• Hardware Platform (Jetson / GPU) Nvidia Geforce RTX 4070 • DeepStream Version 7.0 • JetPack Version (valid for Jetson only) • TensorRT Version 8.6.1 • NVIDIA GPU Driver Version (valid for GPU only) 535.161.08 • Issue Type( questions, new requirements, bugs) BlazePose model integration problem…

[image] roman.tolmachov: Not really. BlazePose model returns only the pose key points, without bboxes, so I need only the key points array. You need to assign bbox to the object. If you don’t need bbox, just ignore bbox in the following plugins. [image] roman.tolmachov: I tried to implem…

[image] roman.tolmachov: net-scale-factor=0.0039215697906911373 model-color-format=0 Only these two parameters can be confirmed to be aligned with [image] roman.tolmachov: def preprocess_frame(frame, input_size): frame_resized = cv2.resize(frame, input_size) frame_normalized = frame_r…

[image] roman.tolmachov: output-tensor-meta=1 Why do you enable this parameter?

Thank you for your answer. I enable it, because I debug the meta data of the model

Thank you! Do I need change the parameter network-type=3 to 100, for the BlazePose? Because, now it is working like a Yolo and I am emulating in the plugin processing of the bboxes. Maybe it is not good way and I need to work with the BlazePose like a custom model?

[image] roman.tolmachov: Do I need change the parameter network-type=3 to 100, for the BlazePose? Seems you want to output the bboxes and the object masks, it is correct to set “network-type=3”. You can refer to the instance segmentation custom postprocessing sample “NvDsInferParseCustomMrcnn…

Not really. BlazePose model returns only the pose key points, without bboxes, so I need only the key points array. How to get it correctly in the deepstream? And is there such a possibility? Because I tried to implement the model via network-type=100 without processing the bboxes, and get the infere…

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

BlazePose integration problem to DeepStream 7.0

Accelerated Computing Intelligent Video Analytics DeepStream SDK

Fiona.Chen September 3, 2024, 10:18am 6

We know nothing about the model. You may refer to DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums to check the nvinfer configurations.

Topic		Replies	Views
I'm not able to set current parameter for headpose estimation model(roll,yaw,pitch) custom model DeepStream SDK	14	633	February 23, 2024
I want to run 「Pose Estimation with DeepStream」, but I don't understand the setup procedure DeepStream SDK	13	1206	February 17, 2023
Object detection pre-trained model inference issue in deepstream DeepStream SDK tensorrt , jetson-inference , gstreamer , python	50	1440	August 9, 2024
Deepstream_pose_estimation DeepStream SDK	14	2137	January 28, 2021
Deepstream pose estimation model: getting error while running DeepStream SDK	4	1216	December 29, 2020
Deepstream-pose-estimation-app --input file://$BODYPOSE3D_HOME/streams/bodypose.mp4: build engine file failed DeepStream SDK tensorrt	1	172	June 29, 2024
Deepstream-pose-classification-app is not working (deepstream 7.1) DeepStream SDK jetson , deepstream	18	433	September 25, 2025
Loss of precision to onnx converter for engine by deepstream 6.3 DeepStream SDK tensorrt , gstreamer , inference-server-triton	30	1029	August 2, 2024
PGIE element could not be created. Exiting DeepStream SDK	22	917	October 24, 2023
Human Pose detection model - Isses with converted model output in Deepstream DeepStream SDK tensorrt , onnx , deepstream	13	1698	September 19, 2022

BlazePose integration problem to DeepStream 7.0

Related topics