Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/programmer-rd-ai/detectx
A Pythonic approach to object detection using Detectron2, a clean, modular framework for training and deploying computer vision models. DetectX simplifies the complexity of object detection while maintaining high performance and extensibility.
https://github.com/programmer-rd-ai/detectx
coco-dataset computer-vision computer-vision-library cuda deep-learning detectron2 faster-rcnn gpu-accelerated machine-learning ml-framework object-detection object-recognition python3 pytorch retinanet
Last synced: about 1 month ago
JSON representation
A Pythonic approach to object detection using Detectron2, a clean, modular framework for training and deploying computer vision models. DetectX simplifies the complexity of object detection while maintaining high performance and extensibility.
- Host: GitHub
- URL: https://github.com/programmer-rd-ai/detectx
- Owner: Programmer-RD-AI
- License: apache-2.0
- Created: 2021-10-10T13:32:21.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2025-01-12T11:01:21.000Z (about 1 month ago)
- Last Synced: 2025-01-12T11:31:36.232Z (about 1 month ago)
- Topics: coco-dataset, computer-vision, computer-vision-library, cuda, deep-learning, detectron2, faster-rcnn, gpu-accelerated, machine-learning, ml-framework, object-detection, object-recognition, python3, pytorch, retinanet
- Language: Python
- Homepage: https://wandb.ai/ranuga-d/Find-Card
- Size: 151 MB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Security: SECURITY.md
Awesome Lists containing this project
README
# DetectX: Simple Yet Powerful Object Detection Framework
A lightweight and modular object detection framework powered by Detectron2, focusing on easy training and deployment.
## Core Features
- 🎯 Pre-configured Detectron2 models (Faster R-CNN, RetinaNet)
- 🔄 Simple data pipeline for custom datasets
- 📊 Built-in evaluation metrics (COCO metrics, RMSE, MSE, PSNR)
- 🚀 Easy model configuration and training
## Quick Start
```bash
# Install dependencies
pip install -r requirements.txt
# Train a model
from Model.modelling.detectron2 import Detectron2
model = Detectron2(
model="COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml",
max_iter=500,
base_lr=0.00025
)
model.train()
```
## Project Structure
```
ML/
├── Model/
│ ├── modelling/ # Core model implementations
│ ├── dataset/ # Dataset handling utilities
│ └── metrics/ # Evaluation metrics
└── tests/ # Unit tests
```
## Currently Supported
- Models: Faster R-CNN, RetinaNet
- Metrics: COCO AP, RMSE, MSE, PSNR
- Data formats: COCO-style annotations
- GPU acceleration with CUDA
## License
Apache License 2.0