Open Heijuner opened 5 days ago
请问解决了吗?我也是这个问题
他这好像是一个警告,我没有管他,一直等它就能生成trt了
---Original--- From: @.> Date: Sat, Jul 6, 2024 17:07 PM To: @.>; Cc: @.**@.>; Subject: Re: [FeiYull/TensorRT-Alpha] [07/04/2024-04:11:39] [I] [TRT] Localtiming cache in use. Profiling results in this builder pass will not bestored. (Issue #135)
请问解决了吗?我也是这个问题
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
感谢,我这会儿也成功转成trt了
你好,在使用yolov8中,我在将best.onnx通过/usr/src/tensorrt/bin/trtexec --onnx=best_640.onnx --saveEngine=best_640.trt --buildOnly --minShapes=images:1x3x640x640 --optShapes=images:2x3x640x640 --maxShapes=images:4x3x640x640 加速推理时,遇到了两条警告: [07/04/2024-04:11:13] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32. [07/04/2024-04:11:39] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored. 请问这该如何解决呢