Skip to content

YOLOv10 Error with TensorRT 10.13 #4820

Description

@BobHo5474

With TensorRT 10.3(R36.4.3), the inference results of both FP32 and FP16 are close to ONNX Runtime. However, after using TensorRT 10.13(R38.4.0), only FP32 inference remains consistent with ONNX Runtime, while FP16 shows significant discrepancies.

Reproduction steps:
python3 export_onnx.py
python3 run.py

export_onnx.py generates yolov10n.onnx, which can be used for the following tests.
run.py generates three output images: ort_result.png, trt_result.png, and trt_fp32_result.png.

Note: export_onnx.py was tested with Ultralytics 8.4.98 and PyTorch 2.8.0+cu126.
file.zip

Metadata

Metadata

Assignees

No one assigned

    Labels

    Module:AccuracyOutput mismatch between TensorRT and other frameworks

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions