&&&& RUNNING TensorRT.trtexec [TensorRT v8502] # ./trtexec --onnx=yolov8n.onnx --saveEngine=yolov8n.trt --minShapes=images:1x3x640x640 --optShapes=images:2x3x640x640 --maxShapes=images:4x3x640x640
[02/21/2024-09:53:37] [I] === Model Options ===
[02/21/2024-09:53:37] [I] Format: ONNX
[02/21/2024-09:53:37] [I] Model: yolov8n.onnx
[02/21/2024-09:53:37] [I] Output:
[02/21/2024-09:53:37] [I] === Build Options ===
[02/21/2024-09:53:37] [I] Max batch: explicit batch
[02/21/2024-09:53:37] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
[02/21/2024-09:53:37] [I] minTiming: 1
[02/21/2024-09:53:37] [I] avgTiming: 8
[02/21/2024-09:53:37] [I] Precision: FP32
[02/21/2024-09:53:37] [I] LayerPrecisions: 
[02/21/2024-09:53:37] [I] Calibration: 
[02/21/2024-09:53:37] [I] Refit: Disabled
[02/21/2024-09:53:37] [I] Sparsity: Disabled
[02/21/2024-09:53:37] [I] Safe mode: Disabled
[02/21/2024-09:53:37] [I] DirectIO mode: Disabled
[02/21/2024-09:53:37] [I] Restricted mode: Disabled
[02/21/2024-09:53:37] [I] Build only: Disabled
[02/21/2024-09:53:37] [I] Save engine: yolov8n.trt
[02/21/2024-09:53:37] [I] Load engine: 
[02/21/2024-09:53:37] [I] Profiling verbosity: 0
[02/21/2024-09:53:37] [I] Tactic sources: Using default tactic sources
[02/21/2024-09:53:37] [I] timingCacheMode: local
[02/21/2024-09:53:37] [I] timingCacheFile: 
[02/21/2024-09:53:37] [I] Heuristic: Disabled
[02/21/2024-09:53:37] [I] Preview Features: Use default preview flags.
[02/21/2024-09:53:37] [I] Input(s)s format: fp32:CHW
[02/21/2024-09:53:37] [I] Output(s)s format: fp32:CHW
[02/21/2024-09:53:37] [I] Input build shape: images=1x3x640x640+2x3x640x640+4x3x640x640
[02/21/2024-09:53:37] [I] Input calibration shapes: model
[02/21/2024-09:53:37] [I] === System Options ===
[02/21/2024-09:53:37] [I] Device: 0
[02/21/2024-09:53:37] [I] DLACore: 
[02/21/2024-09:53:37] [I] Plugins:
[02/21/2024-09:53:37] [I] === Inference Options ===
[02/21/2024-09:53:37] [I] Batch: Explicit
[02/21/2024-09:53:37] [I] Input inference shape: images=2x3x640x640
[02/21/2024-09:53:37] [I] Iterations: 10
[02/21/2024-09:53:37] [I] Duration: 3s (+ 200ms warm up)
[02/21/2024-09:53:37] [I] Sleep time: 0ms
[02/21/2024-09:53:37] [I] Idle time: 0ms
[02/21/2024-09:53:37] [I] Streams: 1
[02/21/2024-09:53:37] [I] ExposeDMA: Disabled
[02/21/2024-09:53:37] [I] Data transfers: Enabled
[02/21/2024-09:53:37] [I] Spin-wait: Disabled
[02/21/2024-09:53:37] [I] Multithreading: Disabled
[02/21/2024-09:53:37] [I] CUDA Graph: Disabled
[02/21/2024-09:53:37] [I] Separate profiling: Disabled
[02/21/2024-09:53:37] [I] Time Deserialize: Disabled
[02/21/2024-09:53:37] [I] Time Refit: Disabled
[02/21/2024-09:53:37] [I] NVTX verbosity: 0
[02/21/2024-09:53:37] [I] Persistent Cache Ratio: 0
[02/21/2024-09:53:37] [I] Inputs:
[02/21/2024-09:53:37] [I] === Reporting Options ===
[02/21/2024-09:53:37] [I] Verbose: Disabled
[02/21/2024-09:53:37] [I] Averages: 10 inferences
[02/21/2024-09:53:37] [I] Percentiles: 90,95,99
[02/21/2024-09:53:37] [I] Dump refittable layers:Disabled
[02/21/2024-09:53:37] [I] Dump output: Disabled
[02/21/2024-09:53:37] [I] Profile: Disabled
[02/21/2024-09:53:37] [I] Export timing to JSON file: 
[02/21/2024-09:53:37] [I] Export output to JSON file: 
[02/21/2024-09:53:37] [I] Export profile to JSON file: 
[02/21/2024-09:53:37] [I] 
[02/21/2024-09:53:37] [I] === Device Information ===
[02/21/2024-09:53:37] [I] Selected Device: Xavier
[02/21/2024-09:53:37] [I] Compute Capability: 7.2
[02/21/2024-09:53:37] [I] SMs: 6
[02/21/2024-09:53:37] [I] Compute Clock Rate: 1.109 GHz
[02/21/2024-09:53:37] [I] Device Global Memory: 6845 MiB
[02/21/2024-09:53:37] [I] Shared Memory per SM: 96 KiB
[02/21/2024-09:53:37] [I] Memory Bus Width: 256 bits (ECC disabled)
[02/21/2024-09:53:37] [I] Memory Clock Rate: 0.51 GHz
[02/21/2024-09:53:37] [I] 
[02/21/2024-09:53:37] [I] TensorRT version: 8.5.2
[02/21/2024-09:53:38] [I] [TRT] [MemUsageChange] Init CUDA: CPU +187, GPU +0, now: CPU 216, GPU 5068 (MiB)
[02/21/2024-09:53:40] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +106, GPU +153, now: CPU 344, GPU 5236 (MiB)
[02/21/2024-09:53:40] [I] Start parsing network model
[02/21/2024-09:53:40] [I] [TRT] ----------------------------------------------------------------
[02/21/2024-09:53:40] [I] [TRT] Input filename:   yolov8n.onnx
[02/21/2024-09:53:40] [I] [TRT] ONNX IR version:  0.0.6
[02/21/2024-09:53:40] [I] [TRT] Opset version:    12
[02/21/2024-09:53:40] [I] [TRT] Producer name:    pytorch
[02/21/2024-09:53:40] [I] [TRT] Producer version: 1.9
[02/21/2024-09:53:40] [I] [TRT] Domain:           
[02/21/2024-09:53:40] [I] [TRT] Model version:    0
[02/21/2024-09:53:40] [I] [TRT] Doc string:       
[02/21/2024-09:53:40] [I] [TRT] ----------------------------------------------------------------
[02/21/2024-09:53:40] [W] [TRT] onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[02/21/2024-09:53:42] [I] Finish parsing network model
[02/21/2024-09:53:42] [W] [TRT] DLA requests all profiles have same min, max, and opt value. All dla layers are falling back to GPU
[02/21/2024-09:53:42] [I] [TRT] ---------- Layers Running on DLA ----------
[02/21/2024-09:53:42] [I] [TRT] ---------- Layers Running on GPU ----------
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 366
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 366_clone_1
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 366_clone_2
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 366_clone_3
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 366_clone_4
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 366_clone_5
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 367 + (Unnamed Layer* 303) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 367_clone_1 + (Unnamed Layer* 316) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 367_clone_2 + (Unnamed Layer* 378) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 367_clone_3 + (Unnamed Layer* 390) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 367_clone_4 + (Unnamed Layer* 451) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: 367_clone_5 + (Unnamed Layer* 463) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 362) [Constant] + (Unnamed Layer* 363) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 435) [Constant] + (Unnamed Layer* 436) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONSTANT: (Unnamed Layer* 508) [Constant] + (Unnamed Layer* 509) [Shuffle]
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_0
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_1), Mul_2)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_3
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_4), Mul_5)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_6
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_7), Mul_8)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_10
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_11), Mul_12)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_13
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(PWN(Sigmoid_14), Mul_15), Add_16)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 137 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 138 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_18
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_19), Mul_20)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_21
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_22), Mul_23)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_24
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_25), Mul_26)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_28
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_29), Mul_30)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_31
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(PWN(Sigmoid_32), Mul_33), Add_34)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_35
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_36), Mul_37)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_38
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(PWN(Sigmoid_39), Mul_40), Add_41)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 156 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 157 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 164 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_43
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_44), Mul_45)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_46
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_47), Mul_48)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_49
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_50), Mul_51)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_53
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_54), Mul_55)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_56
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(PWN(Sigmoid_57), Mul_58), Add_59)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_60
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_61), Mul_62)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_63
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(PWN(Sigmoid_64), Mul_65), Add_66)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 182 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 183 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 190 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_68
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_69), Mul_70)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_71
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_72), Mul_73)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_74
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_75), Mul_76)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_78
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_79), Mul_80)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_81
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(PWN(Sigmoid_82), Mul_83), Add_84)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 208 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 209 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_86
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_87), Mul_88)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_89
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_90), Mul_91)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POOLING: MaxPool_92
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POOLING: MaxPool_93
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POOLING: MaxPool_94
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 223 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 224 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 225 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_96
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_97), Mul_98)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] RESIZE: Resize_100
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 235 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_102
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_103), Mul_104)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_106
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_107), Mul_108)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_109
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_110), Mul_111)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 240 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 241 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_113
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_114), Mul_115)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] RESIZE: Resize_117
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 256 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_119
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_120), Mul_121)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_123
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_124), Mul_125)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_126
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_127), Mul_128)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 261 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 262 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_130
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_131), Mul_132)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_133
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_172 || Conv_179
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_134), Mul_135)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_173), Mul_174)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_180), Mul_181)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 251 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_175
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_182
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_137
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_176), Mul_177)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_183), Mul_184)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_138), Mul_139)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_178
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_185
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_349
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: Reshape_349_copy_output
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_141
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_142), Mul_143)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] SLICE: ConstantOfShape_258
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_144
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_145), Mul_146)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 280 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] COPY: 281 copy
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] FILL: Range_232
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] FILL: Range_226
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_148
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(369_clone_1 + (Unnamed Layer* 317) [Shuffle], Add_234)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(369 + (Unnamed Layer* 305) [Shuffle], Add_228)
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_244
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_248
[02/21/2024-09:53:42] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_149), Mul_150)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_151
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_187 || Conv_194
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_152), Mul_153)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_188), Mul_189)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_195), Mul_196)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 230 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_190
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_197
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: Expand_245
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: Expand_249
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_155
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_191), Mul_192)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_198), Mul_199)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_156), Mul_157)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_193
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_200
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Unsqueeze_251
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Unsqueeze_251_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Unsqueeze_250
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_352
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Reshape_352_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 392 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_254
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Reshape_254_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_159
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_160), Mul_161)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: ConstantOfShape_300
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_162
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_163), Mul_164)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 299 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 300 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] FILL: Range_274
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] FILL: Range_268
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_166
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(369_clone_3 + (Unnamed Layer* 391) [Shuffle], Add_276)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(369_clone_2 + (Unnamed Layer* 379) [Shuffle], Add_270)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_286
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_290
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_167), Mul_168)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_202 || Conv_209
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_203), Mul_204)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_210), Mul_211)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_205
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_212
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: Expand_287
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: Expand_291
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_206), Mul_207)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(PWN(Sigmoid_213), Mul_214)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_208
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_215
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Unsqueeze_293
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Unsqueeze_293_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Unsqueeze_292
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_355
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Reshape_355_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 436 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_296
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Reshape_296_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: ConstantOfShape_342
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] FILL: Range_316
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] FILL: Range_310
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(369_clone_5 + (Unnamed Layer* 464) [Shuffle], Add_318)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(369_clone_4 + (Unnamed Layer* 452) [Shuffle], Add_312)
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Transpose_346 + (Unnamed Layer* 638) [Shuffle]
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_367 + Transpose_368
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_328
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_332
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: Expand_329
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SLICE: Expand_333
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: (Unnamed Layer* 554) [Shuffle]
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SOFTMAX: Softmax_369
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: (Unnamed Layer* 556) [Shuffle] + Transpose_370
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Unsqueeze_335
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Unsqueeze_335_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Unsqueeze_334
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 480 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] CONVOLUTION: Conv_371
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_338
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: Reshape_338_copy_output
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Reshape_375
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] SHUFFLE: Transpose_345 + Unsqueeze_376
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] ELEMENTWISE: Sub_391
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] ELEMENTWISE: Add_392
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] ELEMENTWISE: Sub_395
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(Add_393, PWN(583 + (Unnamed Layer* 631) [Shuffle], Div_394))
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] COPY: 563 copy
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] ELEMENTWISE: Mul_397
[02/21/2024-09:53:43] [I] [TRT] [GpuLayer] POINTWISE: PWN(Sigmoid_398)
[02/21/2024-09:53:45] [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +261, GPU +391, now: CPU 622, GPU 5665 (MiB)
[02/21/2024-09:53:45] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +82, GPU -65, now: CPU 704, GPU 5600 (MiB)
[02/21/2024-09:53:45] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
[02/21/2024-10:04:10] [I] [TRT] Total Activation Memory: 7787154944
[02/21/2024-10:04:10] [I] [TRT] Detected 1 inputs and 3 output network tensors.
[02/21/2024-10:04:11] [I] [TRT] Total Host Persistent Memory: 121184
[02/21/2024-10:04:11] [I] [TRT] Total Device Persistent Memory: 1464832
[02/21/2024-10:04:11] [I] [TRT] Total Scratch Memory: 134217728
[02/21/2024-10:04:11] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 6 MiB, GPU 1686 MiB
[02/21/2024-10:04:11] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 190 steps to complete.
[02/21/2024-10:04:11] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 70.2662ms to assign 13 blocks to 190 nodes requiring 185504256 bytes.
[02/21/2024-10:04:11] [I] [TRT] Total Activation Memory: 185504256
[02/21/2024-10:04:11] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 965, GPU 4413 (MiB)
[02/21/2024-10:04:11] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +2, GPU +33, now: CPU 2, GPU 33 (MiB)
[02/21/2024-10:04:11] [E] Saving engine to file failed.
[02/21/2024-10:04:11] [E] Engine set up failed
&&&& FAILED TensorRT.trtexec [TensorRT v8502] # ./trtexec --onnx=yolov8n.onnx --saveEngine=yolov8n.trt --minShapes=images:1x3x640x640 --optShapes=images:2x3x640x640 --maxShapes=images:4x3x640x640