macroadster/starlight
By macroadster · ↓ 6 · ♥ 0 · Updated 2025-11-17
What's in this repo
This page lists the files in macroadster/starlight, including model.onnx.
- 1 ONNX models (.onnx files)
- 5 files, including 1 .md, 1 .json, 1 .py, 1 .onnx
- Last updated 2025-11-17
ONNX files
| File | Size | Download |
|---|---|---|
| model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Model Card: Starlight Unified Model 2025
Model Overview
- Task: Detection / Extraction
- Architecture: Unified CNN-based Encoder-Decoder with Residual Blocks
- Input: 256x256 RGB/RGBA or metadata
- Output:
- Detector: sigmoid probability
- Extractor: variable-length byte sequence
Training
- Dataset: Combined submissions (grok, gemini, claude, chatgpt, sample)
- Epochs: 50
- Batch Size: 16
- Optimizer: Adam
- Loss: BCE + MSE (detector), CrossEntropy (extractor)
Performance
| Metric | Value |
|---|---|
| Accuracy | 96.3% |
| AUC-ROC | 0.996 |
| F1 Score | 0.982 |
| Extraction BER | 0.003 |
Steganography Coverage
lsb,alpha,dct,exif,eoi,palette
Inference Speed
- CPU: 12 ms/image
- GPU: 2.1 ms/image
License
- Model: Apache 2.0
- Code: MIT
Model info
image-classification
transformers
transformers
onnx
steganography
image-classification
computer-vision
dataset:custom
license:apache-2.0
endpoints_compatible
region:us
↓ 6
♥ 0
Created: 2025-11-17
Updated: 2025-11-17
View on Hugging FaceFiles (5)
.gitattributes
README.md
config.json
inference.py
model.onnx
ONNX
Related models
More from macroadster
No other models by this author.