(YOLO) D:\Create\YOLOv8-TensorRT-main>python export-det.py --weights v8.pt --iou-thres 0.60 --conf-thres 0.1 --topk 100 --opset 18 --sim --input-shape 1 3 320 320 --device cuda:0
YOLOv8-SOEP summary (fused): 194 layers, 3307670 parameters, 0 gradients, 11.8 GFLOPs
Traceback (most recent call last):
File "D:\Create\YOLOv8-TensorRT-main\export-det.py", line 97, in
main(parse_args())
File "D:\Create\YOLOv8-TensorRT-main\export-det.py", line 72, in main
torch.onnx.export(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 516, in export
_export(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 1612, in _export
graph, params_dict, torch_out = _model_to_graph(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 1138, in _model_to_graph
graph = _optimize_graph(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 677, in _optimize_graph
graph = _C._jit_pass_onnx(graph, operator_export_type)
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 1966, in _run_symbolic_function
raise errors.UnsupportedOperatorError(
torch.onnx.errors.UnsupportedOperatorError: Exporting the operator 'aten::fft_fft2' to ONNX opset version 18 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub: https://github.com/pytorch/pytorch/issues.
怎么解决这个问题
(YOLO) D:\Create\YOLOv8-TensorRT-main>python export-det.py --weights v8.pt --iou-thres 0.60 --conf-thres 0.1 --topk 100 --opset 18 --sim --input-shape 1 3 320 320 --device cuda:0
YOLOv8-SOEP summary (fused): 194 layers, 3307670 parameters, 0 gradients, 11.8 GFLOPs
Traceback (most recent call last):
File "D:\Create\YOLOv8-TensorRT-main\export-det.py", line 97, in
main(parse_args())
File "D:\Create\YOLOv8-TensorRT-main\export-det.py", line 72, in main
torch.onnx.export(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 516, in export
_export(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 1612, in _export
graph, params_dict, torch_out = _model_to_graph(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 1138, in _model_to_graph
graph = _optimize_graph(
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 677, in _optimize_graph
graph = _C._jit_pass_onnx(graph, operator_export_type)
File "E:\anaconda3\envs\YOLO\lib\site-packages\torch\onnx\utils.py", line 1966, in _run_symbolic_function
raise errors.UnsupportedOperatorError(
torch.onnx.errors.UnsupportedOperatorError: Exporting the operator 'aten::fft_fft2' to ONNX opset version 18 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub: https://github.com/pytorch/pytorch/issues.
怎么解决这个问题