tensorflow tensorrt error "Can't find a device placement for the op!"

python 3.6
tensorflow 1.12
tensorrt 6.0.1
cuda 10.0
cudnn 7.6.5

by running “https://devblogs.nvidia.com/tensorrt-integration-speeds-tensorflow-inference/” example “https://developer.download.nvidia.com/devblogs/tftrt_sample.tar.xz”.

Namespace(FP16=False, FP32=True, INT8=False, batch_size=4, dump_diff=False, native=False, num_loops=10, topN=5, update_graphdef=False, with_timeline=False, workspace_size=2048)
Starting at 2019-11-13 19:55:18.906182
2019-11-13 19:55:19.174392: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-11-13 19:55:19.174852: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties: 
name: Quadro K2200 major: 5 minor: 0 memoryClockRate(GHz): 1.124
pciBusID: 0000:01:00.0
totalMemory: 3.94GiB freeMemory: 3.46GiB
2019-11-13 19:55:19.174878: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
2019-11-13 19:55:25.870343: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-11-13 19:55:25.870395: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988]      0 
2019-11-13 19:55:25.870408: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0:   N 
2019-11-13 19:55:25.870512: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2019 MB memory) -> physical GPU (device: 0, name: Quadro K2200, pci bus id: 0000:01:00.0, compute capability: 5.0)
starting to convert tensorflow graph to tensorrt gragh
WARNING:tensorflow:From tftrt_sample.py:92: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.gfile.GFile.
INFO:tensorflow:Running against TensorRT version 6.0.1
starting OptimizeGraph
2019-11-13 19:55:27.471869: I tensorflow/core/grappler/devices.cc:51] Number of eligible GPUs (core count >= 8): 0
2019-11-13 19:55:27.472677: I tensorflow/core/grappler/clusters/single_machine.cc:359] Starting new session
2019-11-13 19:55:27.472933: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
2019-11-13 19:55:27.472957: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-11-13 19:55:27.472965: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988]      0 
2019-11-13 19:55:27.472970: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0:   N 
2019-11-13 19:55:27.473038: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2019 MB memory) -> physical GPU (device: 0, name: Quadro K2200, pci bus id: 0000:01:00.0, compute capability: 5.0)
2019-11-13 19:55:28.291331: I tensorflow/contrib/tensorrt/convert/convert_nodes.cc:2957] Segment @scope 'resnet_v1_50/', converted to graph
2019-11-13 19:55:28.291399: E tensorflow/contrib/tensorrt/convert/convert_graph.cc:418] Can't find a device placement for the op!
2019-11-13 19:55:28.833758: W tensorflow/contrib/tensorrt/log/trt_logger.cc:34] DefaultLogger Calling isShapeTensor before the entire network is constructed may result in an inaccurate result.
2019-11-13 19:55:28.856464: F tensorflow/contrib/tensorrt/log/trt_logger.cc:48] DefaultLoggerGot unknown severity level from TRT Applying generic optimizations to the graph for inference.
./run_all.sh: line 13:  9288 Aborted                 (core dumped) python3 tftrt_sample.py --FP32 --num_loops 10 --topN 5 --batch_size 4 --workspace_size 2048 --log_file log.txt --network resnet_v1_50_frozen.pb --input_node input --output_nodes resnet_v1_50/predictions/Reshape_1 --img_size 224 --img_file grace_hopper.jpg

Could you please let us know if you are still facing this issue?

Thanks