Run objecet detection with custom model on Xavier

hi,

  1. I have already trained a fast-rcnn model in tensorflow,I want to use it in Xavier,
    Which website should I visit?

  2. On Xavier I run “python3 camera_tf_trt.py --usb --model ssd_mobilenet_v1_coco”
    it works , but I got multipule bounding box for one class,How can I solve it?

thx

Hi,

1) You can modify this sample for your use case:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#fasterrcnn_sample

2) Do you use this GitHub?
Maybe you can try to increase the confidence value to see if helps:
https://github.com/jkjung-avt/tf_trt_models/blob/master/camera_tf_trt.py#L93

Thanks.