smoke tensorrt部署编译成功后运行报错，信息如下

[zhu709654396]

terminate called after throwing an instance of 'phi::enforce::EnforceNotMet' what():

---

C++ Traceback (most recent call last):

0 paddle::AnalysisPredictor::ZeroCopyRun() 1 paddle::framework::NaiveExecutor::Run() 2 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, phi::Place const&) 3 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, phi::Place const&) const 4 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, phi::Place const&, paddle::framework::RuntimeContext) const 5 paddle::operators::ConvOp::InferShape(paddle::framework::InferShapeContext) const 6 paddle::operators::ConvOp::ComputeOutputShape(paddle::framework::InferShapeContext) const 7 phi::enforce::EnforceNotMet::EnforceNotMet(phi::ErrorSummary const&, char const, int) 8 phi::enforce::GetCurrentTraceBackStringabi:cxx11

---

Error Message Summary:

InvalidArgumentError: The input of Op(Conv) should be a 4-D or 5-D Tensor. But received: input's dimension is 3, input's shape is [1, 3, 3]. [Hint: Expected in_dims.size() == 4 || in_dims.size() == 5 == true, but received in_dims.size() == 4 || in_dims.size() == 5:0 != true:1.] (at /paddle/paddle/fluid/operators/conv_op.cc:71) [operator < conv2d > error] 已放弃 (核心已转储)

[nepeplwu]

@zhu709654396 麻烦发下推理的命令和Paddle的版本

[zhu709654396]

推理命令:./build/infer --model_file /path/to/smoke.pdmodel --params_file /path/to/smoke.pdiparams --image /path/to/image paddle-gpu：2.4.1.post112

[FunnyWii]

请问解决了吗。。。我也是InvalidArgumentError: The input of Op(Conv) should be a 4-D or 5-D Tensor. But received: input's dimension is 3, input's shape is [1, 3, 3].

[nepeplwu]

@zhu709654396 感谢反馈，该问题已经修复，详见：https://github.com/PaddlePaddle/Paddle3D/commit/9df597e381d796f0245815472dbe644cdcec448a，请拉取最新代码试试