aip490-small-object-detection-sp24ai05
A new approach for small object detection with YOLOv5
https://github.com/huynhlam1352/aip490-small-object-detection-sp24ai05
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○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 (5.0%) to scientific vocabulary
Repository
A new approach for small object detection with YOLOv5
Basic Info
- Host: GitHub
- Owner: HuynhLam1352
- Language: Python
- Default Branch: main
- Size: 224 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
AIP490 - SMALL OBJECT DETECTION IN UAV IMAGES
Install
bash
$ git clone https://github.com/HuynhLam1352/AIP490-Small-Object-Detection-SP24AI05.git
$ cd AIP490-Small-Object-Detection-SP24AI05
$ pip install -r requirements.txt
Run demo
bash
$ streamlit run main.py
Resources
Datasets: VisDroneWeights: CustomYOLO
validation
val.py runs inference on VisDrone2019-DET-val, using weights trained with OursYOLO.
bash
$ python val.py --weights ./weights/OursYOLO.pt --img 640 --data ./data/VisDrone.yaml --task val --batch-size 8
Train
train.py allows you to train new model from strach. ```bash $ python train.py --img 640 --batch 8 --epochs 100 --data ./data/VisDrone.yaml --weights yolov5s.pt --cfg models/ourYolo.yaml
```
Collaborators
- Lieu Bach Thanh
- Nguyen Huynh Lam
- Nguyen Chi Khang
References
Thanks to their great works * ultralytics/yolov5
Owner
- Name: Nguyễn Huỳnh Lâm
- Login: HuynhLam1352
- Kind: user
- Location: Ho Chi Minh City, Viet Nam
- Company: FPT University
- Website: https://www.facebook.com/be.bum.94
- Repositories: 1
- Profile: https://github.com/HuynhLam1352
ℓé
GitHub Events
Total
- Push event: 1
Last Year
- Push event: 1
Dependencies
- pytorch/pytorch 2.0.0-cuda11.7-cudnn8-runtime build
- gcr.io/google-appengine/python latest build
- Pillow >=10.0.1
- PyYAML >=5.3.1
- gitpython >=3.1.30
- matplotlib >=3.3
- numpy >=1.23.5
- opencv-python >=4.1.1
- pandas >=1.1.4
- psutil *
- requests >=2.23.0
- scipy >=1.4.1
- seaborn >=0.11.0
- setuptools >=65.5.1
- thop >=0.1.1
- torchvision >=0.9.0
- tqdm >=4.64.0
- ultralytics >=8.0.232
- Flask ==2.3.2
- gunicorn ==19.10.0
- pip ==23.3
- werkzeug >=3.0.1