Ernie 1.0模型 inference cpu切换gpu 报错

[<b>源自github用户bluestinger</b>](https://github.com/PaddlePaddle/Paddle/issues/32189):

环境是paddle 提供的docker的环境
hub.baidubce.com/paddlepaddle/paddle:1.8.0-gpu-cuda10.0-cudnn7-trt6
官方的Paddle-Inference-Demo可以正常使用

我自己训练的模型 Ernie 1.0 的pretrain模型，cpu下能正确输出结果。切换gpu后，报错如下

grep: warning: GREP_OPTIONS is deprecated; please use an alias or script
E0411 03:34:51.655264    84 analysis_config.cc:180] Please compile with MKLDNN first to use MKLDNN
I0411 03:34:52.433706    84 analysis_predictor.cc:138] Profiler is deactivated, and no profiling report will be generated.
I0411 03:34:52.446473    84 analysis_predictor.cc:872] MODEL VERSION: 1.8.3
I0411 03:34:52.446512    84 analysis_predictor.cc:874] PREDICTOR VERSION: 1.8.0
I0411 03:34:52.446916    84 analysis_predictor.cc:432] TensorRT subgraph engine is enabled
--- Running analysis [ir_graph_build_pass]
--- Running analysis [ir_graph_clean_pass]
--- Running analysis [ir_analysis_pass]
--- Running IR pass [conv_affine_channel_fuse_pass]
--- Running IR pass [conv_eltwiseadd_affine_channel_fuse_pass]
--- Running IR pass [shuffle_channel_detect_pass]
--- Running IR pass [quant_conv2d_dequant_fuse_pass]
--- Running IR pass [delete_quant_dequant_op_pass]
--- Running IR pass [simplify_with_basic_ops_pass]
--- Running IR pass [embedding_eltwise_layernorm_fuse_pass]
I0411 03:34:52.755502    84 graph_pattern_detector.cc:101] ---  detected 1 subgraphs
I0411 03:34:52.756510    84 graph_pattern_detector.cc:101] ---  detected 1 subgraphs
I0411 03:34:52.761987    84 graph_pattern_detector.cc:101] ---  detected 25 subgraphs
--- Running IR pass [multihead_matmul_fuse_pass_v2]
I0411 03:34:54.146399    84 graph_pattern_detector.cc:101] ---  detected 12 subgraphs
--- Running IR pass [skip_layernorm_fuse_pass]
I0411 03:34:54.173033    84 graph_pattern_detector.cc:101] ---  detected 24 subgraphs
--- Running IR pass [conv_bn_fuse_pass]
--- Running IR pass [fc_fuse_pass]
I0411 03:34:54.181416    84 graph_pattern_detector.cc:101] ---  detected 12 subgraphs
I0411 03:34:54.185427    84 graph_pattern_detector.cc:101] ---  detected 25 subgraphs
--- Running IR pass [tensorrt_subgraph_pass]
I0411 03:34:54.195298    84 tensorrt_subgraph_pass.cc:115] ---  detect a sub-graph with 77 nodes
W0411 03:34:54.197585    84 tensorrt_subgraph_pass.cc:285] The Paddle lib links the 6015 version TensorRT, make sure the runtime TensorRT you are using is no less than this version, otherwise, there might be Segfault!
I0411 03:34:54.197618    84 tensorrt_subgraph_pass.cc:321] Prepare TRT engine (Optimize model structure, Select OP kernel etc). This process may cost a lot of time.
Traceback (most recent call last):
  File "Demo_pre5.py", line 119, in <module>
    pred=create_predictor()
  File "Demo_pre5.py", line 68, in create_predictor
    predictor=create_paddle_predictor(config)
paddle.fluid.core_avx.EnforceNotMet:

--------------------------------------------
C++ Call Stacks (More useful to developers):
--------------------------------------------
0   std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > paddle::platform::GetTraceBackString<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&&, char const*, int)
1   paddle::platform::EnforceNotMet::EnforceNotMet(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, char const*, int)
2   paddle::inference::tensorrt::OpConverter::ConvertBlockToTRTEngine(paddle::framework::BlockDesc*, paddle::framework::Scope const&, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::unordered_set<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::hash<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::equal_to<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, paddle::inference::tensorrt::TensorRTEngine*)
3   paddle::inference::analysis::TensorRtSubgraphPass::CreateTensorRTOp(paddle::framework::ir::Node*, paddle::framework::ir::Graph*, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >*) const
4   paddle::inference::analysis::TensorRtSubgraphPass::ApplyImpl(paddle::framework::ir::Graph*) const
5   paddle::framework::ir::Pass::Apply(paddle::framework::ir::Graph*) const
6   paddle::inference::analysis::IRPassManager::Apply(std::unique_ptr<paddle::framework::ir::Graph, std::default_delete<paddle::framework::ir::Graph> >)
7   paddle::inference::analysis::IrAnalysisPass::RunImpl(paddle::inference::analysis::Argument*)
8   paddle::inference::analysis::Analyzer::RunAnalysis(paddle::inference::analysis::Argument*)
9   paddle::AnalysisPredictor::OptimizeInferenceProgram()
10  paddle::AnalysisPredictor::PrepareProgram(std::shared_ptr<paddle::framework::ProgramDesc> const&)
11  paddle::AnalysisPredictor::Init(std::shared_ptr<paddle::framework::Scope> const&, std::shared_ptr<paddle::framework::ProgramDesc> const&)
12  std::unique_ptr<paddle::PaddlePredictor, std::default_delete<paddle::PaddlePredictor> > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
13  std::unique_ptr<paddle::PaddlePredictor, std::default_delete<paddle::PaddlePredictor> > paddle::CreatePaddlePredictor<paddle::AnalysisConfig>(paddle::AnalysisConfig const&)

----------------------
Error Message Summary:
----------------------
InvalidArgumentError: TensorRT's tensor input requires at least 2 dimensions, but input 1 has 1 dims.
  [Hint: Expected shape.size() > 1UL, but received shape.size():1 <= 1UL:1.] at (/paddle /trt_refine_int8/paddle/fluid/inference/tensorrt/engine.h:67)

GVP PaddlePaddle/Paddle

内容风险标识

评论 (22)

GVPPaddlePaddle/Paddle

内容风险标识