I want to testing action recognition with deepstream_test5, and use 3d onnx model ,but failed

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) Jetson AGX
• DeepStream Version 7.0
**• JetPack Version (valid for Jetson only) 6.0 GA
**• TensorRT Version 8.6
**• NVIDIA GPU Driver Version (valid for GPU only) 540.3.0
**• Issue Type( questions, new requirements, bugs) questions
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

The config is [property]
gpu-id=0
net-scale-factor=0.0039215697906911373
#uff-file=/pn26-files/peoplenet_V2.6_resnet34_hr_noreg_ph2_dla.uff
#uff-input-dims=3;544;960;0
#uff-input-blob-name=input_1
#int8-calib-file=/pn26-files/peoplenet_V2.6_resnet34_hr_noReg_ph2_dla.cache
#model-engine-file=/opt/nvidia/deepstream/deepstream/rosie-perception-app/ds-rosie/models/pn2.6/peoplenet_V2.6_resnet34_hr_noreg_ph2_dla.uff_b4_dla0_int8.engine
onnx-file=/data/debug/fulltarget-detect/files/resnet18_3d_rgb_hmdb5_32.onnx
model-engine-file=/data/debug/actionrecognitionnet_deployable_onnx_v2.0/model_b1_gpu0_fp16.engine
labelfile-path=/data/debug/deepstream/deepstream/sources/apps/sample_apps/deepstream-3d-action-recognition/labels.txt
batch-size=1
process-mode=1
network-input-shape=4;3;32;224;224
model-color-format=0

0=FP32, 1=INT8, 2=FP16 mode

network-mode=2
num-detected-classes=5
interval=0
gie-unique-id=1
#output-blob-names=output_cov/Sigmoid;output_bbox/BiasAdd

0=Group Rectangles, 1=DBSCAN, 2=NMS, 3 = None(No clustering)

cluster-mode=2
#enable-dla=1
#use-dla-core=0
scaling-filter=4
maintain-aspect-ratio=1
parse-bbox-func-name=NvDsInferParseYolo
custom-lib-path=/data/debug/fulltarget-detect/pn26/pn26/libnvdsinfer_custom_impl_Yolo.so
engine-create-func-name=NvDsInferYoloCudaEngineGet

The wrong result is below

1.Please use test5_config_file_src_infer.txt to build the same pipeline as deepstream-3d-action-recognition

The pipeline like

.... --> nvstreammux --> nvdspreprocess (with configure file config_preprocess_3d_custom.txt ) --> nvinfer ---> ...

2.Modify your nvinfer configuration file like config_infer_primary_3d_action.txt

  1. Since this model output is tensor-meta, so add the post processer like pgie_src_pad_buffer_probe in deepstream_3d_action_recognition.cpp.

But I want to use nvmultiurisrcbin

This has no effect on the above solution.You have to build the right pipeline first.

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

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.