Error when converting tensorrt model

[Yhc-777]

(yolov10) u@u:/mnt/2/haochen/yolov10$ yolo export model=/mnt/2/haochen/yolov10/runs/detect/train_v10/weights/best.pt format=engine
half=False simplify opset=13 workspace=16
WARNING ⚠️ TensorRT requires GPU export, automatically assigning device=0
Ultralytics YOLOv8.1.34 🚀 Python-3.9.19 torch-2.0.1+cu117 CUDA:0 (NVIDIA GeForce RTX 4080, 16071MiB)
YOLOv10x summary (fused): 503 layers, 31595636 parameters, 0 gradients, 169.8 GFLOPs

PyTorch: starting from '/mnt/2/haochen/yolov10/runs/detect/train_v10/weights/best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 300, 6) (61.1 MB)

ONNX: starting export with onnx 1.14.0 opset 13...
============= Diagnostic Run torch.onnx.export version 2.0.1+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

ONNX: simplifying with onnxslim 0.1.31...
ONNX: export success ✅ 4.9s, saved as '/mnt/2/haochen/yolov10/runs/detect/train_v10/weights/best.onnx' (112.5 MB)

TensorRT: starting export with TensorRT 8.6.1...
[09/20/2024-10:59:05] [TRT] [I] [MemUsageChange] Init CUDA: CPU +564, GPU +0, now: CPU 3520, GPU 1140 (MiB)
[09/20/2024-10:59:05] [TRT] [I] [MemUsageChange] Init builder kernel library: CPU +433, GPU +104, now: CPU 3972, GPU 1244 (MiB)
[09/20/2024-10:59:05] [TRT] [I] ----------------------------------------------------------------
[09/20/2024-10:59:05] [TRT] [I] Input filename: /mnt/2/haochen/yolov10/runs/detect/train_v10/weights/best.onnx
[09/20/2024-10:59:05] [TRT] [I] ONNX IR version: 0.0.9
[09/20/2024-10:59:05] [TRT] [I] Opset version: 13
[09/20/2024-10:59:05] [TRT] [I] Producer name: pytorch
[09/20/2024-10:59:05] [TRT] [I] Producer version: 2.0.1
[09/20/2024-10:59:05] [TRT] [I] Domain:
[09/20/2024-10:59:05] [TRT] [I] Model version: 0
[09/20/2024-10:59:05] [TRT] [I] Doc string:
[09/20/2024-10:59:05] [TRT] [I] ----------------------------------------------------------------
[09/20/2024-10:59:05] [TRT] [W] onnx2trt_utils.cpp:369: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[09/20/2024-10:59:05] [TRT] [I] No importer registered for op: Mod. Attempting to import as plugin.
[09/20/2024-10:59:05] [TRT] [I] Searching for plugin: Mod, plugin_version: 1, plugin_namespace:
[09/20/2024-10:59:05] [TRT] [E] ModelImporter.cpp:773: While parsing node number 592 [Mod -> "/model.23/Mod_output_0"]:
[09/20/2024-10:59:05] [TRT] [E] ModelImporter.cpp:774: --- Begin node ---
[09/20/2024-10:59:05] [TRT] [E] ModelImporter.cpp:775: input: "/model.23/TopK_1_output_1"
input: "/model.23/Constant_13_output_0"
output: "/model.23/Mod_output_0"
name: "/model.23/Mod"
op_type: "Mod"
attribute {
name: "fmod"
i: 0
type: INT
}

[09/20/2024-10:59:05] [TRT] [E] ModelImporter.cpp:776: --- End node ---
[09/20/2024-10:59:05] [TRT] [E] ModelImporter.cpp:779: ERROR: builtin_op_importers.cpp:4890 In function importFallbackPluginImporter:
[8] Assertion failed: creator && "Plugin not found, are the plugin name, version, and namespace correct?"
TensorRT: export failure ❌ 6.0s: failed to load ONNX file: /mnt/2/haochen/yolov10/runs/detect/train_v10/weights/best.onnx
Traceback (most recent call last):
File "/home/u/miniconda3/envs/yolov10/bin/yolo", line 8, in
sys.exit(entrypoint())
File "/mnt/2/haochen/yolov10/ultralytics/cfg/init.py", line 594, in entrypoint
getattr(model, mode)(**overrides) # default args from model
File "/mnt/2/haochen/yolov10/ultralytics/engine/model.py", line 590, in export
return Exporter(overrides=args, _callbacks=self.callbacks)(model=self.model)
File "/home/u/miniconda3/envs/yolov10/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/mnt/2/haochen/yolov10/ultralytics/engine/exporter.py", line 288, in call
f[1], _ = self.export_engine()
File "/mnt/2/haochen/yolov10/ultralytics/engine/exporter.py", line 138, in outer_func
raise e
File "/mnt/2/haochen/yolov10/ultralytics/engine/exporter.py", line 133, in outer_func
f, model = inner_func(*args, **kwargs)
File "/mnt/2/haochen/yolov10/ultralytics/engine/exporter.py", line 689, in export_engine
raise RuntimeError(f"failed to load ONNX file: {f_onnx}")
RuntimeError: failed to load ONNX file: /mnt/2/haochen/yolov10/runs/detect/train_v10/weights/best.onnx

How can I solve this problem? Thx!!!