Trying to convert Detectron2's keypoint_rcnn_R_50_fpn_3x to TensorRT

AI & Data Science Deep Learning (Training & Inference) TensorRT
,
1

Description

Hi, so following the Tensorrt’s Github page, I was successfully able to generate the TensorRT engine for mask_rcnn and faster_rcnn.

But when it comes to keypoint_rcnn, while the engine did got created but the output I get is not actual keypoints but the keypoint heatmaps.

Now I do know that the support for detectron2 to tensorrt is specifically supported for mask_rcnn but still, since I am not very skilled at this, I was hoping to get some ideas.

Thank You.

Environment

TensorRT Version: 8.6
GPU Type: NVIDIA GeForce RTX 3070 Ti
CUDA Version: 12.0
CUDNN Version: 8.8
Operating System + Version: Ubuntu 20.04
Python Version (if applicable): 3.8
PyTorch Version (if applicable): 2.1

Relevant Files

Keypoint ONNX: https://drive.google.com/file/d/1po8GkgTc8lr020Wpnqjr5Wpqw9imr8_R/view?usp=share_link

Keypoint Converted ONNX: https://drive.google.com/file/d/12Ncepg8qPmmIuCMzvNnHb5SdAN4cwgtU/view?usp=share_link

Steps To Reproduce

Just follow this link

2

Hi,

We couldn’t successfully build the TensorRT engine using the ONNX file shared.
Please share with us more details of the problem, logs with the issue repro model, and sample data.

Thank you.

3

Please request the converted keypoint onnx file one more time.
Thank You.