tf_trt_models's 'camera_tf_trt.py' about hand-detection-tutorial HOT 8 CLOSED

What version of tensorflow and TensorRT are you using? And which platform or which GPU are you running the code with?

from hand-detection-tutorial.

Tensorflow : 1.14.0
TensorRT : 5.0.6.3
platform : JestonTX2

from hand-detection-tutorial.

I have no idea why you get this error. Would you be able to reproduce the error with my tf_trt_models code? Please show me the procedure to reproduce the error.

from hand-detection-tutorial.

git clone tf_trt_models

create a new directory(ssd_mobilenet_v2_face) in tf_trt_models/data.

Put the .ckpt file, .config file, .frozen_inference_graph.pb, object-detection.pbtxt file in the that directory.

Add my model to the 'egohands_models.py' file in tf_trt_models/utils.
'ssd_mobilenet_v2_face': { 'config_path': 'data/ssd_mobilenet_v2_face.config', 'checkpoint_path': 'data/ssd_mobilenet_v2_face/model.ckpt-22275', },

run python3 camera_tf_trt.py --image --filename image1.jpeg --model ssd_mobilenet_v2_face --labelmap data/object-detection.pbtxt --num-classes 1 --build

from hand-detection-tutorial.

Just running this code makes the same error
: python3 camera_tf_trt.py --usb --model ssd_mobilenet_v1_coco --build

from hand-detection-tutorial.

python3 camera_tf_trt.py --image --filename image1.jpeg --model ssd_mobilenet_v2_face --labelmap data/object-detection.pbtxt --num-classes 1 --build
2020-04-13 16:53:12.396494: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:53:24.173083: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
INFO:main:called with args: Namespace(conf_th=0.3, do_build=True, do_tensorboard=False, filename='image1.jpeg', image_height=480, image_width=640, labelmap_file='data/object-detection.pbtxt', model='ssd_mobilenet_v2_face', num_classes=1, rtsp_latency=200, rtsp_uri=None, use_file=False, use_image=True, use_rtsp=False, use_usb=False, video_dev=0)
INFO:main:reading label map
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/utils/label_map_util.py:131: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

INFO:main:building TRT graph and saving to pb: ./data/ssd_mobilenet_v2_face_trt.pb
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/slim-0.1-py3.6.egg/nets/inception_resnet_v2.py:373: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/slim-0.1-py3.6.egg/nets/mobilenet/mobilenet.py:389: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead.

WARNING:tensorflow:From /home/hyebin/tf_trt_models/tf_trt_models/detection.py:154: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.

WARNING:tensorflow:From /home/hyebin/tf_trt_models/tf_trt_models/detection.py:158: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.

2020-04-13 16:53:26.036398: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2020-04-13 16:53:26.037794: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x27fdc820 executing computations on platform Host. Devices:
2020-04-13 16:53:26.037913: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): ,
2020-04-13 16:53:26.056882: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcuda.so.1
2020-04-13 16:53:26.189656: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:53:26.190243: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x295e2c70 executing computations on platform CUDA. Devices:
2020-04-13 16:53:26.190357: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): NVIDIA Tegra X2, Compute Capability 6.2
2020-04-13 16:53:26.191407: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:53:26.191818: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
2020-04-13 16:53:26.191992: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:53:26.192243: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2020-04-13 16:53:26.192414: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2020-04-13 16:53:26.192566: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2020-04-13 16:53:26.231992: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2020-04-13 16:53:26.255495: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2020-04-13 16:53:26.255963: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2020-04-13 16:53:26.256444: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:53:26.257075: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:53:26.257316: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2020-04-13 16:53:29.166914: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-04-13 16:53:29.167239: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0
2020-04-13 16:53:29.167399: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N
2020-04-13 16:53:29.168219: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:53:29.168838: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:53:29.169174: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 256 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X2, pci bus id: 0000:00:00.0, compute capability: 6.2)
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:374: The name tf.gfile.MakeDirs is deprecated. Please use tf.io.gfile.makedirs instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:130: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:327: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/core/preprocessor.py:2340: The name tf.image.resize_images is deprecated. Please use tf.image.resize instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/meta_architectures/ssd_meta_arch.py:390: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/core/box_predictor.py:704: The name tf.logging.info is deprecated. Please use tf.compat.v1.logging.info instead.

INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/core/box_list_ops.py:687: add_dispatch_support..wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:356: get_or_create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.get_or_create_global_step
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:402: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

2020-04-13 16:54:39.451085: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.451470: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
2020-04-13 16:54:39.451730: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:54:39.451860: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2020-04-13 16:54:39.451982: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2020-04-13 16:54:39.452079: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2020-04-13 16:54:39.452174: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2020-04-13 16:54:39.452268: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2020-04-13 16:54:39.452384: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2020-04-13 16:54:39.452825: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.453349: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.453577: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2020-04-13 16:54:39.458367: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.458778: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
2020-04-13 16:54:39.458958: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:54:39.459068: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2020-04-13 16:54:39.459163: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2020-04-13 16:54:39.459255: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2020-04-13 16:54:39.459351: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2020-04-13 16:54:39.459444: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2020-04-13 16:54:39.459535: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2020-04-13 16:54:39.459865: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.460401: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.460646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2020-04-13 16:54:39.460755: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-04-13 16:54:39.460808: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0
2020-04-13 16:54:39.460854: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N
2020-04-13 16:54:39.461287: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.461843: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:54:39.462122: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 256 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X2, pci bus id: 0000:00:00.0, compute capability: 6.2)
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from data/ssd_mobilenet_v2_face/model.ckpt-22275
2020-04-13 16:55:31.360851: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:31.361197: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
2020-04-13 16:55:31.361361: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:55:31.361467: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2020-04-13 16:55:31.361562: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2020-04-13 16:55:31.361654: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2020-04-13 16:55:31.361752: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2020-04-13 16:55:31.362002: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2020-04-13 16:55:31.362099: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2020-04-13 16:55:31.362456: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:31.363060: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:31.363315: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2020-04-13 16:55:31.363428: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-04-13 16:55:31.363482: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0
2020-04-13 16:55:31.363531: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N
2020-04-13 16:55:31.363924: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:31.364453: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:31.364730: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 256 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X2, pci bus id: 0000:00:00.0, compute capability: 6.2)
INFO:tensorflow:Restoring parameters from data/ssd_mobilenet_v2_face/model.ckpt-22275
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:96: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.compat.v1.graph_util.convert_variables_to_constants
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/graph_util_impl.py:270: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.compat.v1.graph_util.extract_sub_graph
INFO:tensorflow:Froze 344 variables.
INFO:tensorflow:Converted 344 variables to const ops.
INFO:root:2384 ops in the final graph.
2020-04-13 16:55:45.608605: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:45.608934: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
2020-04-13 16:55:45.609108: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:55:45.609212: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2020-04-13 16:55:45.609316: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2020-04-13 16:55:45.609407: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2020-04-13 16:55:45.609500: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2020-04-13 16:55:45.609635: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2020-04-13 16:55:45.609730: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2020-04-13 16:55:45.610061: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:45.610551: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:45.610841: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2020-04-13 16:55:45.610948: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-04-13 16:55:45.610998: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0
2020-04-13 16:55:45.611041: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N
2020-04-13 16:55:45.611398: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:45.611879: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:55:45.612138: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 256 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X2, pci bus id: 0000:00:00.0, compute capability: 6.2)
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:285: The name tf.saved_model.builder.SavedModelBuilder is deprecated. Please use tf.compat.v1.saved_model.builder.SavedModelBuilder instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:288: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info.
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:294: The name tf.saved_model.signature_def_utils.build_signature_def is deprecated. Please use tf.compat.v1.saved_model.signature_def_utils.build_signature_def instead.

WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/exporter.py:300: The name tf.saved_model.tag_constants.SERVING is deprecated. Please use tf.saved_model.SERVING instead.

INFO:tensorflow:No assets to save.
INFO:tensorflow:No assets to write.
INFO:tensorflow:SavedModel written to: .generated_model/saved_model/saved_model.pb
WARNING:tensorflow:From /home/hyebin/.local/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/utils/config_util.py:171: The name tf.gfile.Open is deprecated. Please use tf.io.gfile.GFile instead.

INFO:tensorflow:Writing pipeline config file to .generated_model/pipeline.config
INFO:tensorflow:Linked TensorRT version: (5, 1, 6)
INFO:tensorflow:Loaded TensorRT version: (5, 0, 6)
WARNING:tensorflow:TensorRT mismatch. Compiled against version 5.1.6, but loaded 5.0.6. Things may not work
2020-04-13 16:56:30.869236: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:56:30.869602: I tensorflow/core/grappler/devices.cc:55] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 0
2020-04-13 16:56:30.869968: I tensorflow/core/grappler/clusters/single_machine.cc:359] Starting new session
2020-04-13 16:56:30.871556: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:56:30.871899: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
2020-04-13 16:56:30.872109: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:56:30.872230: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2020-04-13 16:56:30.872327: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2020-04-13 16:56:30.872421: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2020-04-13 16:56:30.872615: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2020-04-13 16:56:30.872754: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2020-04-13 16:56:30.872848: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2020-04-13 16:56:30.873183: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:56:30.873671: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:56:30.873923: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2020-04-13 16:56:30.874077: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-04-13 16:56:30.874132: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0
2020-04-13 16:56:30.874210: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N
2020-04-13 16:56:30.874580: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:56:30.875163: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:972] ARM64 does not support NUMA - returning NUMA node zero
2020-04-13 16:56:30.875441: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 256 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X2, pci bus id: 0000:00:00.0, compute capability: 6.2)
2020-04-13 16:56:40.628278: I tensorflow/compiler/tf2tensorrt/segment/segment.cc:460] There are 156 ops of 29 different types in the graph that are not converted to TensorRT: Fill, Merge, ConcatV2, Switch, Range, ZerosLike, Identity, NonMaxSuppressionV3, Minimum, StridedSlice, ExpandDims, Unpack, TopKV2, Cast, Transpose, Placeholder, Mul, Reshape, ResizeBilinear, Squeeze, Add, Pack, Const, Sub, Greater, Shape, Where, NoOp, GatherV2, (For more information see https://docs.nvidia.com/deeplearning/dgx/tf-trt-user-guide/index.html#supported-ops).
2020-04-13 16:56:40.936112: I tensorflow/compiler/tf2tensorrt/convert/convert_graph.cc:735] Number of TensorRT candidate segments: 1
2020-04-13 16:56:41.096326: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2020-04-13 16:56:41.111189: E tensorflow/compiler/tf2tensorrt/utils/trt_logger.cc:41] DefaultLogger (Unnamed Layer* 3) [Convolution]: at least three non-batch dimensions are required for input
2020-04-13 16:56:41.111684: E tensorflow/compiler/tf2tensorrt/utils/trt_logger.cc:41] DefaultLogger (Unnamed Layer* 9) [Convolution]: at least three non-batch dimensions are required for input
Segmentation fault (core dumped)

from hand-detection-tutorial.

I cannot determine possible root cause by looking at the log above. But I think you should fix the following problem first.

INFO:tensorflow:Linked TensorRT version: (5, 1, 6)
INFO:tensorflow:Loaded TensorRT version: (5, 0, 6)
WARNING:tensorflow:TensorRT mismatch. Compiled against version 5.1.6, but loaded 5.0.6. Things may not work

from hand-detection-tutorial.

Thanks.. I'll try.

from hand-detection-tutorial.