jordandelbar/rf-detr-s-int8

RF-DETR Small INT8

Pre-exported ONNX model and TensorRT INT8 calibration cache for RF-DETR Small.

Files

• inference_model.onnx — FP32 ONNX model (512×512)
• calibration.cache — TensorRT INT8 calibration cache

Usage

from huggingface_hub import hf_hub_download

onnx = hf_hub_download("org/rfdetr-small-int8", "inference_model.onnx")
cache = hf_hub_download("org/rfdetr-small-int8", "calibration.cache")