How to properly inference YOLOv6-L6 onnx?

[HeChengHui]

Before Asking

• I have read the README carefully. 我已经仔细阅读了README上的操作指引。

• I want to train my custom dataset, and I have read the tutorials for training your custom data carefully and organize my dataset correctly; (FYI: We recommand you to apply the config files of xx_finetune.py.) 我想训练自定义数据集，我已经仔细阅读了训练自定义数据的教程，以及按照正确的目录结构存放数据集。（FYI: 我们推荐使用xx_finetune.py等配置文件训练自定义数据集。）

• I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码，重新运行之后，问题仍不能解决。

Search before asking

• I have searched the YOLOv6 issues and found no similar questions.

Question

I am trying to inference YOLOv6-L6 on onnxruntime

torch 2.1.0+cu118 pypi_0 pypi
torchvision 0.16.0+cu118 pypi_0 pypi
onnx 1.15.0 pypi_0 pypi
onnx-simplifier 0.4.35 pypi_0 pypi
onnxruntime-gpu 1.17.0 pypi_0 pypi
onnxscript 0.1.0.dev20240207 pypi_0 pypi

1. when i tried to run python deploy/ONNX/OpenCV/yolo_video.py --model "yolov6l6.onnx", the speed is super slow.
2. tried follow the tutorial here but when i export using

python deploy/ONNX/export_onnx.py \
    --weights weights/yolov6.pt \
    --end2end --simplify \
    --topk-all 100 \
    --iou-thres 0.65 \
    --conf-thres 0.35 \
    --img-size 640 640 \
    --dynamic-batch \
    --ort \

i get the error: onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from YOLO/YOLOv6/yolov6l6.onnx failed:Type Error: Type parameter (T) of Optype (Where) bound to different types (tensor(int64) and tensor(float) in node (/end2end/Where_1).

It works when i remove --end2end but the output becomes outname=['outputs'] instead of ['num_dets', 'det_boxes', 'det_scores', 'det_classes']

Additional

No response

[laishenghui]

#1013 (comment)
我之前也遇到这个问题，你可以看看这个

[HeChengHui]

@laishenghui
我确实尝试过不用 --end2end，但output名称与 jupyter notebook 中所述的不同。这是有意的行为吗？

[laishenghui]

名称不同没关系的，只需要获取到信息，然后计算出区域就可以

[bilibili12433014]

@HeChengHui 我找到了问题并在我的设备上成功运行了，希望能够帮助到你：#1028 (comment)