[Bug] ./pose_tracker : error: mismatched number of keypoints: 17 vs 26, skip pose visualization.

[msabbah06]

Checklist

• I have searched related issues but cannot get the expected help.
• 2. I have read the FAQ documentation but cannot get the expected help.
• 3. The bug has not been fixed in the latest version.

Describe the bug

Hello,
I want to use rtmpose body 26 keypoints model with mmdeploy and tensorrt. I successfully converted the pytorch model to tensorrt model using the commands specified below.

Then to test how the pose_tracker is doing with my webcam, I go inside build/bin and I launch the third command.
The image is well displayed but the visualisation of the model is not and I have the following message :
"error: mismatched number of keypoints: 17 vs 26, skip pose visualization."
Therefore, I think that the visualisation has not been adapted for the body 26 models of mmpose. Is it something that I am missing or should it be implemented ? The next question would be to if in python, when importing PoseTracker, would the visualisation be available ?

Thank you a lot in advance.
Best regards,
Maxime

Reproduction

Convert mmdet to .engine

python3 tools/deploy.py \
configs/mmdet/detection/detection_tensorrt_static-320x320.py \
../mmpose/projects/rtmpose/rtmdet/person/rtmdet_nano_320-8xb32_coco-person.py \
https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_nano_8xb32-100e_coco-obj365-person-05d8511e.pth \
demo/resources/human-pose.jpg \
--work-dir rtmpose-trt/rtmdet-nano \
--device cuda:0 \
--show \
--dump-info  # dump sdk info

Convert mmpose halpe 26 to .engine

python3 tools/deploy.py \
configs/mmpose/pose-detection_simcc_tensorrt_dynamic-256x192.py \
../mmpose/projects/rtmpose/rtmpose/body_2d_keypoint/rtmpose-m_8xb512-700e_body8-halpe26-256x192.py \
https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7-halpe26_700e-256x192-4d3e73dd_20230605.pth \
demo/resources/human-pose.jpg \
--work-dir rtmpose-trt/rtmpose-m \
--device cuda:0 \
--show \
--dump-info  # dump sdk info

Command to test the pose tracker :

./pose_tracker ../../rtmpose-trt/rtmdet-nano/ ../../rtmpose-trt/rtmpose-m/ 0 --device cuda

Environment

The environment setup is the latest docker image I pulled from mmdeploy docker hub.

Error traceback

error: mismatched number of keypoints: 17 vs 26, skip pose visualization.