Giter VIP home page Giter VIP logo

eaefnet's Introduction

EAEFNet

license PyTorch-1.10.0

Introduction

This is the official pytorch implementation of EAEFNet: Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks. Some of the codes are borrowed from MFNet , RTFNet , LSNet and RGBT-CC. The master branch works with PyTorch 1.10+.

Installation

Crow-Counting

conda create -n EAEF python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y
conda activate EAEF
cd EAEFNet_RGBT-CC
pip install -r requirements.txt

Detection

conda create -n EAEF python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y
conda activate EAEF
pip install openmim
mim install "mmengine>=0.3.1"
mim install "mmcv>=2.0.0rc1,<2.1.0"
mim install "mmdet>=3.0.0rc3,<3.1.0"
cd EAEFNet_Detection/EAEF_mmyolo
# Install albumentations
pip install -r requirements/albu.txt
# Install MMYOLO , don't forget it!
mim install -v -e .

Segmentation

conda create -n EAEF python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y
conda activate EAEF
cd EAEFNet_Seg_MF/EAEFNet_MF
pip install -r requirements.txt

SOD

conda create -n EAEF python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y
conda activate EAEF
cd EAEFNet_SOD
pip install -r requirements.txt

Data Download

1671154999406

MFTNet Dataset: http://gofile.me/4jm56/CfukComo1

PST900 Dataset: https://drive.google.com/file/d/1hZeM-MvdUC_Btyok7mdF00RV-InbAadm/view

M3FD Dataset: https://drive.google.com/drive/folders/1H-oO7bgRuVFYDcMGvxstT1nmy0WF_Y_6

RGBT-CC Dataset: https://www.dropbox.com/sh/o4ww2f5tv3nay9n/AAA4CfVMTZcdwsFxFlhwDsSba?dl=0

Ps: You also can download them from here!

Trained Model Download

Task Dataset model mIoU Trained Model
Segmentation MFNet EAEFNet 58.91% https://drive.google.com/drive/folders/12ONwVaaO35VbW7rZ83P-pSVWp_bFiPhv?usp=share_link
Segmentation PSP900 EAEFNet 85.56% https://drive.google.com/drive/folders/1Czm7vtmaW6fTCk4fBAfO2OAWoHrJry9Z?usp=share_link
Task Dataset model [email protected] Trained Model
Detection M3FD EAEF+Yolov5 80.4% https://drive.google.com/drive/folders/1JcvZUmTUB936H9JoYjYrM9H-jHKnjNzc?usp=share_link
Task Dataset model RMSE Trained Model
Crowcount RGBTCC EAEF 21.85% https://drive.google.com/drive/folders/1eb0GwISb0AUULrDpUo8jBZC5Oh4zShgD?usp=share_link
Task Dataset model MAE Trained Model
SOD VT5000 EAEF 0.0031 https://drive.google.com/file/d/1mIcCKumip27fcSFnbvGIsycUvUTrYk36/view?usp=share_link

Test

M3FD Detection

python EAEF_mmyolo/tools/test.py yolov5/bi_yolov5 

MFNet Segmentation

python EAEF_MF/run_own_pth.py

PST900 Segmentation

python EAEF_PST/run_own_pth.py

RGBT-CC Crow-counting

python EAEF_CC/test.py

VT821/VT1000/VT5000 SOD

python EAEF_SOD/test.py

eaefnet's People

Contributors

matrixgame2018 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.