Upload README.md with huggingface_hub

README.md

@@ -1,59 +1,46 @@
 ---
 license: gpl-2.0
-tags:
-- Radio Astronomy
-- Mask-RCNN
-- Pulsar
-- RRAT
-- FRB
-- Signal Processing
 library_name: pytorch
-pipeline_tag: image-segmentation
-datasets:
-- CRAFTS-FRT
-metrics:
-- recall
-- FPR
+tags:
+  - pytorch
+  - mask-rcnn
+  - astronomy
+  - object-detection
+  - frb
+  - pulsar
+pipeline_tag: object-detection
 ---
 
 # FRTSearch: Fast Radio Transient Search
 
-[![Paper](https://img.shields.io/badge/Paper-AASTeX-blue.svg)](https://doi.org/10.57760/sciencedb.Fastro.00038) [![Dataset](https://img.shields.io/badge/Dataset-CRAFTS--FRT-yellow.svg)](https://doi.org/10.57760/sciencedb.Fastro.00038) [![GitHub](https://img.shields.io/badge/GitHub-FRTSearch-black.svg)](https://github.com/BinZhang109/FRTSearch)
-
-**FRTSearch** is an end-to-end deep learning framework for detecting and characterizing Fast Radio Transients (FRTs), including: **Pulsars**, **Rotating Radio Transients (RRATs)** and **Fast Radio Bursts (FRBs)**.
+**FRTSearch** is a deep learning model for detecting **Pulsars**, **RRATs**, and **Fast Radio Bursts (FRBs)** in radio astronomical observation data.
 
-## Model Info
+## Model Details
 
-| Item | Value |
-|------|-------|
-| Backbone | HRNet-W32 |
-| Input | 256 × 8192 (freq × time) |
-| Size | 381.75 MB |
-| Formats | `.fits` (PSRFITS), `.fil` (Filterbank) |
-| Bit Depth | 1/2/4/8/32-bit |
+- **Architecture**: Mask R-CNN with HRNet backbone
+- **Framework**: PyTorch
+- **Task**: Instance Segmentation / Object Detection
+- **License**: GPL-2.0
 
-## Quick Start
+## Usage
 
 ```python
-from huggingface_hub import hf_hub_download
+import torch
+from mmdet.apis import init_detector
 
-model_path = hf_hub_download(
-    repo_id="waterfall109/FRTSearch",
-    filename="models/hrnet_epoch_36.pth"
-)
+# Load model
+config_file = 'configs/detector_FAST.py'
+checkpoint_file = 'models/hrnet_epoch_36.pth'
+model = init_detector(config_file, checkpoint_file, device='cuda:0')
 ```
 
-Or download directly from [Files and versions](https://huggingface.co/waterfall109/FRTSearch/tree/main).
-
-
-## Test Samples
-
-This repository includes 5 test samples from 2 different telescopes to demonstrate cross-facility performance:
+## Files
 
-| Telescope | FRB | DM (pc cm⁻³) |
-|-----------|-----|--------------|
-| FAST | 20121102, 20180301, 20201124 | 565, 420, 525 |
-| ASKAP | 20180119, 20180212 | 400, 168|
+| File | Description |
+|------|-------------|
+| `models/hrnet_epoch_36.pth` | Model weights (Mask R-CNN with HRNet backbone) |
+| `configs/detector_FAST.py` | Configuration for FAST telescope data |
+| `configs/detector_SKA.py` | Configuration for SKA telescope data |
 
 ## Citation
 
@@ -61,25 +48,16 @@ This repository includes 5 test samples from 2 different telescopes to demonstra
 @article{zhang2026frtsearch,
   title={FRTSearch: Unified Detection and Parameter Inference of Fast Radio Transients using Instance Segmentation},
   author={Zhang, Bin and Wang, Yabiao and Xie, Xiaoyao et al.},
-  year={2026}
+  year={2026},
 }
 ```
 
-### Test Sample References
+## Links
 
-When using the test samples, please also cite the original observations:
+- **GitHub**: https://github.com/BinZhang109/FRTSearch
+- **Paper**: https://doi.org/10.57760/sciencedb.Fastro.00038
+- **Dataset**: [CRAFTS-FRT](https://doi.org/10.57760/sciencedb.Fastro.00038)
 
-- **FAST samples**: [Guo et al. (2025)](https://doi.org/10.3847/1538-4365/adf42d)
-- **SKA samples**: [Shannon et al. (2018)](https://doi.org/10.1038/s41586-018-0588-y)
-
-## License & Acknowledgments
-
-GPL-2.0 | Based on [MMDetection](https://github.com/open-mmlab/mmdetection) & [PRESTO](https://github.com/scottransom/presto)
-
----
-<div align="center">
-  <sub>🌌 Questions? <a href="https://github.com/BinZhang109/FRTSearch/issues">GitHub Issues</a></sub>
-</div>
-```
+## License
 
----
+This model is licensed under GPL-2.0. See [LICENSE](LICENSE) for details.