How to speed up ssd_mobilenet_v1_fpn with tensorRT?

I have try some of ssd models in Tensorflow object detection API.But “fpn” is 640x640,I don’t know how to speed it.

Hi,

Have you tried to accelerate it with TensorFlow-TRT?
Here is a tutorial for your reference:
https://github.com/NVIDIA-AI-IOT/tf_trt_models

Thanks.

I have tried this github, but it doesn’t speed up ‘ssd_mobilenet_v1_fpn’.I think that TensorRT doesn’t seem to support FPN.

Hi,

Have you tried to convert the model into pure TensorRT PLAN?
https://github.com/NVIDIA-AI-IOT/tf_to_trt_image_classification

If the whole layer are supported, it should give you some speed up.
Thanks.

Any update?