pzoltowski's picture
Add model card for rfdetr-nano-fp16-coreml
380e0dd verified
|
Raw
History Blame Contribute Delete
1.01 kB
---
license: apache-2.0
tags:
- coreml
- object-detection
- real-time
- rfdetr
- computer-vision
---
# Rfdetr Nano Fp16 Coreml
RF-DETR Nano model exported to CoreML format (FP16) for Apple devices. Fastest inference with 384×384 resolution.
## Model Details
- **Model Type**: Object Detection
- **Framework**: CoreML
- **Precision**: FP16
- **Input Resolution**: 384×384
- **Performance**: ~56 FPS on iPhone 13 Mini
- **Inference Time**: 17.96 ms
## Usage
This model can be used for real-time object detection on Apple devices (iOS, macOS, watchOS, tvOS).
## Custom conversion to CoreML
Check the repo https://github.com/pzoltowski/rf-detr-coreml
## Performance
| Model | Resolution | Inference Time (ms) | FPS |
|-------|------------|---------------------|-----|
| RF-DETR-Nano | 384×384 | 17.96 | ~56 |
| RF-DETR-Small | 512×512 | 27.07 | ~37 |
| RF-DETR-Medium | 576×576 | 41.85 | ~24 |
*Performance measured on iPhone 13 Mini using Xcode performance tools with FP16 precision.*
```