Closed LongruiDong closed 4 years ago
This error is TensorRT related. You just have to run the code again until it reaches a size that is suitable for your GPU. (I personally never encountered this error, but I read that other people "fixed" it like this.)
This error is TensorRT related. You just have to run the code again until it reaches a size that is suitable for your GPU. (I personally never encountered this error, but I read that other people "fixed" it like this.)
As you can see in #5 ,I tried adjusting MAX_WORKSPACE_SIZE and MIN_WORKSPACE_SIZE, but still get same error...
and I noticed there is a WARNING before parsing model.onnx :
WARNING: ONNX model has a newer ir_version (0.0.4) than this parser was built against (0.0.3).
I am wondering whether the Version conflict of ir_version led to this error?
This issue seems also caused by TensorRT and GUP versions. I will therefore also close this one, and feel free to ask me reopening it if needed.
Hi, after build project, run the demo:
Does anyone know where the bug is?
Thanks!