it is because the source number is not equal to the first parameter(nvdspreprocess batch-size) of network-input-shape in configs/nvinfer/bodypose_classification_tao/config_preprocess_bodypose_classification.txt.
solution:
you can set two sources in indeepstream_pose_classification_config.yaml. for example:
list: file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_walk.mov;file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_walk.mov
1 Like