idealboy opened a new issue #14191: About mxnet-tensorrt's problem between different mxnet version? URL: https://github.com/apache/incubator-mxnet/issues/14191 Note: Providing complete information in the most concise form is the best way to get help. This issue template serves as the checklist for essential information to most of the technical issues and bug reports. For non-technical issues and feature requests, feel free to present the information in what you believe is the best form. For Q & A and discussion, please start a discussion thread at https://discuss.mxnet.io ## Description when I use mxnet 1.3.0 with USE_TENSORRT, I found it has some problem when loading model(generate from 0.9.3).The executor with tensorrt always give the same output whatever is the input. I re-save the old version model within mxnet1.3.0 framework, but it is still such case when doing inference. ## Environment info (Required) ``` What to do: 1. Download the diagnosis script from https://raw.githubusercontent.com/apache/incubator-mxnet/master/tools/diagnose.py 2. Run the script using `python diagnose.py` and paste its output here. ``` ----------Python Info---------- ('Version :', '2.7.15') ('Compiler :', 'GCC 7.3.0') ('Build :', ('default', 'Dec 14 2018 19:04:19')) ('Arch :', ('64bit', '')) ------------Pip Info----------- ('Version :', '18.1') ('Directory :', '$ANACONDA_HOME/lib/python2.7/site-packages/pip') ----------MXNet Info----------- ('Version :', '1.3.0') ('Directory :', '/**/python2.7/site-packages/mxnet-1.3.0-py2.7.egg/mxnet') Hashtag not found. Not installed from pre-built package. ----------System Info---------- ('Platform :', 'Linux-3.18.6-2.el7.centos.x86_64-x86_64-with-centos-7.3.1611-Core') ('system :', 'Linux') ('node :', '**') ('release :', '3.18.6-2.el7.centos.x86_64') ('version :', '#1 SMP Mon Oct 24 13:01:33 CST 2016') ----------Hardware Info---------- ('machine :', 'x86_64') ('processor :', 'x86_64') Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 56 On-line CPU(s) list: 0-55 Thread(s) per core: 2 Core(s) per socket: 14 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 79 Model name: Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz Stepping: 1 CPU MHz: 2599.725 BogoMIPS: 5205.75 Virtualization: VT-x L1d cache: 32K L1i cache: 32K L2 cache: 256K L3 cache: 35840K NUMA node0 CPU(s): 0-13,28-41 NUMA node1 CPU(s): 14-27,42-55 ----------Network Test---------- Package used (Python/R/Scala/Julia): (I'm using Python and c++ package) For Scala user, please provide: 1. Java version: (`java -version`) 2. Maven version: (`mvn -version`) 3. Scala runtime if applicable: (`scala -version`) For R user, please provide R `sessionInfo()`: ## Build info (Required if built from source) Compiler (gcc/clang/mingw/visual studio):gcc MXNet commit hash: (Paste the output of `git rev-parse HEAD` here.) Build config: (Paste the content of config.mk, or the build command.) ADD_LDFLAGS=-L/usr/lib64 -lgfortran -L/usr/local/lib -lopenblas # the additional compile flags you want to add ADD_CFLAGS = #--------------------------------------------- # matrix computation libraries for CPU/GPU #--------------------------------------------- # whether use CUDA during compile USE_CUDA = 1 # add the path to CUDA library to link and compile flag # if you have already add them to environment variable, leave it as NONE # USE_CUDA_PATH = /usr/local/cuda USE_CUDA_PATH = /usr/local/cuda # whether to enable CUDA runtime compilation ENABLE_CUDA_RTC = 1 # whether use CuDNN R3 library USE_CUDNN = 1 #whether to use NCCL library USE_NCCL = 0 #add the path to NCCL library USE_NCCL_PATH = NONE # whether use opencv during compilation # you can disable it, however, you will not able to use # imbin iterator USE_OPENCV = 1 #whether use libjpeg-turbo for image decode without OpenCV wrapper USE_LIBJPEG_TURBO = 0 #add the path to libjpeg-turbo library USE_LIBJPEG_TURBO_PATH = NONE # use openmp for parallelization USE_OPENMP = 1 USE_OPERATOR_TUNING = 1 # Use gperftools if found USE_GPERFTOOLS = 1 # path to gperftools (tcmalloc) library in case of a non-standard installation USE_GPERFTOOLS_PATH = # Link gperftools statically USE_GPERFTOOLS_STATIC = # Use JEMalloc if found, and not using gperftools USE_JEMALLOC = 1 # path to jemalloc library in case of a non-standard installation USE_JEMALLOC_PATH = # Link jemalloc statically USE_JEMALLOC_STATIC = # Create C++ interface package USE_CPP_PACKAGE = 1 # Create C++ interface package USE_CPP_PACKAGE = 1 ## Error Message: (Paste the complete error message, including stack trace.) ## Minimum reproducible example (If you are using your own code, please provide a short script that reproduces the error. Otherwise, please provide link to the existing example.) ## Steps to reproduce (Paste the commands you ran that produced the error.) 1. 2. ## What have you tried to solve it? 1. re-save by mxnet1.3.0, then it has the same problem 2. re-train by mxnet-1.3.0, then it seems work. 3. At first, I think it's my fault in re-implementing the MXPredCreate and MxSetInputEx( the two functions are going to support tensorrt in c++ interface). but I think they are right after debuging and comparing with the result from "pip install mxnet-tensorrt-cu90" . Thank you very much for your explanation and review, so that the mxnet-tensorrt has a better compatibility wit hthe old verions model. Thank you!
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
