Data

Tools

Indexes

Applications

Experiments

Open Source Science

icpr_jnu_mmd

https://github.com/yangxiao2/icpr_jnu_mmd

Science Score: 44.0%

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
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: yangxiao2
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 29.5 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme Contributing License Citation

README.md

ICPR Multi-Modal Visual Pattern Recognition Challenge Track 2: Multi-Modal Object Detection

Overview

This is the official repository for Track 2: Multi-Modal Object Detection challenge (ICPR 2024).

This challenge focuses on Object Detection utilizing multi-modal data source including RGB, depth, and infrared images. You can visit the official website for more details or directly participate in this track on codalab.

Dataset

In this track, we provide a dataset named ICPR_JNU MDetection-v1, which comprises 5,000 multi-modal image pairs (4000 for training and 1000 for testing) across 13 classes. Details are as follows in this repo. To participate in this track, please submit your requirements by choosing "Challenge Track 2: Multi-modal Detection" in this Online Form and filling out other options.

Details

| Lables | Labels Correlation | |:-----------:|:-----------:| || |

Examples

| Depth | Thermal-IR | RGB | |:-----------:|:------------:|:---------:| | Depth Output | IR Output | RGB Output | | Depth Output | IR Output | RGB Output |

Structure

ICPR_JNU MDetection-v1 ├──/images/ │ ├── train │ │ ├──color │ │ │ ├── train_0001.png │ │ │ ├── train_0002.png │ │ │ ├── ... ... │ │ │ ├── train_4000.png │ │ ├──depth │ │ │ ├── train_0001.png │ │ │ ├── train_0002.png │ │ │ ├── ... ... │ │ │ ├── train_4000.png │ │ ├──infrared │ │ │ ├── train_0001.png │ │ │ ├── train_0002.png │ │ │ ├── ... ... │ │ │ ├── train_4000.png │ ├── val │ │ ├── ... ... │ ├── test │ │ ├──color │ │ │ ├── test_0001.png │ │ │ ├── test_0002.png │ │ │ ├── ... ... │ │ │ ├── test_1000.png │ │ ├──depth │ │ │ ├── test_0001.png │ │ │ ├── test_0002.png │ │ │ ├── ... ... │ │ │ ├── test_1000.png │ │ ├──infrared │ │ │ ├── test_0001.png │ │ │ ├── test_0002.png │ │ │ ├── ... ... │ │ │ ├── test_1000.png └──/labels/ ├── /train/color/ │ ├── train_0001.txt │ ├── train_0002.txt │ │ ├── ... ... │ ├── train_4000.txt ├── /val/color │ ├── ... ... ├── /test/color/ │ ├── test_0001.txt │ ├── test_0002.txt │ │ ├── ... ... │ ├── test_1000.txt └───

Baseline

This code is based on yolo-v5, you can follow the README_yolo.md or README_yolo.zh-CN.md first to build an environment. We have modified it to accommodate this multimodal task, while you can also build your own model to accomplish this task.

In this code, we provide a /data/ICPRJNUMMDetection_v1.yaml to suit this dataset. You should prepare the dataset and change the path to your own in this file.

  • ❗Note!!! The validation set is not provided, you should divide the train set appropriately by yourself to validate during training.

Training

  • To build your own model, you should redesign the modules in ./models/yolo.py at least.
  • To train your own model, you should modify the Hyperparameters in ./data/hyps first.
  • Train your own model directly using: bash python train.py ## Testing

Generate the predictions pred.zip for test set:

bash python test_model.py

  • ❗Note that labels in testset are all blank, only on purpose of generating your predictions conveniently. Results pred.zip will be generated automatically and it's the only file you need to submit to Codalab for evaluation. More details of evaluation can be found here.

If you have any questions, please email us at yangxiao2326@gmail.com.

Owner

  • Login: yangxiao2
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
preferred-citation:
  type: software
  message: If you use YOLOv5, please cite it as below.
  authors:
  - family-names: Jocher
    given-names: Glenn
    orcid: "https://orcid.org/0000-0001-5950-6979"
  title: "YOLOv5 by Ultralytics"
  version: 7.0
  doi: 10.5281/zenodo.3908559
  date-released: 2020-5-29
  license: AGPL-3.0
  url: "https://github.com/ultralytics/yolov5"

GitHub Events

Total
Last Year

Dependencies

utils/docker/Dockerfile docker
  • pytorch/pytorch 2.0.0-cuda11.7-cudnn8-runtime build
utils/google_app_engine/Dockerfile docker
  • gcr.io/google-appengine/python latest build
pyproject.toml pypi
  • matplotlib >=3.3.0
  • numpy >=1.22.2
  • opencv-python >=4.6.0
  • pandas >=1.1.4
  • pillow >=7.1.2
  • psutil *
  • py-cpuinfo *
  • pyyaml >=5.3.1
  • requests >=2.23.0
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • thop >=0.1.1
  • torch >=1.8.0
  • torchvision >=0.9.0
  • tqdm >=4.64.0
  • ultralytics >=8.1.47
requirements.txt pypi
  • PyYAML >=5.3.1
  • gitpython >=3.1.30
  • matplotlib >=3.3
  • numpy >=1.23.5
  • opencv-python >=4.1.1
  • pandas >=1.1.4
  • pillow >=10.3.0
  • psutil *
  • requests >=2.32.0
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • setuptools >=65.5.1
  • thop >=0.1.1
  • torchvision >=0.9.0
  • tqdm >=4.64.0
utils/google_app_engine/additional_requirements.txt pypi
  • Flask ==2.3.2
  • gunicorn ==22.0.0
  • pip ==23.3
  • werkzeug >=3.0.1