Trying to go from tensorflow faster rcnn frozen model to tensorrt engine

I have the faster_rcnn_resnet101_coco_2018_01_28 frozen model for tensorflow(from the google object detection model zoo) and im attempting to optimize with tensorrt 4. I know there is a c++ example using caffe and a couple modified layer, but it is not much help for tensorflow and python.
Code im using is here:

import tensorrt as trt
import uff
from tensorrt.parsers import uffparser
import glob
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction = .67)

I have 2 questions:

  1. Does anyone understand how to obtain the output layer name(s)? The model is from the google detection api and I do not know what the output layer is called.

  2. Does tensorrt support all the layers from the faster_rcnn_resnet101_coco_2018_01_28? If not, is there an easy solution for that?


same problem…

1.) Following code will print the output nodes of tensorflow graph.

for i in sess.graph.get_operations():

2.) tensorRT wont support dropout layers. When I was checking dropout layers gave me error after the removal everything was fine.