How to detect with my model in TRT_object_detection

Robotics & Edge Computing Jetson & Embedded Systems Jetson TX2
1

I succeeded by following the TRT_object_detection script as it is. The ssd_mobilenet_v2_coco model was used here. I want to run the script with the model I retrained. I means I want to use a model that I’ve re-trained with my data. I don’t know how. I have “frozen_inference_graph.pb” file.

I use Jepack 4.2, tensorflow version=1.14.0, TensorRT version=5.0

3

Hi,

Does your model also use ssd_mobilenet_v2 architecture?
If yes, you just need to update the file path here:

https://github.com/AastaNV/TRT_object_detection/blob/master/config/model_ssd_mobilenet_v2_coco_2018_03_29.py#L3

Thanks.