error message | Notion

root@dc0b5a46e808:/edge-inference/CNN# python3 ic_inference.py --batchsize=1 --model=mobilenet --case=trt --quantization=FP32 --engines=1 --img_size=224
2022-09-19 05:50:13.423247: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.10.2
2022-09-19 05:50:16.588393: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcuda.so.1
2022-09-19 05:50:16.593101: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:16.593257: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1734] Found device 0 with properties: 
pciBusID: 0000:00:00.0 name: Xavier computeCapability: 7.2
coreClock: 1.377GHz coreCount: 8 deviceMemorySize: 31.18GiB deviceMemoryBandwidth: 82.08GiB/s
2022-09-19 05:50:16.593337: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.10.2
2022-09-19 05:50:16.596101: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublas.so.10
2022-09-19 05:50:16.596245: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublasLt.so.10
2022-09-19 05:50:16.598520: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcufft.so.10
2022-09-19 05:50:16.599049: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcurand.so.10
2022-09-19 05:50:16.601640: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcusolver.so.10
2022-09-19 05:50:16.603756: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcusparse.so.10
2022-09-19 05:50:16.604253: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudnn.so.8
2022-09-19 05:50:16.604482: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:16.604689: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:16.604774: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1872] Adding visible gpu devices: 0
1: svmem(total=33479544832, available=29507403776, percent=11.9, used=7685345280, free=22936342528, active=3399487488, inactive=1070657536, buffers=79306752, cached=2778550272, shared=58093568, slab=334544896)
2: svmem(total=33479544832, available=29507403776, percent=11.9, used=7685345280, free=22936342528, active=3399487488, inactive=1070657536, buffers=79306752, cached=2778550272, shared=58093568, slab=334544896)
2022-09-19 05:50:16.670796: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:16.670980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1734] Found device 0 with properties: 
pciBusID: 0000:00:00.0 name: Xavier computeCapability: 7.2
coreClock: 1.377GHz coreCount: 8 deviceMemorySize: 31.18GiB deviceMemoryBandwidth: 82.08GiB/s
2022-09-19 05:50:16.671200: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:16.671457: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:16.671541: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1872] Adding visible gpu devices: 0
2022-09-19 05:50:16.671642: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.10.2
2022-09-19 05:50:18.172855: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-09-19 05:50:18.172939: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]      0 
2022-09-19 05:50:18.172974: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0:   N 
2022-09-19 05:50:18.173235: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:18.173488: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:18.173712: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:50:18.173827: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 184 MB memory) -> physical GPU (device: 0, name: Xavier, pci bus id: 0000:00:00.0, compute capability: 7.2)
Downloading data from <https://storage.googleapis.com/tensorflow/keras-applications/mobilenet/mobilenet_1_0_224_tf.h5>
17227776/17225924 [==============================] - 2s 0us/step
Downloading data from <https://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.0_224.h5>
14540800/14536120 [==============================] - 1s 0us/step
Downloading data from <https://storage.googleapis.com/tensorflow/keras-applications/inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels.h5>
96116736/96112376 [==============================] - 9s 0us/step
WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.
2022-09-19 05:50:56.357534: W tensorflow/python/util/util.cc:348] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
2022-09-19 05:51:28.148944: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libnvinfer.so.8
2022-09-19 05:51:55.895836: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:55.896002: I tensorflow/core/grappler/devices.cc:69] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1
2022-09-19 05:51:55.896299: I tensorflow/core/grappler/clusters/single_machine.cc:357] Starting new session
2022-09-19 05:51:55.897144: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:55.897291: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1734] Found device 0 with properties: 
pciBusID: 0000:00:00.0 name: Xavier computeCapability: 7.2
coreClock: 1.377GHz coreCount: 8 deviceMemorySize: 31.18GiB deviceMemoryBandwidth: 82.08GiB/s
2022-09-19 05:51:55.897537: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:55.897746: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:55.897844: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1872] Adding visible gpu devices: 0
2022-09-19 05:51:55.897909: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-09-19 05:51:55.897933: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]      0 
2022-09-19 05:51:55.897951: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0:   N 
2022-09-19 05:51:55.898159: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:55.898483: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:55.898609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 184 MB memory) -> physical GPU (device: 0, name: Xavier, pci bus id: 0000:00:00.0, compute capability: 7.2)
2022-09-19 05:51:55.899955: I tensorflow/core/platform/profile_utils/cpu_utils.cc:114] CPU Frequency: 31250000 Hz
2022-09-19 05:51:56.140341: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:1171] Optimization results for grappler item: graph_to_optimize
  function_optimizer: Graph size after: 583 nodes (443), 832 edges (692), time = 27.776ms.
  function_optimizer: function_optimizer did nothing. time = 0.428ms.

2022-09-19 05:51:58.591230: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:58.591476: I tensorflow/core/grappler/devices.cc:69] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1
2022-09-19 05:51:58.591678: I tensorflow/core/grappler/clusters/single_machine.cc:357] Starting new session
2022-09-19 05:51:58.592290: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:58.592460: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1734] Found device 0 with properties: 
pciBusID: 0000:00:00.0 name: Xavier computeCapability: 7.2
coreClock: 1.377GHz coreCount: 8 deviceMemorySize: 31.18GiB deviceMemoryBandwidth: 82.08GiB/s
2022-09-19 05:51:58.592686: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:58.592890: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:58.592972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1872] Adding visible gpu devices: 0
2022-09-19 05:51:58.593042: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-09-19 05:51:58.593073: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]      0 
2022-09-19 05:51:58.593095: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0:   N 
2022-09-19 05:51:58.593277: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:58.593539: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1001] ARM64 does not support NUMA - returning NUMA node zero
2022-09-19 05:51:58.593676: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 184 MB memory) -> physical GPU (device: 0, name: Xavier, pci bus id: 0000:00:00.0, compute capability: 7.2)
2022-09-19 05:51:59.118600: I tensorflow/compiler/tf2tensorrt/segment/segment.cc:790] There are 14 ops of 8 different types in the graph that are not converted to TensorRT: Identity, Placeholder, NoOp, Pack, Shape, DataFormatVecPermute, StridedSlice, Reshape, (For more information see <https://docs.nvidia.com/deeplearning/frameworks/tf-trt-user-guide/index.html#supported-ops>).
2022-09-19 05:51:59.136814: I tensorflow/compiler/tf2tensorrt/convert/convert_graph.cc:759] Number of TensorRT candidate segments: 2
2022-09-19 05:51:59.171113: I tensorflow/compiler/tf2tensorrt/convert/convert_graph.cc:853] Replaced segment 0 consisting of 229 nodes by TRTEngineOp_0_0.
2022-09-19 05:51:59.172244: I tensorflow/compiler/tf2tensorrt/convert/convert_graph.cc:853] Replaced segment 1 consisting of 9 nodes by StatefulPartitionedCall/mobilenet_1.00_224/TRTEngineOp_0_1.
2022-09-19 05:51:59.343063: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:1171] Optimization results for grappler item: tf_graph
  constant_folding: Graph size after: 256 nodes (-274), 531 edges (-274), time = 152.719ms.
  layout: Graph size after: 268 nodes (12), 543 edges (12), time = 62.029ms.
  constant_folding: Graph size after: 263 nodes (-5), 538 edges (-5), time = 37.714ms.
  TensorRTOptimizer: Graph size after: 27 nodes (-236), 28 edges (-510), time = 102.967ms.
  constant_folding: Graph size after: 27 nodes (0), 28 edges (0), time = 5.256ms.
Optimization results for grappler item: StatefulPartitionedCall/mobilenet_1.00_224/TRTEngineOp_0_1_native_segment
  constant_folding: Graph size after: 12 nodes (0), 11 edges (0), time = 3.451ms.
  layout: Graph size after: 12 nodes (0), 11 edges (0), time = 5.278ms.
  constant_folding: Graph size after: 12 nodes (0), 11 edges (0), time = 3.417ms.
  TensorRTOptimizer: Graph size after: 12 nodes (0), 11 edges (0), time = 0.532ms.
  constant_folding: Graph size after: 12 nodes (0), 11 edges (0), time = 3.357ms.
Optimization results for grappler item: TRTEngineOp_0_0_native_segment
  constant_folding: Graph size after: 231 nodes (0), 230 edges (0), time = 18.51ms.
  layout: Graph size after: 231 nodes (0), 230 edges (0), time = 28.146ms.
  constant_folding: Graph size after: 231 nodes (0), 230 edges (0), time = 19.408ms.
  TensorRTOptimizer: Graph size after: 231 nodes (0), 230 edges (0), time = 2.993ms.
  constant_folding: Graph size after: 231 nodes (0), 230 edges (0), time = 19.63ms.

2022-09-19 05:53:41.049492: W tensorflow/core/framework/op_kernel.cc:1767] OP_REQUIRES failed at trt_engine_resource_ops.cc:193 : Not found: Container TF-TRT does not exist. (Could not find resource: TF-TRT/TRTEngineOp_0_0)
2022-09-19 05:53:41.050167: W tensorflow/core/framework/op_kernel.cc:1767] OP_REQUIRES failed at trt_engine_resource_ops.cc:193 : Not found: Container TF-TRT does not exist. (Could not find resource: TF-TRT/TRTEngineOp_0_1)
2022-09-19 05:56:08.019001: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:176] None of the MLIR Optimization Passes are enabled (registered 2)
2022-09-19 05:56:08.376198: I tensorflow/compiler/tf2tensorrt/common/utils.cc:58] Linked TensorRT version: 8.0.1
2022-09-19 05:56:08.377095: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libnvinfer.so.8
2022-09-19 05:56:08.377406: I tensorflow/compiler/tf2tensorrt/common/utils.cc:60] Loaded TensorRT version: 8.2.1
2022-09-19 05:56:08.381209: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libnvinfer_plugin.so.8
Segmentation fault (core dumped)