TensorRT-Alpha icon indicating copy to clipboard operation
TensorRT-Alpha copied to clipboard

onnx转换trt报错

Open Yi-hash1 opened this issue 1 year ago • 1 comments

[04/10/2024-16:11:31] [W] [TRT] onnx2trt_utils.cpp:366: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32. [04/10/2024-16:11:32] [I] Finish parsing network model [04/10/2024-16:11:32] [E] Static model does not take explicit shapes since the shape of inference tensors will be determined by the model itself [04/10/2024-16:11:32] [E] Network And Config setup failed [04/10/2024-16:11:32] [E] Building engine failed [04/10/2024-16:11:32] [E] Failed to create engine from model. [04/10/2024-16:11:32] [E] Engine set up failed

Yi-hash1 avatar Apr 10 '24 08:04 Yi-hash1

@Yi-hash1 导出的onnx是静态输入,可参考仓库中导出onnx的指令

FeiYull avatar Apr 10 '24 10:04 FeiYull