yolov8_msg
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 (7.3%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: MInsanKamil
- License: agpl-3.0
- Language: Python
- Default Branch: main
- Size: 6.69 MB
Statistics
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 4
- Releases: 0
Metadata Files
README.md
YOLOv8MSG (MaxSpatialpoolingGhostmodule) adalah YOLOv8 versi nano yang telah dioptimasi menggunakan metode:
- Implementasi Ghost Module
- Modifikasi Bagian Head (Detect):
- DetectGhostModule (ultralytics/nn/modules/head.py):
- GhostConv (ultralytics/nn/modules/conv.py)
- DetectGhostModuleModfication (ultralytics/nn/modules/head.py):
- GhostConvModification (ultralytics/nn/modules/conv.py)
- Penambahan Proses Down-sampling
- Modifikasi Conv Module:
- ConvAvgPooling (ultralytics/nn/modules/conv.py)
- ConvMaxPooling (ultralytics/nn/modules/conv.py)
- ConvMaxPoolingDropout (ultralytics/nn/modules/conv.py)
- ConvAttnPooling (ultralytics/nn/modules/conv.py)
- Integrasi Attention Mechanism (CBAM)
- ConvStrideAttn_Pooling (ultralytics/nn/modules/conv.py)
Dokumentasi
Contoh Penggunaan
Python
- Lokasi Model Yang Telah Dimodifikasi:
- ultralytics/cfg/models/v8/
- Nama Model Modifikasi (Best Model):
- yolov8nMaxPoolingDropout.yaml (YOLOv8n + Max Pooling Dropout(need adjust dropout probability))(ultralytics/cfg/models/v8/yolov8nMaxPoolingDropout.yaml)
- yolov8nGhostModuleAttnPooling.yaml (YOLOv8n + Ghost Module + Attention Max Pooling)(ultralytics/cfg/models/v8/yolov8nGhostModuleAttnPooling.yaml)
bash
pip install ultralytics
bash
git clone https://github.com/MInsanKamil/YOLOv8_MSG.git
bash
cd YOLOv8_MSG
```python from ultralytics.models.yolo.model import YOLO
Load a model
model = YOLO("ultralytics/cfg/models/v8/namamodel.yaml") # build a new model from scratch model = YOLO("ultralytics/cfg/models/v8/namamodel.yaml").load("yolov8n.pt") # load weight pretrained yolov8n coco dataset
Load a model pretrained yolov8_msg indoor dataset
model = YOLO('best.pt')
Use the model
model.train(data="coco8.yaml", epochs=3) # train the model metrics = model.val() # evaluate model performance on the validation set results = model("https://ultralytics.com/images/bus.jpg") # predict on an image path = model.export(format="onnx") # export the model to ONNX format ```
Models
Dibawah ini hasi evaluasi model untuk mendeteksi objek dalam rumah (Indoor Object Dataset)
| Model | size
(pixels) | Dropout Probability | Kernel Size
(Depthwise Convolution) | mAPval
50 | mAPtest
50 | GFLOPs
(B) | Notebook |
| ------------------------------------------------------------------------------------ | --------------------- | --------------------- | --------------------- | -------------------- | -------------------- | ----------------- | ----------------- |
| YOLOv8n (Baseline) | 640 | - |- | 73.1 | 71.1 | 8.09 | Google Colab |
| YOLOv8n + Attention Stride Pooling | 640 | - |- | 73.4 | 73.2 | 8.16 | Google Colab |
| YOLOv8n + Ghost Module | 640 | - | 7 | 72.5 | 72.9 | 6.75 | Google Colab |
| YOLOv8n + Ghost Module | 640 | - | 5 | 72.8 | 73.1 | 6.70 | Google Colab |
| YOLOv8n + Ghost Module | 640 | - | 3 | 73 | 73.1 | 6.67 | Google Colab |
| YOLOv8n + Ghost Module Modification | 640 | - | 3 | 72.5 | 71.7 | 5.87 | Google Colab |
| YOLOv8n + Attention Max Pooling | 640 | - | - | 74.4 | 72.1 | 2.13 | Google Colab |
| YOLOv8n + Average Pooling | 640 | - | - | 74.8 | 72.5 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling | 640 | - | - | 74.3 | 71.9 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.01 | - | 74.7 | 72.8 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.02 | - | 73.2 | 72.3 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.03 | - | 73.6 | 71.1 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.04 | - | 73.6 | 73.3 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.05 | - | 73.8 | 72.2 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.06 | - | 73.4 | 73.8 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.07 | - | 73.8 | 72.4 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.08 | - | 73.9 | 71.6 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.09 | - | 73 | 72.4 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.1 | - | 73.4 | 70.9 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.2 | - | 73.5 | 71.5 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.3 | - | 72.4 | 71.7 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.4 | - | 72.8 | 69.7 | 2.10 | Google Colab |
| YOLOv8n + Max Pooling Dropout | 640 | 0.5 | - | 69.4 | 66.9 | 2.10 | Google Colab |
| YOLOv8n + Ghost Module + Average Pooling | 640 | - | 3 | 71.7 | 73.4 | 1.75 | Google Colab |
| YOLOv8n + Ghost Module + Max Pooling Dropout| 640 | 0.06 | 3 | 72.8 | 71.4 | 1.75 | Google Colab |
| YOLOv8n + Ghost Module + Max Pooling | 640 | - | 3 | 73.6 | 71.9 | 1.75 | Google Colab |
| YOLOv8n + Ghost Module + Attention Max Pooling | 640 | - | 3 | 73.3 | 73.2 | 1.77 | Google Colab |
| YOLOv8n + Ghost Module + Attention Max Pooling + Attention Stride Pooling| 640 | - | 3 | 74.1 | 73.4 | 1.79 | Google Colab |
Owner
- Login: MInsanKamil
- Kind: user
- Repositories: 1
- Profile: https://github.com/MInsanKamil
Citation (CITATION.cff)
# This CITATION.cff file was generated with https://bit.ly/cffinit
cff-version: 1.2.0
title: Ultralytics YOLO
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Glenn
family-names: Jocher
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0001-5950-6979'
- given-names: Ayush
family-names: Chaurasia
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0002-7603-6750'
- family-names: Qiu
given-names: Jing
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0003-3783-7069'
repository-code: 'https://github.com/ultralytics/ultralytics'
url: 'https://ultralytics.com'
license: AGPL-3.0
version: 8.0.0
date-released: '2023-01-10'
GitHub Events
Total
- Push event: 56
Last Year
- Push event: 56
Dependencies
- actions/checkout v4 composite
- actions/setup-python v5 composite
- codecov/codecov-action v4 composite
- conda-incubator/setup-miniconda v3 composite
- slackapi/slack-github-action v1.26.0 composite
- contributor-assistant/github-action v2.4.0 composite
- actions/checkout v4 composite
- github/codeql-action/analyze v3 composite
- github/codeql-action/init v3 composite
- actions/checkout v4 composite
- docker/login-action v3 composite
- docker/setup-buildx-action v3 composite
- docker/setup-qemu-action v3 composite
- nick-invision/retry v3 composite
- slackapi/slack-github-action v1.26.0 composite
- ultralytics/actions main composite
- actions/first-interaction v1 composite
- actions/checkout v4 composite
- nick-invision/retry v3 composite
- actions/checkout v4 composite
- actions/setup-python v5 composite
- actions/checkout v4 composite
- actions/setup-python v5 composite
- slackapi/slack-github-action v1.26.0 composite
- actions/stale v9 composite
- pytorch/pytorch 2.3.1-cuda12.1-cudnn8-runtime build
- transformers *
- ultralytics *
- matplotlib >=3.3.0
- numpy >=1.23.0,<2.0.0
- 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
- torch >=1.8.0
- torchvision >=0.9.0
- tqdm >=4.64.0
- ultralytics-thop >=2.0.0