the main parameters. If you want to know more about the meaning of the parameters, you can refer to MMSegmentation documentation.

Parameter Parsing:

  • work_dir: The output path of the model training, which generally does not need to be modified.
  • default_hooks-CheckpointHook: Checkpoint saving configuration during model training, which generally does not need to be modified.
  • default_hooks-visualization: Visualization configuration during model training, comment out during training and uncomment during testing.
  • vis_backends-WandbVisBackend: Configuration of network-side visualization tools, after opening the comment, you need to register an account on the wandb official website, and you can view the visualization results during the training process in the network browser.
  • sam_pretrain_ckpt_path: The checkpoint path of the SAM backbone provided by MMPretrain, refer to download address.
  • model-backbone-peft_cfg: Whether to introduce fine-tuning parameters, which generally does not need to be modified.
  • dataset_type: The type of dataset, needs to be modified according to the type of dataset.
  • data_root: Dataset root directory, modify to the absolute path of the dataset root directory.
  • batch_size_per_gpu: The batch size of a single card, needs to be modified according to the memory size.
  • resume: Whether to resume training, which generally does not need to be modified.
  • load_from: The checkpoint path of the model's pre-training, which generally does not need to be modified.
  • max_epochs: The maximum number of training rounds, which generally does not need to be modified.

Single Card Training

shell python tools/train.py configs/TTP/xxx.py # xxx.py is the configuration file you want to use

Multi-card Training

shell sh ./tools/dist_train.sh configs/TTP/xxx.py ${GPU_NUM} # xxx.py is the configuration file you want to use, GPU_NUM is the number of GPUs used

Other Instance Segmentation Models

If you want to use other change detection models, you can refer to [Open-CD](https://github.com/likyoo/open-cd) to train the models, or you can put their Config files into the `configs` folder of this project, and then train them according to the above method.

Model Testing

Single Card Testing:

shell python tools/test.py configs/TTP/xxx.py ${CHECKPOINT_FILE} # xxx.py is the configuration file you want to use, CHECKPOINT_FILE is the checkpoint file you want to use

Multi-card Testing:

shell sh ./tools/dist_test.sh configs/TTP/xxx.py ${CHECKPOINT_FILE} ${GPU_NUM} # xxx.py is the configuration file you want to use, CHECKPOINT_FILE is the checkpoint file you want to use, GPU_NUM is the number of GPUs used

Note: If you need to get the visualization results, you can uncomment default_hooks-visualization in the Config file.

Image Prediction

Single Image Prediction:

shell python demo/image_demo_with_cdinferencer.py ${IMAGE_FILE1} ${IMAGE_FILE2} configs/TTP/ttp_sam_large_levircd_infer.py --checkpoint ${CHECKPOINT_FILE} --out-dir ${OUTPUT_DIR} # IMAGE_FILE is the image file you want to predict, xxx.py is the configuration file, CHECKPOINT_FILE is the checkpoint file you want to use, OUTPUT_DIR is the output path of the prediction result

FAQ

We have listed some common problems and their corresponding solutions here. If you find that some problems are missing, please feel free to provide a PR to enrich this list. If you cannot get help here, please use [issue](https://github.com/KyanChen/TTP/issues) to seek help. Please fill in all the required information in the template, which will help us locate the problem faster. ### 1. Do I need to install MMSegmentation, MMPretrain, MMDet, Open-CD? We recommend that you do not install them, because we have partially modified their code, which may cause errors in the code if you install them. If you get an error that the module has not been registered, please check: - Whether these libraries are installed, if so, uninstall them - Whether `@MODELS.register_module()` is added in front of the class name, if not, add it - Whether `from .xxx import xxx` is added in `__init__.py`, if not, add it - Whether `custom_imports = dict(imports=['mmseg.ttp'], allow_failed_imports=False)` is added in the Config file, if not, add it ### 2. About resource consumption Here we list the resource consumption of using different training methods for your reference. | Model Name | Backbone Type | Image Size | GPU | Batch Size | Acceleration Strategy | Single Card Memory Usage | Training Time | |:----:|:--------:|:-------:|:---------------:|:----------:|:----:|:-------:|:----:| | TTP | ViT-L/16 | 512x512 | 4x RTX 4090 24G | 2 | FP32 | 14 GB | 3H | | TTP | ViT-L/16 | 512x512 | 4x RTX 4090 24G | 2 | FP16 | 12 GB | 2H | ### 4. Solution to dist_train.sh: Bad substitution If you get a `Bad substitution` error when running `dist_train.sh`, use `bash dist_train.sh` to run the script. ### 5. You should set `PYTHONPATH` to make `sys.path` include the directory which contains your custom module Please check the detailed error message, generally some dependent packages are not installed, please use `pip install` to install the dependent packages.

Acknowledgements

The repository is the code implementation of the paper Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection, based on MMSegmentation and Open-CD projects.

Citation

If you use the code or performance benchmarks of this project in your research, please refer to the following bibtex to cite TTP.

@misc{chen2023time, title={Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection}, author={Keyan Chen and Chengyang Liu and Wenyuan Li and Zili Liu and Hao Chen and Haotian Zhang and Zhengxia Zou and Zhenwei Shi}, year={2023}, eprint={2312.16202}, archivePrefix={arXiv}, primaryClass={cs.CV} }

License

The repository is licensed under the Apache 2.0 license.

Contact Us

If you have other questions❓, please contact us in time 👬

Owner

  • Name: Keyan Chen
  • Login: KyanChen
  • Kind: user
  • Location: Beijing
  • Company: Beihang University

I am a Ph.D. student at Beihang University, primarily focused on remote sensing image processing, deep learning, and multimodal.

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMSegmentation Contributors"
title: "OpenMMLab Semantic Segmentation Toolbox and Benchmark"
date-released: 2020-07-10
url: "https://github.com/open-mmlab/mmsegmentation"
license: Apache-2.0

GitHub Events

Total
  • Issues event: 9
  • Watch event: 23
  • Issue comment event: 5
  • Fork event: 2
Last Year
  • Issues event: 9
  • Watch event: 23
  • Issue comment event: 5
  • Fork event: 2

Dependencies

.github/workflows/deploy.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
.circleci/docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/serve/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
requirements/albu.txt pypi
  • albumentations >=0.3.2
requirements/docs.txt pypi
  • docutils ==0.16.0
  • myst-parser *
  • sphinx ==4.0.2
  • sphinx_copybutton *
  • sphinx_markdown_tables *
  • urllib3 <2.0.0
requirements/mminstall.txt pypi
  • mmcv >=2.0.0rc4,<2.2.0
  • mmengine >=0.5.0,<1.0.0
requirements/multimodal.txt pypi
  • ftfy *
  • regex *
requirements/optional.txt pypi
  • cityscapesscripts *
  • diffusers *
  • einops ==0.3.0
  • imageio ==2.9.0
  • imageio-ffmpeg ==0.4.2
  • invisible-watermark *
  • kornia ==0.6
  • nibabel *
  • omegaconf ==2.1.1
  • pudb ==2019.2
  • pytorch-lightning ==1.4.2
  • streamlit >=0.73.1
  • test-tube >=0.7.5
  • timm *
  • torch-fidelity ==0.3.0
  • torchmetrics ==0.6.0
  • transformers ==4.19.2
requirements/readthedocs.txt pypi
  • mmcv >=2.0.0rc1,<2.1.0
  • mmengine >=0.4.0,<1.0.0
  • prettytable *
  • scipy *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • matplotlib *
  • numpy *
  • packaging *
  • prettytable *
  • scipy *
requirements/tests.txt pypi
  • codecov * test
  • flake8 * test
  • ftfy * test
  • interrogate * test
  • pytest * test
  • regex * test
  • xdoctest >=0.10.0 test
  • yapf * test
requirements.txt pypi
setup.py pypi