Paddle3D
Paddle3D copied to clipboard
Published
20 hours ago •
PaddlePaddle
PaddlePaddle
测试Paddle3D的pointpillars案例c++推理过程报错（求解决）：
##已经按照Paddle3D文档安装好了python环境以及配置好了Paddle-Inference的环境，执行至文档（Paddle3D-develop/docs/models/pointpillars/README.md）"#### C++部署（Linux系统）"步骤处报错：
(venv) xx@xx-System-Product-Name:~/下载/Paddle3D-develop/deploy/pointpillars/cpp$ ./build/main --model_file /home/xx/下载/Paddle3D-develop/output/pointpillars.pdmodel --params_file /home/xx/下载/Paddle3D-develop/output/pointpillars.pdiparams --lidar_file /home/xx/下载/Paddle3D-develop/datasets/KITTI/testing/velodyne/000019.bin --point_cloud_range "0 -39.68 -3 69.12 39.68 1" --voxel_size ".16 .16 4" --max_points_in_voxel 32 --max_voxel_num 40000
--- Running analysis [ir_graph_build_pass]
--- Running analysis [ir_graph_clean_pass]
--- Running analysis [ir_analysis_pass]
--- Running IR pass [is_test_pass]
--- Running IR pass [simplify_with_basic_ops_pass]
--- Running IR pass [conv_bn_fuse_pass]
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0902 19:28:10.384897 29206 fuse_pass_base.cc:57] --- detected 16 subgraphs
--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]
--- Running IR pass [embedding_eltwise_layernorm_fuse_pass]
--- Running IR pass [multihead_matmul_fuse_pass_v2]
--- Running IR pass [gpu_cpu_squeeze2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_reshape2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_flatten2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_map_matmul_v2_to_mul_pass]
I0902 19:28:10.393903 29206 fuse_pass_base.cc:57] --- detected 1 subgraphs
--- Running IR pass [gpu_cpu_map_matmul_v2_to_matmul_pass]
--- Running IR pass [matmul_scale_fuse_pass]
--- Running IR pass [multihead_matmul_fuse_pass_v3]
--- Running IR pass [gpu_cpu_map_matmul_to_mul_pass]
--- Running IR pass [fc_fuse_pass]
--- Running IR pass [fc_elementwise_layernorm_fuse_pass]
--- Running IR pass [conv_elementwise_add_act_fuse_pass]
--- Running IR pass [conv_elementwise_add2_act_fuse_pass]
--- Running IR pass [conv_elementwise_add_fuse_pass]
I0902 19:28:10.408993 29206 fuse_pass_base.cc:57] --- detected 3 subgraphs
--- Running IR pass [transpose_flatten_concat_fuse_pass]
--- Running IR pass [runtime_context_cache_pass]
--- Running analysis [ir_params_sync_among_devices_pass]
I0902 19:28:10.417521 29206 ir_params_sync_among_devices_pass.cc:100] Sync params from CPU to GPU
--- Running analysis [adjust_cudnn_workspace_size_pass]
--- Running analysis [inference_op_replace_pass]
--- Running analysis [ir_graph_to_program_pass]
I0902 19:28:10.507484 29206 analysis_predictor.cc:1035] ======= optimize end =======
I0902 19:28:10.511466 29206 naive_executor.cc:102] --- skip [feed], feed -> voxels
I0902 19:28:10.511483 29206 naive_executor.cc:102] --- skip [feed], feed -> num_points_per_voxel
I0902 19:28:10.511484 29206 naive_executor.cc:102] --- skip [feed], feed -> coords
I0902 19:28:10.512696 29206 naive_executor.cc:102] --- skip [_generated_var_56], fetch -> fetch
I0902 19:28:10.512703 29206 naive_executor.cc:102] --- skip [_generated_var_57], fetch -> fetch
I0902 19:28:10.512706 29206 naive_executor.cc:102] --- skip [_generated_var_58], fetch -> fetch
W0902 19:28:10.523443 29206 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 11.7, Runtime API Version: 10.2
W0902 19:28:10.523874 29206 gpu_resources.cc:91] device: 0, cuDNN Version: 8.3.
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::operators::ConditionalBlockInferOp::RunImpl(paddle::framework::Scope const&, phi::Place const&) const
4 paddle::framework::Executor::Run(paddle::framework::ProgramDesc const&, paddle::framework::Scope*, int, bool, bool, std::vector<std::string, std::allocator<std::string > > const&, bool, bool)
5 paddle::framework::Executor::RunPreparedContext(paddle::framework::ExecutorPrepareContext*, paddle::framework::Scope*, bool, bool, bool)
6 paddle::framework::Executor::RunPartialPreparedContext(paddle::framework::ExecutorPrepareContext*, paddle::framework::Scope*, long, long, bool, bool, bool)
7 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, phi::Place const&)
8 paddle::operators::ConditionalBlockOp::RunImpl(paddle::framework::Scope const&, phi::Place const&) const
9 paddle::framework::Executor::Run(paddle::framework::ProgramDesc const&, paddle::framework::Scope*, int, bool, bool, std::vector<std::string, std::allocator<std::string > > const&, bool, bool)
10 paddle::framework::Executor::Prepare(paddle::framework::ProgramDesc const&, int, std::vector<std::string, std::allocator<std::string > > const&, bool)
11 paddle::framework::OpRegistry::CreateOp(paddle::framework::OpDesc const&)
12 paddle::framework::OpRegistry::CreateOp(std::string const&, std::map<std::string, std::vector<std::string, std::allocator<std::string > >, std::less<std::string >, std::allocator<std::pair<std::string const, std::vector<std::string, std::allocator<std::string > > > > > const&, std::map<std::string, std::vector<std::string, std::allocator<std::string > >, std::less<std::string >, std::allocator<std::pair<std::string const, std::vector<std::string, std::allocator<std::string > > > > > const&, paddle::framework::AttributeMap const&, bool)
13 phi::enforce::EnforceNotMet::EnforceNotMet(phi::ErrorSummary const&, char const*, int)
14 phi::enforce::GetCurrentTraceBackString[abi:cxx11](bool)
----------------------
Error Message Summary:
----------------------
NotFoundError: Operator (nms_gpu) is not registered.
[Hint: op_info_ptr should not be null.] (at /home/ls/下载/Paddle/paddle/fluid/framework/op_info.h:151)
已放弃 (核心已转储)
##运行python环境如下：
(venv) xx@xx-System-Product-Name:~/下载/Paddle3D-develop/deploy/pointpillars/cpp$ pip list
Package Version Editable project location
-------------------- ------------ ----------------------------
argon2-cffi 21.3.0
argon2-cffi-bindings 21.2.0
astor 0.8.1
async-generator 1.10
attrs 22.1.0
Babel 2.10.3
backcall 0.2.0
bce-python-sdk 0.8.74
bleach 4.1.0
cachetools 4.2.4
certifi 2022.6.15
cffi 1.15.1
charset-normalizer 2.0.12
click 8.0.4
colorlog 6.6.0
cycler 0.11.0
Cython 0.29.32
dataclasses 0.8
decorator 4.4.2
defusedxml 0.7.1
descartes 1.1.0
dill 0.3.4
easydict 1.9
entrypoints 0.4
et-xmlfile 1.1.0
filelock 3.4.1
fire 0.4.0
Flask 2.0.3
Flask-Babel 2.0.0
future 0.18.2
gast 0.5.3
idna 3.3
imageio 2.15.0
importlib-metadata 4.8.3
importlib-resources 5.4.0
ipykernel 5.5.6
ipython 7.16.3
ipython-genutils 0.2.0
ipywidgets 7.7.2
itsdangerous 2.0.1
jedi 0.17.2
Jinja2 3.0.3
joblib 1.1.0
jsonschema 4.0.0
jupyter 1.0.0
jupyter-client 7.1.2
jupyter-console 6.4.3
jupyter-core 4.9.2
jupyterlab-pygments 0.1.2
jupyterlab-widgets 1.1.1
kiwisolver 1.3.1
lap 0.4.0
llvmlite 0.36.0
MarkupSafe 2.0.1
matplotlib 3.3.4
mistune 0.8.4
motmetrics 1.2.5
multiprocess 0.70.12.2
nbclient 0.5.9
nbconvert 6.0.7
nbformat 5.1.3
nest-asyncio 1.5.5
networkx 2.5.1
notebook 6.4.10
numba 0.53.1
numpy 1.19.5
nuscenes-devkit 1.1.9
opencv-python 4.6.0.66
openpyxl 3.0.10
opt-einsum 3.3.0
packaging 21.3
paddle-bfloat 0.1.7
paddle3d 0.5.0 /home/xx/下载/Paddle3D-develop
paddledet 2.4.0
paddlepaddle-gpu 2.3.2
paddleseg 2.6.0
pandas 1.1.5
pandocfilters 1.5.0
parso 0.7.1
pexpect 4.8.0
pickleshare 0.7.5
Pillow 8.3.2
pip 21.3.1
pkg_resources 0.0.0
prettytable 2.5.0
prometheus-client 0.14.1
prompt-toolkit 3.0.30
protobuf 3.19.4
ptyprocess 0.7.0
pycocotools 2.0.4
pycparser 2.21
pycryptodome 3.15.0
Pygments 2.13.0
pyparsing 3.0.9
pyquaternion 0.9.9
pyrsistent 0.18.0
python-dateutil 2.8.2
pytz 2022.2.1
PyWavelets 1.1.1
PyYAML 6.0
pyzmq 23.2.1
qtconsole 5.2.2
QtPy 2.0.1
rarfile 4.0
requests 2.27.1
scikit-image 0.17.2
scikit-learn 0.24.2
scipy 1.5.4
Send2Trash 1.8.0
setuptools 59.6.0
Shapely 1.8.4
six 1.16.0
sklearn 0.0
termcolor 1.1.0
terminado 0.13.0
terminaltables 3.1.10
testpath 0.6.0
threadpoolctl 3.1.0
tifffile 2020.9.3
torch 1.10.0+cu102
torchaudio 0.10.0+cu102
torchvision 0.11.0+cu102
tornado 6.1
tqdm 4.64.0
traitlets 4.3.3
typeguard 2.13.3
typing_extensions 4.1.1
urllib3 1.26.12
visualdl 2.4.0
wcwidth 0.2.5
webencodings 0.5.1
Werkzeug 2.0.3
wheel 0.37.1
widgetsnbextension 3.6.1
xmltodict 0.13.0
zipp 3.6.0
在
paddle3d/ops/路径下，执行python setup.py install安装一下模型所需的自定义算子
nms_gpu。
感谢解答，您提出的这个方法试过了，不过还是会有问题。后面gcc改用8.2.0版本就解决了。