Got the "out of memory" error. Found that this is usually related to "cuDNN not being used". Double-checked that VS project was built with "enable cuDNN" in CMake. Reinstalled cuDNN, nothing changed. Used "Dependencies"/"DependencyWalker" on "caffe.dll" in the bin folder. Found that it was depending on cudnn64_7.dll in my older installation of openpose. But in this newest openpose 1.7.0.1 installation, caffe.dll is not depending on any "cudnn*.dll"--although there is indeed a "cudnn64_8.dll" in openpose's bin folder.
Executed Command (if any)
Note: add --logging_level 0 --disable_multi_thread to get higher debug information.
OpenPose Output (if any)
Errors (if any)
Check failed: error == cudaSuccess (2 vs. 0) out of memory
Type of Issue
Compilation/installation error
Execution error
Your System Configuration
Whole console output (if errors appeared), paste the error to PasteBin and then paste the link here: LINK
OpenPose version: Latest GitHub code? Or specific commit (e.g., d52878f)? Or specific version from Release section (e.g., 1.2.0)?
1.7.0.1
Issue Summary
Got the "out of memory" error. Found that this is usually related to "cuDNN not being used". Double-checked that VS project was built with "enable cuDNN" in CMake. Reinstalled cuDNN, nothing changed. Used "Dependencies"/"DependencyWalker" on "caffe.dll" in the bin folder. Found that it was depending on cudnn64_7.dll in my older installation of openpose. But in this newest openpose 1.7.0.1 installation, caffe.dll is not depending on any "cudnn*.dll"--although there is indeed a "cudnn64_8.dll" in openpose's bin folder.
Executed Command (if any)
Note: add
--logging_level 0 --disable_multi_thread
to get higher debug information.OpenPose Output (if any)
Errors (if any)
Check failed: error == cudaSuccess (2 vs. 0) out of memory
Type of Issue
Your System Configuration
Whole console output (if errors appeared), paste the error to PasteBin and then paste the link here: LINK
OpenPose version: Latest GitHub code? Or specific commit (e.g., d52878f)? Or specific version from
Release
section (e.g., 1.2.0)? 1.7.0.1General configuration:
lsb_release -a
in Ubuntu):gcc --version
in Ubuntu or VS version in Windows): 5.4.0, ... (Ubuntu); VS2015 Enterprise Update 3, VS2017 community, ... (Windows); ...?Windows10 + VS2019 comminuity+CMake
Non-default settings:
3rd-party software:
cmake --version
in Ubuntu):apt-get install libopencv-dev
(only Ubuntu); OpenPose default (only Windows); compiled from source? If so, 2.4.9, 2.4.12, 3.1, 3.2?; ...?All default
cat /usr/local/cuda/version.txt
in most cases):nvidia-smi
in Ubuntu):CUDA 11.1, cuDNN 8.0.5, GPU RTX3080
If CPU-only mode issue:
If Python API:
python -c "import numpy; print numpy.version.version"
in Ubuntu):If Windows system:
If speed performance issue: