HFNet.onnx命令行转化为engine失败

[t676290894]

您好，我通过trtexec --onnx=HF-Net.onnx --saveEngine=best.engine --fp16命令，想将您的HFNet.onnx转化为engine文件，但是失败了，卡在 [07/25/2024-19:55:53] [I] [TRT] ---------------------------------------------------------------- [07/25/2024-19:55:53] [W] [TRT] onnx2trt_utils.cpp:377: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32. [07/25/2024-19:55:53] [I] Finish parsing network model [07/25/2024-19:55:53] [W] Dynamic dimensions required for input: image:0, but no shapes were provided. Automatically overriding shape to: 1x1x1x1 [07/25/2024-19:55:54] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1012, GPU +10, now: CPU 1889, GPU 431 (MiB) [07/25/2024-19:55:54] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 1890, GPU 441 (MiB) [07/25/2024-19:55:54] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored. 不动了 我想问一下HFNet.cache的作用是什么？？？？为什么您的代码中直接使用HFNet.cache与HFNet.onnx可行，而我使用trtexec命令行转化却无法实现