TF TRT Integration Output Graph Def empty

Using a .pb file to create an optimized graph def using TF TRT integration with TRT 3, I can succesfully convert a mnist model, however when using an object detection model, it outputs the following, does this mean, no operation was optimized ?

library {
versions {

The following code was used for both:

import tensorflow as tf
from tensorflow.python.platform import gfile
with tf.Session() as sess:
    print("load graph")
    with gfile.FastGFile("model.pb",'rb') as f:
        graph_def = tf.GraphDef()
    # Get optimized graph
    trt_graph = trt.create_inference_graph(
    max_workspace_size_bytes=1 << 25,
    precision_mode="FP32",  # TRT Engine precision "FP32","FP16" or "INT8"
    minimum_segment_size=2  # minimum number of nodes in an engine

If i use .ckpt file to restore the session, and get the graph def, I am able to get the optimized trt graph.

got this on and tf 1.8.0…

Solved after lates tensorflow commit with TRT 4GA