'TensorRT_model.pb' model's size is twice as large as the original pb model

[Julyliying]

Hi,
when i use tensorrt to generate trt model, i found the FP16 or INT8 trt model's size is twice as large as the original tensorflow pb model, i think it's wired, and do you know why?
my running environment is:
GPU 1080Ti, CUDA10.0, cudann7.5, Tensorflow1.13, TensorRT5.0
thanks

[Julyliying]

Does anyone know what is wrong?

[ruyijidan]

my FP16 trt model is 653.5M ， I guess it‘s OK，because at GPU 970M the PFS from 10 to 20

[ruyijidan]

can you see the trt model fps？if you can please tell me the detail version ty!!
cudann7.5.?, Tensorflow1.13.?, TensorRT5.0.?

[Julyliying]

GPU 1080Ti, CUDA10.0, cudann7.5, Tensorflow1.13, TensorRT5.0. @ruyijidan

[ruyijidan]

@Julyliying ty！but little obvious effect at 1080ti,
cudnn7.5.1.10 Tensorflow1.13,.1 TensorRT5.1.5.0