2020-07-10 01:02:54.545337: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-07-10 01:02:59.704959: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libnvinfer.so.7
2020-07-10 01:02:59.756647: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libnvinfer_plugin.so.7
2020-07-10 01:03:05.388512: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1
2020-07-10 01:03:05.452344: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:05.452491: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:00:00.0 name: NVIDIA Tegra X1 computeCapability: 5.3
coreClock: 0.9216GHz coreCount: 1 deviceMemorySize: 3.87GiB deviceMemoryBandwidth: 194.55MiB/s
2020-07-10 01:03:05.452550: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-07-10 01:03:05.452651: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-07-10 01:03:05.508861: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-07-10 01:03:05.566081: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-07-10 01:03:05.631987: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-07-10 01:03:05.659172: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-07-10 01:03:05.659369: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.8
2020-07-10 01:03:05.659686: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:05.660058: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:05.660194: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2020-07-10 01:03:08.356882: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2020-07-10 01:03:08.358103: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x236e8b40 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-07-10 01:03:08.358161: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-07-10 01:03:08.472967: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:08.473263: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2364e440 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-07-10 01:03:08.473311: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): NVIDIA Tegra X1, Compute Capability 5.3
2020-07-10 01:03:08.473637: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:08.473743: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:00:00.0 name: NVIDIA Tegra X1 computeCapability: 5.3
coreClock: 0.9216GHz coreCount: 1 deviceMemorySize: 3.87GiB deviceMemoryBandwidth: 194.55MiB/s
2020-07-10 01:03:08.473817: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-07-10 01:03:08.473864: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-07-10 01:03:08.473939: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-07-10 01:03:08.473987: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-07-10 01:03:08.474029: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-07-10 01:03:08.474072: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-07-10 01:03:08.474108: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.8
2020-07-10 01:03:08.474239: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:08.474400: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:08.474465: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2020-07-10 01:03:08.474556: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-07-10 01:03:20.380033: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-07-10 01:03:20.380112: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]      0
2020-07-10 01:03:20.380135: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0:   N
2020-07-10 01:03:20.380397: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:20.380642: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:20.380798: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2048 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X1, pci bus id: 0000:00:00.0, compute capability: 5.3)
2020-07-10 01:03:29.251034: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:29.289712: I tensorflow/core/grappler/devices.cc:55] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 0
2020-07-10 01:03:29.352846: I tensorflow/core/grappler/clusters/single_machine.cc:356] Starting new session
2020-07-10 01:03:29.446887: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:29.477382: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:00:00.0 name: NVIDIA Tegra X1 computeCapability: 5.3
coreClock: 0.9216GHz coreCount: 1 deviceMemorySize: 3.87GiB deviceMemoryBandwidth: 194.55MiB/s
2020-07-10 01:03:29.593908: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-07-10 01:03:29.669517: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-07-10 01:03:29.905311: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-07-10 01:03:29.924776: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-07-10 01:03:29.948337: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-07-10 01:03:29.975708: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-07-10 01:03:30.008204: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.8
2020-07-10 01:03:30.009809: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:30.011883: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:30.012984: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2020-07-10 01:03:30.029220: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-07-10 01:03:30.029934: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]      0
2020-07-10 01:03:30.030516: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0:   N
2020-07-10 01:03:30.033389: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:30.035096: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-07-10 01:03:30.035942: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2048 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X1, pci bus id: 0000:00:00.0, compute capability: 5.3)
2020-07-10 01:03:30.337734: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:841] Optimization results for grappler item: graph_to_optimize
2020-07-10 01:03:30.337870: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:843]   function_optimizer: Graph size after: 12 nodes (9), 12 edges (10), time = 32.086ms.
2020-07-10 01:03:30.337929: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:843]   function_optimizer: Graph size after: 12 nodes (0), 12 edges (0), time = 3.446ms.
2020-07-10 01:03:30.337978: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:841] Optimization results for grappler item: __inference_TRTEngineOp_0_native_segment_23
2020-07-10 01:03:30.338027: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:843]   function_optimizer: function_optimizer did nothing. time = 0.004ms.
2020-07-10 01:03:30.338075: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:843]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2020-07-10 01:03:31.141904: I tensorflow/compiler/tf2tensorrt/kernels/trt_engine_op.cc:736] Building a new TensorRT engine for PartitionedCall/TRTEngineOp_0 with input shapes: [[100,28,28,1]]
2020-07-10 01:03:31.142162: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libnvinfer.so.7
2020-07-10 01:03:31.252899: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libnvinfer_plugin.so.7
(100, 10) (100,)
Accuracy of predictions = 89.00 %
Finished inference
Time taken (total) = 70.295 s
Time taken (inference) = 32.325 s