Openpose: cudnn_conv_layer.cu:28] Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED

[xufunly]

Posting rules

1. python demo: examplestutorial_api_python01_body_from_image.py
   code line: opWrapper.emplaceAndPop([datum])
   get err:
   F0608 08:30:11.604262 10688 cudnn_conv_layer.cu:28] Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED
   * Check failure stack trace: *

2. My System Configuration
   CPU Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz
   Win10
   NVIDIA GeForce RTX 2060, Driver Version 430.86
   CUDA v10.0
   cudnn 7.5.0

   python code, get error, F0608 08:30:11.604262 10688 cudnn_conv_layer.cu:28] Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED
   * Check failure stack trace: *
   can anyone help me, thanks!

Issue Summary

Executed Command (if any)

Note: add --logging_level 0 --disable_multi_thread to get higher debug information.

OpenPose Output (if any)

Errors (if any)

Type of Issue

You might select multiple topics, delete the rest:

• Compilation/installation error
• Execution error
• Help wanted
• Question
• Enhancement / offering possible extensions / pull request / etc
• Other (type your own type)

Your System Configuration

1. Whole console output (if errors appeared), paste the error to PasteBin and then paste the link here: LINK

2. OpenPose version: Latest GitHub code? Or specific commit (e.g., d52878f)? Or specific version from Release section (e.g., 1.2.0)?

3. General configuration:

   • Installation mode: CMake, sh script, manual Makefile installation, ... (Ubuntu); CMake, ... (Windows); ...?
   • Operating system (lsb_release -a in Ubuntu):
   • Operating system version (e.g., Ubuntu 16, Windows 10, ...):
   • Release or Debug mode? (by default: release):
   • Compiler (gcc --version in Ubuntu or VS version in Windows): 5.4.0, ... (Ubuntu); VS2015 Enterprise Update 3, VS2017 community, ... (Windows); ...?

4. Non-default settings:

   • 3-D Reconstruction module added? (by default: no):
   • Any other custom CMake configuration with respect to the default version? (by default: no):

5. 3rd-party software:

   • Caffe version: Default from OpenPose, custom version, ...?
   • CMake version (cmake --version in Ubuntu):
   • OpenCV version: pre-compiled 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?; ...?

6. If GPU mode issue:

   • CUDA version (cat /usr/local/cuda/version.txt in most cases):
   • cuDNN version:
   • GPU model (nvidia-smi in Ubuntu):

7. If CPU-only mode issue:

   • CPU brand & model:
   • Total RAM memory available:

8. If Python API:

   • Python version: 2.7, 3.7, ...?
   • Numpy version (python -c "import numpy; print numpy.version.version" in Ubuntu):

9. If Windows system:

   • Portable demo or compiled library?

10. If speed performance issue:

    • Report OpenPose timing speed based on this link.

[fabian57fabian]

I'm having the same issue.
Check failed: status == CUDNN_STATUS_SUCCESS (1 vs. 0) CUDNN_STATUS_NOT_INITIALIZED
Similar to the Check failed: error == cudaSuccess (2 vs. 0) out of memory, it seemed like a low GPU memory but it can be a problem with CUDA and cuDNN: you should download a version of cuDNN that supports your CUDA version

[fabian57fabian]

I solved this buying a brand new GTX 1660ti Armor Oc 6G.
Upragrated from 2 Gb to 6 Gb, now it works perfectly.
I also used CUDA 10.0 and cuDNN 7.5.

[imistyrain]

The architure of 20x0 is Turing, the compute ability is compute_75, you should change some code of caffe and rebuild it as Windows+RTX2080+Caffe+Yolo配置

[CrazyReason]

I also encountered the same problem
OpenPoseDemo.exe --video xxx.avi
get err:
Starting pose estimation demo.
Auto-detecting all available GPUs... Detected 1 GPU(s), using 1 of them starting at GPU 0.
Starting thread(s)
F0707 16:24:19.065626 11580 pooling_layer.cu:212] Check failed: error == cudaSuccess (8 vs. 0) invalid device function
* Check failure stack trace: *

My System Configuration
CPU: amd 2700X
GPU:RTX2080
CUDA 10.0 and cuDNN 7.5.

can anyone help me, thanks!

[CrazyReason]

Updating the latest version can solve this problem

[gineshidalgo99]

Seems that the error no longer happens in the latest version of OpenPose (v1.5, using the Caffe version included with OpenPose).

[xufunly]

Thanks @ALL，the latest version can solve this problem

[hooman67]

@gineshidalgo99 updating the latest version of what?

[ycyoon]

I encounted this problem with the latest openpose version.
I solved this problem by building without CUDNN

[g782373711]

I encounted this problem with the latest openpose version.
I solved this problem by building without CUDNN

me too，I try to update CUDNN ,but it doesn't work.
finally, I comment CUDNN in Makefile.Config, but this solution can‘t give full play to CUDNN abilities