Google Colab ( runtime T4 GPU ) openpose execution error!

[krish07751]

Python 3.10.12

Google Colab cell:

!cd openpose && ./build/examples/openpose/openpose.bin --image_dir ./examples/images/ --face --hand --display 0 --render_pose 0 --write_json ./output_jsons

Error:

Starting OpenPose demo...
Configuring OpenPose...
Starting thread(s)...
Auto-detecting all available GPUs... Detected 1 GPU(s), using 1 of them starting at GPU 0.
F1129 04:40:41.864763 16387 cudnn_conv_layer.cpp:53] Check failed: status == CUDNN_STATUS_SUCCESS (1 vs. 0) CUDNN_STATUS_NOT_INITIALIZED
*** Check failure stack trace: ***
@ 0x7bf61769cb03 google::LogMessage::Fail()
@ 0x7bf6176a49d1 google::LogMessage::SendToLog()
...

Tested cell:

import torch
torch.backends.cudnn.is_available()
Output: True

!nvidia-smi

Fri Nov 29 04:40:31 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |
| N/A 39C P0 25W / 70W | 121MiB / 15360MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
+---------------------------------------------------------------------------------------+

[zaina1864]

hello, were you able to find a solution for this?