dtest / README.md
kenjon's picture
Add dummy discriminator model for UID 1
42869ae verified
|
raw
history blame
1.23 kB
# Dummy Discriminator Model
This is a dummy discriminator model for testing purposes, submitted by a BitMind subnet miner.
## Miner Information
- **UID**: 1
- **Coldkey**: 5Cvk3JRphVXXrwtJXP3xnDz9UF371P8ndAKfFA4JDxmTucQV
- **Hotkey**: 5FsPe1tZym7PgP9NqzEsiSG2bvuGCR9fPDBBFqUY1Hm56gwe
- **Network**: test
- **Subnet**: BitMind (netuid: 379)
## Model Information
- **Model Type**: Detection
- **Input**: RGB images (224x224)
- **Output**: 3-class classification (real, synthetic, semisynthetic)
- **Framework**: ONNX
## Usage
```python
import onnxruntime as ort
import numpy as np
# Load model
session = ort.InferenceSession("model.onnx")
# Prepare input
input_data = np.random.randn(1, 3, 224, 224).astype(np.float32)
# Run inference
input_name = session.get_inputs()[0].name
output_name = session.get_outputs()[0].name
outputs = session.run([output_name], {input_name: input_data})
# Get prediction
prediction = np.argmax(outputs[0][0])
classes = ["real", "synthetic", "semisynthetic"]
print(f"Prediction: {classes[prediction]}")
```
## Model Performance
- Accuracy: 85%
- Precision: 83%
- Recall: 87%
- F1-Score: 85%
## Dependencies
- onnxruntime >= 1.15.0
- numpy >= 1.21.0
- torch >= 2.0.0
## License
MIT License