Segmentation fault when loading the model into the session

[catarinasantiago]

Hi,

I was able to compile and run your code sample, however on the instruction to load the model into the tensorflow session it gets segmentation fault.

This is my console output ( I added some prints to see where it got the segmentation fault):

2019-03-19 08:23:55.636337: I /home/catarina/Downloads/tensorflow-object-detection-cpp-master/main.cpp:52] graphPath:../demo/ssd_mobilenet_v1_egohands/frozen_inference_graph.pb >>>Read model into graph_def 2019-03-19 08:23:55.650293: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-03-19 08:23:55.679777: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2592000000 Hz 2019-03-19 08:23:55.680226: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x41a9a60 executing computations on platform Host. Devices: 2019-03-19 08:23:55.680250: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): , 2019-03-19 08:23:55.742939: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-03-19 08:23:55.743307: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties: name: GeForce GTX 965M major: 5 minor: 2 memoryClockRate(GHz): 0.9495 pciBusID: 0000:01:00.02019-03-19 08:23:55.636337: I /home/catarina/Downloads/tensorflow-object-detection-cpp-master/main.cpp:52] graphPath:../demo/ssd_mobilenet_v1_egohands/frozen_inference_graph.pb >>>Read model into graph_def 2019-03-19 08:23:55.650293: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-03-19 08:23:55.679777: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2592000000 Hz 2019-03-19 08:23:55.680226: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x41a9a60 executing computations on platform Host. Devices: 2019-03-19 08:23:55.680250: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): , 2019-03-19 08:23:55.742939: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-03-19 08:23:55.743307: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties: name: GeForce GTX 965M major: 5 minor: 2 memoryClockRate(GHz): 0.9495 pciBusID: 0000:01:00.0 totalMemory: 1.96GiB freeMemory: 1.16GiB 2019-03-19 08:23:55.743322: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0 2019-03-19 08:23:56.563700: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-03-19 08:23:56.563739: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 2019-03-19 08:23:56.563744: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N 2019-03-19 08:23:56.563892: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 887 MB memory) -> physical GPU (device: 0, name: GeForce GTX 965M, pci bus id: 0000:01:00.0, compute capability: 5.2) 2019-03-19 08:23:56.565482: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x174d9920 executing computations on platform CUDA. Devices: 2019-03-19 08:23:56.565509: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): GeForce GTX 965M, Compute Capability 5.2 >>>Reset tensorflow session Segmentation fault (core dumped)

Any help would be welcome.

Thanks!