when ran this command “./trtexec --onnx=/home/jetson/my_apps/my_pigs/best.onnx”
output message like this:
[12/06/2022-19:43:03] [I] === Model Options ===
[12/06/2022-19:43:03] [I] Format: ONNX
[12/06/2022-19:43:03] [I] Model: /home/jetson/my_apps/my_pigs/best.onnx
[12/06/2022-19:43:03] [I] Output:
[12/06/2022-19:43:03] [I] === Build Options ===
[12/06/2022-19:43:03] [I] Max batch: explicit batch
[12/06/2022-19:43:03] [I] Workspace: 16 MiB
[12/06/2022-19:43:03] [I] minTiming: 1
[12/06/2022-19:43:03] [I] avgTiming: 8
[12/06/2022-19:43:03] [I] Precision: FP32
[12/06/2022-19:43:03] [I] Calibration:
[12/06/2022-19:43:03] [I] Refit: Disabled
[12/06/2022-19:43:03] [I] Sparsity: Disabled
[12/06/2022-19:43:03] [I] Safe mode: Disabled
[12/06/2022-19:43:03] [I] DirectIO mode: Disabled
[12/06/2022-19:43:03] [I] Restricted mode: Disabled
[12/06/2022-19:43:03] [I] Save engine:
[12/06/2022-19:43:03] [I] Load engine:
[12/06/2022-19:43:03] [I] Profiling verbosity: 0
[12/06/2022-19:43:03] [I] Tactic sources: Using default tactic sources
[12/06/2022-19:43:03] [I] timingCacheMode: local
[12/06/2022-19:43:03] [I] timingCacheFile:
[12/06/2022-19:43:03] [I] Input(s)s format: fp32:CHW
[12/06/2022-19:43:03] [I] Output(s)s format: fp32:CHW
[12/06/2022-19:43:03] [I] Input build shapes: model
[12/06/2022-19:43:03] [I] Input calibration shapes: model
[12/06/2022-19:43:03] [I] === System Options ===
[12/06/2022-19:43:03] [I] Device: 0
[12/06/2022-19:43:03] [I] DLACore:
[12/06/2022-19:43:03] [I] Plugins:
[12/06/2022-19:43:03] [I] === Inference Options ===
[12/06/2022-19:43:03] [I] Batch: Explicit
[12/06/2022-19:43:03] [I] Input inference shapes: model
[12/06/2022-19:43:03] [I] Iterations: 10
[12/06/2022-19:43:03] [I] Duration: 3s (+ 200ms warm up)
[12/06/2022-19:43:03] [I] Sleep time: 0ms
[12/06/2022-19:43:03] [I] Idle time: 0ms
[12/06/2022-19:43:03] [I] Streams: 1
[12/06/2022-19:43:03] [I] ExposeDMA: Disabled
[12/06/2022-19:43:03] [I] Data transfers: Enabled
[12/06/2022-19:43:03] [I] Spin-wait: Disabled
[12/06/2022-19:43:03] [I] Multithreading: Disabled
[12/06/2022-19:43:03] [I] CUDA Graph: Disabled
[12/06/2022-19:43:03] [I] Separate profiling: Disabled
[12/06/2022-19:43:03] [I] Time Deserialize: Disabled
[12/06/2022-19:43:03] [I] Time Refit: Disabled
[12/06/2022-19:43:03] [I] Skip inference: Disabled
[12/06/2022-19:43:03] [I] Inputs:
[12/06/2022-19:43:03] [I] === Reporting Options ===
[12/06/2022-19:43:03] [I] Verbose: Disabled
[12/06/2022-19:43:03] [I] Averages: 10 inferences
[12/06/2022-19:43:03] [I] Percentile: 99
[12/06/2022-19:43:03] [I] Dump refittable layers:Disabled
[12/06/2022-19:43:03] [I] Dump output: Disabled
[12/06/2022-19:43:03] [I] Profile: Disabled
[12/06/2022-19:43:03] [I] Export timing to JSON file:
[12/06/2022-19:43:03] [I] Export output to JSON file:
[12/06/2022-19:43:03] [I] Export profile to JSON file:
[12/06/2022-19:43:03] [I]
[12/06/2022-19:43:03] [I] === Device Information ===
[12/06/2022-19:43:03] [I] Selected Device: Xavier
[12/06/2022-19:43:03] [I] Compute Capability: 7.2
[12/06/2022-19:43:03] [I] SMs: 6
[12/06/2022-19:43:03] [I] Compute Clock Rate: 1.109 GHz
[12/06/2022-19:43:03] [I] Device Global Memory: 7767 MiB
[12/06/2022-19:43:03] [I] Shared Memory per SM: 96 KiB
[12/06/2022-19:43:03] [I] Memory Bus Width: 256 bits (ECC disabled)
[12/06/2022-19:43:03] [I] Memory Clock Rate: 1.109 GHz
[12/06/2022-19:43:03] [I]
[12/06/2022-19:43:03] [I] TensorRT version: 8.2.1
[12/06/2022-19:43:05] [I] [TRT] [MemUsageChange] Init CUDA: CPU +362, GPU +0, now: CPU 381, GPU 4261 (MiB)
[12/06/2022-19:43:05] [I] [TRT] [MemUsageSnapshot] Begin constructing builder kernel library: CPU 381 MiB, GPU 4261 MiB
[12/06/2022-19:43:06] [I] [TRT] [MemUsageSnapshot] End constructing builder kernel library: CPU 486 MiB, GPU 4367 MiB
[12/06/2022-19:43:06] [I] Start parsing network model
[12/06/2022-19:43:06] [I] [TRT] ----------------------------------------------------------------
[12/06/2022-19:43:06] [I] [TRT] Input filename: /home/jetson/my_apps/my_pigs/best.onnx
[12/06/2022-19:43:06] [I] [TRT] ONNX IR version: 0.0.7
[12/06/2022-19:43:06] [I] [TRT] Opset version: 12
[12/06/2022-19:43:06] [I] [TRT] Producer name: pytorch
[12/06/2022-19:43:06] [I] [TRT] Producer version: 1.13.0
[12/06/2022-19:43:06] [I] [TRT] Domain:
[12/06/2022-19:43:06] [I] [TRT] Model version: 0
[12/06/2022-19:43:06] [I] [TRT] Doc string:
[12/06/2022-19:43:06] [I] [TRT] ----------------------------------------------------------------
[12/06/2022-19:43:06] [W] [TRT] onnx2trt_utils.cpp:366: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[12/06/2022-19:43:06] [I] Finish parsing network model
[12/06/2022-19:43:06] [I] [TRT] ---------- Layers Running on DLA ----------
[12/06/2022-19:43:06] [I] [TRT] ---------- Layers Running on GPU ----------
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.0/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.0/act/Sigmoid), /model.0/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.1/act/Sigmoid), /model.1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.2/cv1/conv/Conv || /model.2/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.2/cv1/act/Sigmoid), /model.2/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.2/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.2/m/m.0/cv1/act/Sigmoid), /model.2/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.2/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.2/m/m.0/cv2/act/Sigmoid), /model.2/m/m.0/cv2/act/Mul), /model.2/m/m.0/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.2/cv2/act/Sigmoid), /model.2/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.2/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.2/cv3/act/Sigmoid), /model.2/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.3/act/Sigmoid), /model.3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.4/cv1/conv/Conv || /model.4/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.4/cv1/act/Sigmoid), /model.4/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.4/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.4/m/m.0/cv1/act/Sigmoid), /model.4/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.4/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.4/m/m.0/cv2/act/Sigmoid), /model.4/m/m.0/cv2/act/Mul), /model.4/m/m.0/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.4/m/m.1/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.4/m/m.1/cv1/act/Sigmoid), /model.4/m/m.1/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.4/m/m.1/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.4/m/m.1/cv2/act/Sigmoid), /model.4/m/m.1/cv2/act/Mul), /model.4/m/m.1/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.4/cv2/act/Sigmoid), /model.4/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.4/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.4/cv3/act/Sigmoid), /model.4/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.5/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.5/act/Sigmoid), /model.5/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/cv1/conv/Conv || /model.6/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.6/cv1/act/Sigmoid), /model.6/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.6/m/m.0/cv1/act/Sigmoid), /model.6/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.6/m/m.0/cv2/act/Sigmoid), /model.6/m/m.0/cv2/act/Mul), /model.6/m/m.0/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/m/m.1/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.6/m/m.1/cv1/act/Sigmoid), /model.6/m/m.1/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/m/m.1/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.6/m/m.1/cv2/act/Sigmoid), /model.6/m/m.1/cv2/act/Mul), /model.6/m/m.1/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/m/m.2/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.6/m/m.2/cv1/act/Sigmoid), /model.6/m/m.2/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/m/m.2/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.6/m/m.2/cv2/act/Sigmoid), /model.6/m/m.2/cv2/act/Mul), /model.6/m/m.2/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.6/cv2/act/Sigmoid), /model.6/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.6/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.6/cv3/act/Sigmoid), /model.6/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.7/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.7/act/Sigmoid), /model.7/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.8/cv1/conv/Conv || /model.8/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.8/cv1/act/Sigmoid), /model.8/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.8/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.8/m/m.0/cv1/act/Sigmoid), /model.8/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.8/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(PWN(/model.8/m/m.0/cv2/act/Sigmoid), /model.8/m/m.0/cv2/act/Mul), /model.8/m/m.0/Add)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.8/cv2/act/Sigmoid), /model.8/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.8/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.8/cv3/act/Sigmoid), /model.8/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.9/cv1/act/Sigmoid), /model.9/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/m/MaxPool
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/m_1/MaxPool
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/m_2/MaxPool
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/cv1/act/Mul_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/m/MaxPool_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/m_1/MaxPool_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/m_2/MaxPool_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.9/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.9/cv2/act/Sigmoid), /model.9/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.10/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.10/act/Sigmoid), /model.10/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.11/Resize
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.11/Resize_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.13/cv1/conv/Conv || /model.13/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.13/cv1/act/Sigmoid), /model.13/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.13/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.13/m/m.0/cv1/act/Sigmoid), /model.13/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.13/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.13/m/m.0/cv2/act/Sigmoid), /model.13/m/m.0/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.13/cv2/act/Sigmoid), /model.13/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.13/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.13/cv3/act/Sigmoid), /model.13/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.14/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.14/act/Sigmoid), /model.14/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.15/Resize
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.15/Resize_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.17/cv1/conv/Conv || /model.17/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.17/cv1/act/Sigmoid), /model.17/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.17/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.17/m/m.0/cv1/act/Sigmoid), /model.17/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.17/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.17/m/m.0/cv2/act/Sigmoid), /model.17/m/m.0/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.17/cv2/act/Sigmoid), /model.17/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.17/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.17/cv3/act/Sigmoid), /model.17/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.18/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.18/act/Sigmoid), /model.18/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.14/act/Mul_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.20/cv1/conv/Conv || /model.20/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.20/cv1/act/Sigmoid), /model.20/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.20/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.20/m/m.0/cv1/act/Sigmoid), /model.20/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.20/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.20/m/m.0/cv2/act/Sigmoid), /model.20/m/m.0/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.20/cv2/act/Sigmoid), /model.20/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.20/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.20/cv3/act/Sigmoid), /model.20/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.21/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.21/act/Sigmoid), /model.21/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.10/act/Mul_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.23/cv1/conv/Conv || /model.23/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.23/cv1/act/Sigmoid), /model.23/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.23/m/m.0/cv1/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.23/m/m.0/cv1/act/Sigmoid), /model.23/m/m.0/cv1/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.23/m/m.0/cv2/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.23/m/m.0/cv2/act/Sigmoid), /model.23/m/m.0/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.23/cv2/act/Sigmoid), /model.23/cv2/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.23/cv3/conv/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.23/cv3/act/Sigmoid), /model.23/cv3/act/Mul)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/m.0/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape + /model.24/Transpose
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(/model.24/Sigmoid)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_1
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Constant_2_output_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.24/Constant_1_output_0 + (Unnamed Layer* 204) [Shuffle] + /model.24/Mul, /model.24/Add), /model.24/Constant_3_output_0 + (Unnamed Layer* 209) [Shuffle] + /model.24/Mul_1)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Constant_6_output_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.24/Constant_5_output_0 + (Unnamed Layer* 215) [Shuffle], PWN(/model.24/Constant_4_output_0 + (Unnamed Layer* 212) [Shuffle] + /model.24/Mul_2, /model.24/Pow)), /model.24/Mul_3)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Mul_1_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Mul_3_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_output_2 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_1
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/m.1/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_2 + /model.24/Transpose_1
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(/model.24/Sigmoid_1)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_1_2
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_1_3
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_1_4
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Constant_10_output_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.24/Constant_9_output_0 + (Unnamed Layer* 229) [Shuffle] + /model.24/Mul_4, /model.24/Add_1), /model.24/Constant_11_output_0 + (Unnamed Layer* 234) [Shuffle] + /model.24/Mul_5)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Constant_14_output_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.24/Constant_13_output_0 + (Unnamed Layer* 240) [Shuffle], PWN(/model.24/Constant_12_output_0 + (Unnamed Layer* 237) [Shuffle] + /model.24/Mul_6, /model.24/Pow_1)), /model.24/Mul_7)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Mul_5_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Mul_7_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_1_output_2 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_3
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/m.2/Conv
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_4 + /model.24/Transpose_2
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(/model.24/Sigmoid_2)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_2
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_2_5
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_2_6
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Constant_18_output_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.24/Constant_17_output_0 + (Unnamed Layer* 254) [Shuffle] + /model.24/Mul_8, /model.24/Add_2), /model.24/Constant_19_output_0 + (Unnamed Layer* 259) [Shuffle] + /model.24/Mul_9)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Constant_22_output_0
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] PWN(PWN(/model.24/Constant_21_output_0 + (Unnamed Layer* 265) [Shuffle], PWN(/model.24/Constant_20_output_0 + (Unnamed Layer* 262) [Shuffle] + /model.24/Mul_10, /model.24/Pow_2)), /model.24/Mul_11)
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Mul_9_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Mul_11_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Split_2_output_2 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_5
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_1_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_3_output_0 copy
[12/06/2022-19:43:06] [I] [TRT] [GpuLayer] /model.24/Reshape_5_output_0 copy
[12/06/2022-19:43:07] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +226, GPU +204, now: CPU 744, GPU 4656 (MiB)
[12/06/2022-19:43:09] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +307, GPU +308, now: CPU 1051, GPU 4964 (MiB)
[12/06/2022-19:43:09] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
[12/06/2022-19:43:32] [I] [TRT] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
[12/06/2022-19:50:54] [I] [TRT] Detected 1 inputs and 4 output network tensors.
[12/06/2022-19:50:54] [I] [TRT] Total Host Persistent Memory: 149104
[12/06/2022-19:50:54] [I] [TRT] Total Device Persistent Memory: 37168640
[12/06/2022-19:50:54] [I] [TRT] Total Scratch Memory: 0
[12/06/2022-19:50:54] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 7 MiB, GPU 105 MiB
[12/06/2022-19:50:54] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 52.9292ms to assign 9 blocks to 135 nodes requiring 35635202 bytes.
[12/06/2022-19:50:54] [I] [TRT] Total Activation Memory: 35635202
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +0, now: CPU 1523, GPU 5952 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1523, GPU 5952 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +3, GPU +64, now: CPU 3, GPU 64 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 1555, GPU 5996 (MiB)
[12/06/2022-19:50:54] [I] [TRT] Loaded engine size: 43 MiB
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +0, now: CPU 1563, GPU 5996 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 1563, GPU 5996 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +42, now: CPU 0, GPU 42 (MiB)
[12/06/2022-19:50:54] [I] Engine built in 470.922 sec.
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +0, now: CPU 1386, GPU 5953 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +0, now: CPU 1387, GPU 5953 (MiB)
[12/06/2022-19:50:54] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +70, now: CPU 0, GPU 112 (MiB)
[12/06/2022-19:50:54] [I] Using random values for input images
[12/06/2022-19:50:54] [I] Created input binding for images with dimensions 1x3x640x640
[12/06/2022-19:50:54] [I] Using random values for output output0
[12/06/2022-19:50:54] [I] Created output binding for output0 with dimensions 1x25200x6
[12/06/2022-19:50:54] [I] Starting inference
[12/06/2022-19:50:58] [I] Warmup completed 4 queries over 200 ms
[12/06/2022-19:50:58] [I] Timing trace has 60 queries over 3.05645 s
[12/06/2022-19:50:58] [I]
[12/06/2022-19:50:58] [I] === Trace details ===
[12/06/2022-19:50:58] [I] Trace averages of 10 runs:
[12/06/2022-19:50:58] [I] Average on 10 runs - GPU latency: 50.612 ms - Host latency: 51.0146 ms (end to end 51.0242 ms, enqueue 3.02969 ms)
[12/06/2022-19:50:58] [I] Average on 10 runs - GPU latency: 50.5397 ms - Host latency: 50.9419 ms (end to end 50.9501 ms, enqueue 2.99625 ms)
[12/06/2022-19:50:58] [I] Average on 10 runs - GPU latency: 50.4972 ms - Host latency: 50.8993 ms (end to end 50.9079 ms, enqueue 2.81522 ms)
[12/06/2022-19:50:58] [I] Average on 10 runs - GPU latency: 50.3701 ms - Host latency: 50.7717 ms (end to end 50.7817 ms, enqueue 2.67208 ms)
[12/06/2022-19:50:58] [I] Average on 10 runs - GPU latency: 50.8235 ms - Host latency: 51.2253 ms (end to end 51.2347 ms, enqueue 2.71804 ms)
[12/06/2022-19:50:58] [I] Average on 10 runs - GPU latency: 50.3218 ms - Host latency: 50.7272 ms (end to end 50.7374 ms, enqueue 2.70623 ms)
[12/06/2022-19:50:58] [I]
[12/06/2022-19:50:58] [I] === Performance summary ===
[12/06/2022-19:50:58] [I] Throughput: 19.6306 qps
[12/06/2022-19:50:58] [I] Latency: min = 50.5018 ms, max = 53.2183 ms, mean = 50.93 ms, median = 50.8052 ms, percentile(99%) = 53.2183 ms
[12/06/2022-19:50:58] [I] End-to-End Host Latency: min = 50.5098 ms, max = 53.2253 ms, mean = 50.9393 ms, median = 50.8172 ms, percentile(99%) = 53.2253 ms
[12/06/2022-19:50:58] [I] Enqueue Time: min = 2.56158 ms, max = 3.26117 ms, mean = 2.82292 ms, median = 2.76025 ms, percentile(99%) = 3.26117 ms
[12/06/2022-19:50:58] [I] H2D Latency: min = 0.346558 ms, max = 0.391602 ms, mean = 0.348452 ms, median = 0.347412 ms, percentile(99%) = 0.391602 ms
[12/06/2022-19:50:58] [I] GPU Compute Time: min = 50.0991 ms, max = 52.8159 ms, mean = 50.5274 ms, median = 50.4038 ms, percentile(99%) = 52.8159 ms
[12/06/2022-19:50:58] [I] D2H Latency: min = 0.0483398 ms, max = 0.0568542 ms, mean = 0.0541463 ms, median = 0.0545349 ms, percentile(99%) = 0.0568542 ms
[12/06/2022-19:50:58] [I] Total Host Walltime: 3.05645 s
[12/06/2022-19:50:58] [I] Total GPU Compute Time: 3.03164 s
[12/06/2022-19:50:58] [I] Explanations of the performance metrics are printed in the verbose logs.