PVRCNN C++部署推理报错

[wayyeah]

[libprotobuf ERROR /paddle/build/third_party/protobuf/src/extern_protobuf/src/google/protobuf/message_lite.cc:119] Can't parse message of type "paddle.framework.proto.ProgramDesc" because it is missing required| fields: blocks[0].vars[983].type.type, blocks[0].vars[989].type.type, blocks[0].vars[995].type.type, blocks[0].vars[1001].type.type, blocks[0].vars[1007].type.type, blocks[0].vars[1013].type.type, blocks[0].va| rs[1019].type.type, blocks[0].vars[1025].type.type, blocks[0].vars[1031].type.type, blocks[0].vars[1037].type.type, blocks[0].vars[1043].type.type, blocks[0].vars[1049].type.type, blocks[0].vars[1052].type.type| , blocks[0].vars[1055].type.type, blocks[0].vars[1058].type.type, blocks[0].vars[1061].type.type, blocks[0].vars[1064].type.type, blocks[0].vars[1067].type.type, blocks[0].vars[1070].type.type, blocks[0].vars[1| 073].type.type, blocks[0].vars[1076].type.type, blocks[0].vars[1079].type.type, blocks[0].vars[1082].type.type, blocks[0].vars[1085].type.type, blocks[0].vars[1086].type.type, blocks[0].vars[1087].type.type, bl| ocks[0].vars[1088].type.type, blocks[0].vars[1089].type.type, blocks[0].vars[1090].type.type, blocks[0].vars[1091].type.type, blocks[0].vars[1092].type.type, blocks[0].vars[1093].type.type, blocks[0].vars[1094]| .type.type, blocks[0].vars[1095].type.type, blocks[0].vars[1096].type.type, blocks[0].vars[1097].type.type, blocks[0].vars[1098].type.type | --- Running analysis [ir_graph_build_pass] | [libprotobuf ERROR /paddle/build/third_party/protobuf/src/extern_protobuf/src/google/protobuf/message_lite.cc:119] Can't parse message of type "paddle.framework.proto.ProgramDesc" because it is missing required| fields: blocks[0].vars[983].type.type, blocks[0].vars[989].type.type, blocks[0].vars[995].type.type, blocks[0].vars[1001].type.type, blocks[0].vars[1007].type.type, blocks[0].vars[1013].type.type, blocks[0].va| rs[1019].type.type, blocks[0].vars[1025].type.type, blocks[0].vars[1031].type.type, blocks[0].vars[1037].type.type, blocks[0].vars[1043].type.type, blocks[0].vars[1049].type.type, blocks[0].vars[1052].type.type| , blocks[0].vars[1055].type.type, blocks[0].vars[1058].type.type, blocks[0].vars[1061].type.type, blocks[0].vars[1064].type.type, blocks[0].vars[1067].type.type, blocks[0].vars[1070].type.type, blocks[0].vars[1| 073].type.type, blocks[0].vars[1076].type.type, blocks[0].vars[1079].type.type, blocks[0].vars[1082].type.type, blocks[0].vars[1085].type.type, blocks[0].vars[1086].type.type, blocks[0].vars[1087].type.type, bl| ocks[0].vars[1088].type.type, blocks[0].vars[1089].type.type, blocks[0].vars[1090].type.type, blocks[0].vars[1091].type.type, blocks[0].vars[1092].type.type, blocks[0].vars[1093].type.type, blocks[0].vars[1094]| .type.type, blocks[0].vars[1095].type.type, blocks[0].vars[1096].type.type, blocks[0].vars[1097].type.type, blocks[0].vars[1098].type.type | Aborted (core dumped)

指令：

./build/main --model_file /home/yw/Paddle3D/output/pv_rcnn.pdmodel  --params_file /home/yw/Paddle3D/output/pv_rcnn.pdiparams |
 --lidar_file /mnt/8tssd/kitti/detection/training/velodyne/000002.bin  --num_point_dim 4 --point_cloud_range "0 -40 -3 70.4 40 1

环境：paddlepaddle-gpu=2.4.1.post112 cuda=11.2 python3.8 cudnn=8.2.0

[wayyeah]

`[libprotobuf ERROR /paddle/build/third_party/protobuf/src/extern_protobuf/src/google/protobuf/message_lite.cc:119] Can't parse message of type "paddle.framework.proto.ProgramDesc" because it is missing required fields: blocks[0].vars[983].type.type, blocks[0].vars[989].type.type, blocks[0].vars[995].type.type, blocks[0].vars[1001].type.type, blocks[0].vars[1007].type.type, blocks[0].vars[1013].type.type, blocks[0].vars[1019].type.type, blocks[0].vars[1025].type.type, blocks[0].vars[1031].type.type, blocks[0].vars[1037].type.type, blocks[0].vars[1043].type.type, blocks[0].vars[1049].type.type, blocks[0].vars[1052].type.type, blocks[0].vars[1055].type.type, blocks[0].vars[1058].type.type, blocks[0].vars[1061].type.type, blocks[0].vars[1064].type.type, blocks[0].vars[1067].type.type, blocks[0].vars[1070].type.type, blocks[0].vars[1073].type.type, blocks[0].vars[1076].type.type, blocks[0].vars[1079].type.type, blocks[0].vars[1082].type.type, blocks[0].vars[1085].type.type, blocks[0].vars[1086].type.type, blocks[0].vars[1087].type.type, blocks[0].vars[1088].type.type, blocks[0].vars[1089].type.type, blocks[0].vars[1090].type.type, blocks[0].vars[1091].type.type, blocks[0].vars[1092].type.type, blocks[0].vars[1093].type.type, blocks[0].vars[1094].type.type, blocks[0].vars[1095].type.type, blocks[0].vars[1096].type.type, blocks[0].vars[1097].type.type, blocks[0].vars[1098].type.type
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0330 16:10:00.430377 7046 analysis_predictor.cc:881] TensorRT subgraph engine is enabled
--- Running analysis [ir_graph_build_pass]
[libprotobuf ERROR /paddle/build/third_party/protobuf/src/extern_protobuf/src/google/protobuf/message_lite.cc:119] Can't parse message of type "paddle.framework.proto.ProgramDesc" because it is missing required fields: blocks[0].vars[983].type.type, blocks[0].vars[989].type.type, blocks[0].vars[995].type.type, blocks[0].vars[1001].type.type, blocks[0].vars[1007].type.type, blocks[0].vars[1013].type.type, blocks[0].vars[1019].type.type, blocks[0].vars[1025].type.type, blocks[0].vars[1031].type.type, blocks[0].vars[1037].type.type, blocks[0].vars[1043].type.type, blocks[0].vars[1049].type.type, blocks[0].vars[1052].type.type, blocks[0].vars[1055].type.type, blocks[0].vars[1058].type.type, blocks[0].vars[1061].type.type, blocks[0].vars[1064].type.type, blocks[0].vars[1067].type.type, blocks[0].vars[1070].type.type, blocks[0].vars[1073].type.type, blocks[0].vars[1076].type.type, blocks[0].vars[1079].type.type, blocks[0].vars[1082].type.type, blocks[0].vars[1085].type.type, blocks[0].vars[1086].type.type, blocks[0].vars[1087].type.type, blocks[0].vars[1088].type.type, blocks[0].vars[1089].type.type, blocks[0].vars[1090].type.type, blocks[0].vars[1091].type.type, blocks[0].vars[1092].type.type, blocks[0].vars[1093].type.type, blocks[0].vars[1094].type.type, blocks[0].vars[1095].type.type, blocks[0].vars[1096].type.type, blocks[0].vars[1097].type.type, blocks[0].vars[1098].type.type
terminate called after throwing an instance of 'phi::enforce::EnforceNotMet'
what():

---

C++ Traceback (most recent call last):

0 paddle_infer::CreatePredictor(paddle::AnalysisConfig const&)
1 paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&)
2 std::unique_ptr<paddle::PaddlePredictor, std::default_deletepaddle::PaddlePredictor > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
3 paddle::AnalysisPredictor::Init(std::shared_ptrpaddle::framework::Scope const&, std::shared_ptrpaddle::framework::ProgramDesc const&)
4 paddle::AnalysisPredictor::PrepareProgram(std::shared_ptrpaddle::framework::ProgramDesc const&)
5 paddle::AnalysisPredictor::OptimizeInferenceProgram()
6 paddle::inference::analysis::Analyzer::RunAnalysis(paddle::inference::analysis::Argument*)
7 paddle::inference::analysis::IrGraphBuildPass::RunImpl(paddle::inference::analysis::Argument*)
8 paddle::inference::analysis::IrGraphBuildPass::LoadModel(std::string const&, std::string const&, paddle::framework::Scope*, phi::Place const&, bool)
9 paddle::inference::Load(paddle::framework::Executor*, paddle::framework::Scope*, std::string const&, std::string const&)
10 paddle::framework::ProgramDesc::ProgramDesc(std::string const&)
11 phi::enforce::EnforceNotMet::EnforceNotMet(phi::ErrorSummary const&, char const*, int)
12 phi::enforce::GetCurrentTraceBackStringabi:cxx11

---

Error Message Summary:

InvalidArgumentError: Failed to parse program_desc from binary string.
[Hint: Expected desc_.ParseFromString(binary_str) == true, but received desc_.ParseFromString(binary_str):0 != true:1.] (at /paddle/paddle/fluid/framework/program_desc.cc:103)

已放弃 (核心已转储)`
AI studio线上环境同样报错

[wayyeah]

python部署推理同样报错

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
2023-03-30 20:05:01,389 -  WARNING - No custom op iou3d_nms_cuda found, try JIT build
Compiling user custom op, it will cost a few seconds.....
2023-03-30 20:05:03,922 -     INFO - iou3d_nms_cuda builded success!
2023-03-30 20:05:04,323 -  WARNING - No custom op voxelize found, try JIT build
Compiling user custom op, it will cost a few seconds.....
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
W0330 20:05:14.809769  8689 custom_operator.cc:723] Operator (boxes_iou_bev_gpu) has been registered.
W0330 20:05:14.809840  8689 custom_operator.cc:723] Operator (boxes_iou_bev_cpu) has been registered.
W0330 20:05:14.809862  8689 custom_operator.cc:723] Operator (boxes_overlap_bev_gpu) has been registered.
W0330 20:05:14.809873  8689 custom_operator.cc:723] Operator (nms_gpu) has been registered.
W0330 20:05:14.810021  8689 custom_operator.cc:723] Operator (nms_normal_gpu) has been registered.
2023-03-30 20:05:14,832 -     INFO - voxelize builded success!
2023-03-30 20:05:14,833 -  WARNING - No custom op pointnet2_ops found, try JIT build
Compiling user custom op, it will cost a few seconds.....
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
W0330 20:06:07.779171  8689 custom_operator.cc:723] Operator (nms_gpu) has been registered.
W0330 20:06:07.779286  8689 custom_operator.cc:723] Operator (boxes_overlap_bev_gpu) has been registered.
W0330 20:06:07.779403  8689 custom_operator.cc:723] Operator (boxes_iou_bev_cpu) has been registered.
W0330 20:06:07.779443  8689 custom_operator.cc:723] Operator (nms_normal_gpu) has been registered.
W0330 20:06:07.779453  8689 custom_operator.cc:723] Operator (hard_voxelize) has been registered.
W0330 20:06:07.779464  8689 custom_operator.cc:723] Operator (boxes_iou_bev_gpu) has been registered.
2023-03-30 20:06:07,800 -     INFO - pointnet2_ops builded success!
Traceback (most recent call last):
  File "infer.py", line 23, in <module>
    from paddle3d.ops.pointnet2_ops import voxel_query_wrapper, grouping_operation, farthest_point_sample
ModuleNotFoundError: No module named 'pointnet2_ops'

[nepeplwu]

@wayyeah 感谢反馈，已经提交PR修复该问题：https://github.com/PaddlePaddle/Paddle3D/pull/297，可以拉取该PR进行验证

[wayyeah]

@wayyeah 感谢反馈，已经提交PR修复该问题：https://github.com/PaddlePaddle/Paddle3D/pull/297，可以拉取该PR进行验证

感谢修复，python推理问题修复了，C++推理的问题还是存在