Views
No views yet
inference_model.onnx — FP32 ONNX model (512×512)calibration.cache — TensorRT INT8 calibration cache1from huggingface_hub import hf_hub_download
2
3onnx = hf_hub_download("org/rfdetr-small-int8", "inference_model.onnx")
4cache = hf_hub_download("org/rfdetr-small-int8", "calibration.cache")