trtexec failure of TensorRT 8.6.1.6 when running trtexec on GPU RTX4090
@zerollzeng is already working on this.
Since Jan 12, 2024.
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
Environment
TensorRT Version:
NVIDIA GPU: RTX 4090
NVIDIA Driver Version: 535.129.03
CUDA Version: 11.8
CUDNN Version: 8.9.6.50
Operating System: ubuntu 22.04
Python Version (if applicable): 3.9
Tensorflow Version (if applicable):
PyTorch Version (if applicable): 1.13
Baremetal or Container (if so, version):
Relevant Files
Model link: https://www.dropbox.com/scl/fi/vzgb4iew1lvj64h6adnjt/model.onnx?rlkey=vqq56hc2t91r7b1m078ks7ycl&dl=0
Steps To Reproduce
I want to transform onnx to engine by using code trtexec --onnx=model.onnx --saveEngine=model.trt --verbose. Then an error was reported. /MaxPool: at least 5 dimensions are required for input.
But I don't know why! The maxpool that reported the error is used here.
&&&& RUNNING TensorRT.trtexec [TensorRT v8601] # trtexec --onnx=model.onnx --saveEngine=model.trt --verbose
[01/11/2024-17:39:45] [I] === Model Options ===
[01/11/2024-17:39:45] [I] Format: ONNX
[01/11/2024-17:39:45] [I] Model: model.onnx
[01/11/2024-17:39:45] [I] Output:
[01/11/2024-17:39:45] [I] === Build Options ===
[01/11/2024-17:39:45] [I] Max batch: explicit batch
[01/11/2024-17:39:45] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
[01/11/2024-17:39:45] [I] minTiming: 1
[01/11/2024-17:39:45] [I] avgTiming: 8
[01/11/2024-17:39:45] [I] Precision: FP32
[01/11/2024-17:39:45] [I] LayerPrecisions:
[01/11/2024-17:39:45] [I] Layer Device Types:
[01/11/2024-17:39:45] [I] Calibration:
[01/11/2024-17:39:45] [I] Refit: Disabled
[01/11/2024-17:39:45] [I] Version Compatible: Disabled
[01/11/2024-17:39:45] [I] TensorRT runtime: full
[01/11/2024-17:39:45] [I] Lean DLL Path:
[01/11/2024-17:39:45] [I] Tempfile Controls: { in_memory: allow, temporary: allow }
[01/11/2024-17:39:45] [I] Exclude Lean Runtime: Disabled
[01/11/2024-17:39:45] [I] Sparsity: Disabled
[01/11/2024-17:39:45] [I] Safe mode: Disabled
[01/11/2024-17:39:45] [I] Build DLA standalone loadable: Disabled
[01/11/2024-17:39:45] [I] Allow GPU fallback for DLA: Disabled
[01/11/2024-17:39:45] [I] DirectIO mode: Disabled
[01/11/2024-17:39:45] [I] Restricted mode: Disabled
[01/11/2024-17:39:45] [I] Skip inference: Disabled
[01/11/2024-17:39:45] [I] Save engine: model.trt
[01/11/2024-17:39:45] [I] Load engine:
[01/11/2024-17:39:45] [I] Profiling verbosity: 0
[01/11/2024-17:39:45] [I] Tactic sources: Using default tactic sources
[01/11/2024-17:39:45] [I] timingCacheMode: local
[01/11/2024-17:39:45] [I] timingCacheFile:
[01/11/2024-17:39:45] [I] Heuristic: Disabled
[01/11/2024-17:39:45] [I] Preview Features: Use default preview flags.
[01/11/2024-17:39:45] [I] MaxAuxStreams: -1
[01/11/2024-17:39:45] [I] BuilderOptimizationLevel: -1
[01/11/2024-17:39:45] [I] Input(s)s format: fp32:CHW
[01/11/2024-17:39:45] [I] Output(s)s format: fp32:CHW
[01/11/2024-17:39:45] [I] Input build shapes: model
[01/11/2024-17:39:45] [I] Input calibration shapes: model
[01/11/2024-17:39:45] [I] === System Options ===
[01/11/2024-17:39:45] [I] Device: 0
[01/11/2024-17:39:45] [I] DLACore:
[01/11/2024-17:39:45] [I] Plugins:
[01/11/2024-17:39:45] [I] setPluginsToSerialize:
[01/11/2024-17:39:45] [I] dynamicPlugins:
[01/11/2024-17:39:45] [I] ignoreParsedPluginLibs: 0
[01/11/2024-17:39:45] [I]
[01/11/2024-17:39:45] [I] === Inference Options ===
[01/11/2024-17:39:45] [I] Batch: Explicit
[01/11/2024-17:39:45] [I] Input inference shapes: model
[01/11/2024-17:39:45] [I] Iterations: 10
[01/11/2024-17:39:45] [I] Duration: 3s (+ 200ms warm up)
[01/11/2024-17:39:45] [I] Sleep time: 0ms
[01/11/2024-17:39:45] [I] Idle time: 0ms
[01/11/2024-17:39:45] [I] Inference Streams: 1
[01/11/2024-17:39:45] [I] ExposeDMA: Disabled
[01/11/2024-17:39:45] [I] Data transfers: Enabled
[01/11/2024-17:39:45] [I] Spin-wait: Disabled
[01/11/2024-17:39:45] [I] Multithreading: Disabled
[01/11/2024-17:39:45] [I] CUDA Graph: Disabled
[01/11/2024-17:39:45] [I] Separate profiling: Disabled
[01/11/2024-17:39:45] [I] Time Deserialize: Disabled
[01/11/2024-17:39:45] [I] Time Refit: Disabled
[01/11/2024-17:39:45] [I] NVTX verbosity: 0
[01/11/2024-17:39:45] [I] Persistent Cache Ratio: 0
[01/11/2024-17:39:45] [I] Inputs:
[01/11/2024-17:39:45] [I] === Reporting Options ===
[01/11/2024-17:39:45] [I] Verbose: Enabled
[01/11/2024-17:39:45] [I] Averages: 10 inferences
[01/11/2024-17:39:45] [I] Percentiles: 90,95,99
[01/11/2024-17:39:45] [I] Dump refittable layers:Disabled
[01/11/2024-17:39:45] [I] Dump output: Disabled
[01/11/2024-17:39:45] [I] Profile: Disabled
[01/11/2024-17:39:45] [I] Export timing to JSON file:
[01/11/2024-17:39:45] [I] Export output to JSON file:
[01/11/2024-17:39:45] [I] Export profile to JSON file:
[01/11/2024-17:39:45] [I]
[01/11/2024-17:39:45] [I] === Device Information ===
[01/11/2024-17:39:45] [I] Selected Device: NVIDIA GeForce RTX 4090
[01/11/2024-17:39:45] [I] Compute Capability: 8.9
[01/11/2024-17:39:45] [I] SMs: 128
[01/11/2024-17:39:45] [I] Device Global Memory: 24217 MiB
[01/11/2024-17:39:45] [I] Shared Memory per SM: 100 KiB
[01/11/2024-17:39:45] [I] Memory Bus Width: 384 bits (ECC disabled)
[01/11/2024-17:39:45] [I] Application Compute Clock Rate: 2.52 GHz
[01/11/2024-17:39:45] [I] Application Memory Clock Rate: 10.501 GHz
[01/11/2024-17:39:45] [I]
[01/11/2024-17:39:45] [I] Note: The application clock rates do not reflect the actual clock rates that the GPU is currently running at.
[01/11/2024-17:39:45] [I]
[01/11/2024-17:39:45] [I] TensorRT version: 8.6.1
[01/11/2024-17:39:45] [I] Loading standard plugins
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::BatchedNMSDynamic_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::BatchedNMS_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::BatchTilePlugin_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::Clip_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::CoordConvAC version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::CropAndResizeDynamic version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::CropAndResize version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::DecodeBbox3DPlugin version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::DetectionLayer_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::EfficientNMS_Explicit_TF_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::EfficientNMS_Implicit_TF_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::EfficientNMS_ONNX_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::EfficientNMS_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::FlattenConcat_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::GenerateDetection_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::GridAnchor_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::GridAnchorRect_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::InstanceNormalization_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::InstanceNormalization_TRT version 2
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::LReLU_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::ModulatedDeformConv2d version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::MultilevelCropAndResize_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::MultilevelProposeROI_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::MultiscaleDeformableAttnPlugin_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::NMSDynamic_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::NMS_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::Normalize_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::PillarScatterPlugin version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::PriorBox_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::ProposalDynamic version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::ProposalLayer_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::Proposal version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::PyramidROIAlign_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::Region_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::Reorg_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::ResizeNearest_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::ROIAlign_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::RPROI_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::ScatterND version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::SpecialSlice_TRT version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::Split version 1
[01/11/2024-17:39:45] [V] [TRT] Registered plugin creator - ::VoxelGeneratorPlugin version 1
[01/11/2024-17:39:45] [I] [TRT] [MemUsageChange] Init CUDA: CPU +13, GPU +0, now: CPU 19, GPU 5895 (MiB)
[01/11/2024-17:39:45] [V] [TRT] Trying to load shared library libnvinfer_builder_resource.so.8.6.1
[01/11/2024-17:39:45] [V] [TRT] Loaded shared library libnvinfer_builder_resource.so.8.6.1
[01/11/2024-17:39:50] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +1450, GPU +266, now: CPU 1545, GPU 6161 (MiB)
[01/11/2024-17:39:50] [V] [TRT] CUDA lazy loading is enabled.
[01/11/2024-17:39:50] [I] Start parsing network model.
[01/11/2024-17:39:50] [I] [TRT] ----------------------------------------------------------------
[01/11/2024-17:39:50] [I] [TRT] Input filename: model.onnx
[01/11/2024-17:39:50] [I] [TRT] ONNX IR version: 0.0.8
[01/11/2024-17:39:50] [I] [TRT] Opset version: 16
[01/11/2024-17:39:50] [I] [TRT] Producer name: pytorch
[01/11/2024-17:39:50] [I] [TRT] Producer version: 1.13.0
[01/11/2024-17:39:50] [I] [TRT] Domain:
[01/11/2024-17:39:50] [I] [TRT] Model version: 0
[01/11/2024-17:39:50] [I] [TRT] Doc string:
[01/11/2024-17:39:50] [I] [TRT] ----------------------------------------------------------------
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::BatchedNMSDynamic_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::BatchedNMS_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::BatchTilePlugin_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::Clip_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::CoordConvAC version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::CropAndResizeDynamic version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::CropAndResize version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::DecodeBbox3DPlugin version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::DetectionLayer_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::EfficientNMS_Explicit_TF_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::EfficientNMS_Implicit_TF_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::EfficientNMS_ONNX_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::EfficientNMS_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::FlattenConcat_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::GenerateDetection_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::GridAnchor_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::GridAnchorRect_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::InstanceNormalization_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::InstanceNormalization_TRT version 2
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::LReLU_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::ModulatedDeformConv2d version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::MultilevelCropAndResize_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::MultilevelProposeROI_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::MultiscaleDeformableAttnPlugin_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::NMSDynamic_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::NMS_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::Normalize_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::PillarScatterPlugin version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::PriorBox_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::ProposalDynamic version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::ProposalLayer_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::Proposal version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::PyramidROIAlign_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::Region_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::Reorg_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::ResizeNearest_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::ROIAlign_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::RPROI_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::ScatterND version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::SpecialSlice_TRT version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::Split version 1
[01/11/2024-17:39:50] [V] [TRT] Plugin creator already registered - ::VoxelGeneratorPlugin version 1
[01/11/2024-17:39:50] [V] [TRT] Adding network input: input.1 with dtype: float32, dimensions: (1, 1, 682, 1024)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: input.1 for ONNX tensor: input.1
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv1a.weight with dtype: float32, dimensions: (64, 1, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv1a.weight for ONNX tensor: conv1a.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv1a.bias with dtype: float32, dimensions: (64)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv1a.bias for ONNX tensor: conv1a.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv1b.weight with dtype: float32, dimensions: (64, 64, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv1b.weight for ONNX tensor: conv1b.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv1b.bias with dtype: float32, dimensions: (64)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv1b.bias for ONNX tensor: conv1b.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv2a.weight with dtype: float32, dimensions: (64, 64, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv2a.weight for ONNX tensor: conv2a.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv2a.bias with dtype: float32, dimensions: (64)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv2a.bias for ONNX tensor: conv2a.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv2b.weight with dtype: float32, dimensions: (64, 64, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv2b.weight for ONNX tensor: conv2b.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv2b.bias with dtype: float32, dimensions: (64)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv2b.bias for ONNX tensor: conv2b.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv3a.weight with dtype: float32, dimensions: (128, 64, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv3a.weight for ONNX tensor: conv3a.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv3a.bias with dtype: float32, dimensions: (128)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv3a.bias for ONNX tensor: conv3a.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv3b.weight with dtype: float32, dimensions: (128, 128, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv3b.weight for ONNX tensor: conv3b.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv3b.bias with dtype: float32, dimensions: (128)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv3b.bias for ONNX tensor: conv3b.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv4a.weight with dtype: float32, dimensions: (128, 128, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv4a.weight for ONNX tensor: conv4a.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv4a.bias with dtype: float32, dimensions: (128)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv4a.bias for ONNX tensor: conv4a.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv4b.weight with dtype: float32, dimensions: (128, 128, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv4b.weight for ONNX tensor: conv4b.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: conv4b.bias with dtype: float32, dimensions: (128)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: conv4b.bias for ONNX tensor: conv4b.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convPa.weight with dtype: float32, dimensions: (256, 128, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convPa.weight for ONNX tensor: convPa.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convPa.bias with dtype: float32, dimensions: (256)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convPa.bias for ONNX tensor: convPa.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convPb.weight with dtype: float32, dimensions: (65, 256, 1, 1)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convPb.weight for ONNX tensor: convPb.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convPb.bias with dtype: float32, dimensions: (65)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convPb.bias for ONNX tensor: convPb.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convDa.weight with dtype: float32, dimensions: (256, 128, 3, 3)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convDa.weight for ONNX tensor: convDa.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convDa.bias with dtype: float32, dimensions: (256)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convDa.bias for ONNX tensor: convDa.bias
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convDb.weight with dtype: float32, dimensions: (256, 256, 1, 1)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convDb.weight for ONNX tensor: convDb.weight
[01/11/2024-17:39:50] [V] [TRT] Adding network input: convDb.bias with dtype: float32, dimensions: (256)
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: convDb.bias for ONNX tensor: convDb.bias
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv1a/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: input.1
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv1a.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv1a.bias
[01/11/2024-17:39:50] [V] [TRT] /conv1a/Conv [Conv] inputs: [input.1 -> (1, 1, 682, 1024)[FLOAT]], [conv1a.weight -> (64, 1, 3, 3)[FLOAT]], [conv1a.bias -> (64)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv1a/Conv for ONNX node: /conv1a/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv1a/Conv_output_0 for ONNX tensor: /conv1a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv1a/Conv [Conv] outputs: [/conv1a/Conv_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv1a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu/Relu [Relu] inputs: [/conv1a/Conv_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu/Relu for ONNX node: /relu/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu/Relu_output_0 for ONNX tensor: /relu/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu/Relu [Relu] outputs: [/relu/Relu_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv1b/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv1b.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv1b.bias
[01/11/2024-17:39:50] [V] [TRT] /conv1b/Conv [Conv] inputs: [/relu/Relu_output_0 -> (1, 64, 682, 1024)[FLOAT]], [conv1b.weight -> (64, 64, 3, 3)[FLOAT]], [conv1b.bias -> (64)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv1b/Conv for ONNX node: /conv1b/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv1b/Conv_output_0 for ONNX tensor: /conv1b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv1b/Conv [Conv] outputs: [/conv1b/Conv_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_1/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv1b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_1/Relu [Relu] inputs: [/conv1b/Conv_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_1/Relu for ONNX node: /relu_1/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_1/Relu_output_0 for ONNX tensor: /relu_1/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_1/Relu [Relu] outputs: [/relu_1/Relu_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /pool/MaxPool [MaxPool]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_1/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /pool/MaxPool [MaxPool] inputs: [/relu_1/Relu_output_0 -> (1, 64, 682, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /pool/MaxPool for ONNX node: /pool/MaxPool
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /pool/MaxPool_output_0 for ONNX tensor: /pool/MaxPool_output_0
[01/11/2024-17:39:50] [V] [TRT] /pool/MaxPool [MaxPool] outputs: [/pool/MaxPool_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv2a/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /pool/MaxPool_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv2a.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv2a.bias
[01/11/2024-17:39:50] [V] [TRT] /conv2a/Conv [Conv] inputs: [/pool/MaxPool_output_0 -> (1, 64, 341, 512)[FLOAT]], [conv2a.weight -> (64, 64, 3, 3)[FLOAT]], [conv2a.bias -> (64)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv2a/Conv for ONNX node: /conv2a/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv2a/Conv_output_0 for ONNX tensor: /conv2a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv2a/Conv [Conv] outputs: [/conv2a/Conv_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_2/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv2a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_2/Relu [Relu] inputs: [/conv2a/Conv_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_2/Relu for ONNX node: /relu_2/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_2/Relu_output_0 for ONNX tensor: /relu_2/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_2/Relu [Relu] outputs: [/relu_2/Relu_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv2b/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_2/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv2b.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv2b.bias
[01/11/2024-17:39:50] [V] [TRT] /conv2b/Conv [Conv] inputs: [/relu_2/Relu_output_0 -> (1, 64, 341, 512)[FLOAT]], [conv2b.weight -> (64, 64, 3, 3)[FLOAT]], [conv2b.bias -> (64)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv2b/Conv for ONNX node: /conv2b/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv2b/Conv_output_0 for ONNX tensor: /conv2b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv2b/Conv [Conv] outputs: [/conv2b/Conv_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_3/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv2b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_3/Relu [Relu] inputs: [/conv2b/Conv_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_3/Relu for ONNX node: /relu_3/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_3/Relu_output_0 for ONNX tensor: /relu_3/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_3/Relu [Relu] outputs: [/relu_3/Relu_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /pool_1/MaxPool [MaxPool]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_3/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /pool_1/MaxPool [MaxPool] inputs: [/relu_3/Relu_output_0 -> (1, 64, 341, 512)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /pool_1/MaxPool for ONNX node: /pool_1/MaxPool
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /pool_1/MaxPool_output_0 for ONNX tensor: /pool_1/MaxPool_output_0
[01/11/2024-17:39:50] [V] [TRT] /pool_1/MaxPool [MaxPool] outputs: [/pool_1/MaxPool_output_0 -> (1, 64, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv3a/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /pool_1/MaxPool_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv3a.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv3a.bias
[01/11/2024-17:39:50] [V] [TRT] /conv3a/Conv [Conv] inputs: [/pool_1/MaxPool_output_0 -> (1, 64, 170, 256)[FLOAT]], [conv3a.weight -> (128, 64, 3, 3)[FLOAT]], [conv3a.bias -> (128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv3a/Conv for ONNX node: /conv3a/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv3a/Conv_output_0 for ONNX tensor: /conv3a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv3a/Conv [Conv] outputs: [/conv3a/Conv_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_4/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv3a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_4/Relu [Relu] inputs: [/conv3a/Conv_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_4/Relu for ONNX node: /relu_4/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_4/Relu_output_0 for ONNX tensor: /relu_4/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_4/Relu [Relu] outputs: [/relu_4/Relu_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv3b/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_4/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv3b.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv3b.bias
[01/11/2024-17:39:50] [V] [TRT] /conv3b/Conv [Conv] inputs: [/relu_4/Relu_output_0 -> (1, 128, 170, 256)[FLOAT]], [conv3b.weight -> (128, 128, 3, 3)[FLOAT]], [conv3b.bias -> (128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv3b/Conv for ONNX node: /conv3b/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv3b/Conv_output_0 for ONNX tensor: /conv3b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv3b/Conv [Conv] outputs: [/conv3b/Conv_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_5/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv3b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_5/Relu [Relu] inputs: [/conv3b/Conv_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_5/Relu for ONNX node: /relu_5/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_5/Relu_output_0 for ONNX tensor: /relu_5/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_5/Relu [Relu] outputs: [/relu_5/Relu_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /pool_2/MaxPool [MaxPool]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_5/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /pool_2/MaxPool [MaxPool] inputs: [/relu_5/Relu_output_0 -> (1, 128, 170, 256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /pool_2/MaxPool for ONNX node: /pool_2/MaxPool
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /pool_2/MaxPool_output_0 for ONNX tensor: /pool_2/MaxPool_output_0
[01/11/2024-17:39:50] [V] [TRT] /pool_2/MaxPool [MaxPool] outputs: [/pool_2/MaxPool_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv4a/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /pool_2/MaxPool_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv4a.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv4a.bias
[01/11/2024-17:39:50] [V] [TRT] /conv4a/Conv [Conv] inputs: [/pool_2/MaxPool_output_0 -> (1, 128, 85, 128)[FLOAT]], [conv4a.weight -> (128, 128, 3, 3)[FLOAT]], [conv4a.bias -> (128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv4a/Conv for ONNX node: /conv4a/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv4a/Conv_output_0 for ONNX tensor: /conv4a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv4a/Conv [Conv] outputs: [/conv4a/Conv_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_6/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv4a/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_6/Relu [Relu] inputs: [/conv4a/Conv_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_6/Relu for ONNX node: /relu_6/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_6/Relu_output_0 for ONNX tensor: /relu_6/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_6/Relu [Relu] outputs: [/relu_6/Relu_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /conv4b/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_6/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv4b.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: conv4b.bias
[01/11/2024-17:39:50] [V] [TRT] /conv4b/Conv [Conv] inputs: [/relu_6/Relu_output_0 -> (1, 128, 85, 128)[FLOAT]], [conv4b.weight -> (128, 128, 3, 3)[FLOAT]], [conv4b.bias -> (128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /conv4b/Conv for ONNX node: /conv4b/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /conv4b/Conv_output_0 for ONNX tensor: /conv4b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /conv4b/Conv [Conv] outputs: [/conv4b/Conv_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_7/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /conv4b/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_7/Relu [Relu] inputs: [/conv4b/Conv_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_7/Relu for ONNX node: /relu_7/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_7/Relu_output_0 for ONNX tensor: /relu_7/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_7/Relu [Relu] outputs: [/relu_7/Relu_output_0 -> (1, 128, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /convPa/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_7/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: convPa.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: convPa.bias
[01/11/2024-17:39:50] [V] [TRT] /convPa/Conv [Conv] inputs: [/relu_7/Relu_output_0 -> (1, 128, 85, 128)[FLOAT]], [convPa.weight -> (256, 128, 3, 3)[FLOAT]], [convPa.bias -> (256)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /convPa/Conv for ONNX node: /convPa/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /convPa/Conv_output_0 for ONNX tensor: /convPa/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /convPa/Conv [Conv] outputs: [/convPa/Conv_output_0 -> (1, 256, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /relu_8/Relu [Relu]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /convPa/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_8/Relu [Relu] inputs: [/convPa/Conv_output_0 -> (1, 256, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /relu_8/Relu for ONNX node: /relu_8/Relu
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /relu_8/Relu_output_0 for ONNX tensor: /relu_8/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] /relu_8/Relu [Relu] outputs: [/relu_8/Relu_output_0 -> (1, 256, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /convPb/Conv [Conv]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /relu_8/Relu_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: convPb.weight
[01/11/2024-17:39:50] [V] [TRT] Searching for input: convPb.bias
[01/11/2024-17:39:50] [V] [TRT] /convPb/Conv [Conv] inputs: [/relu_8/Relu_output_0 -> (1, 256, 85, 128)[FLOAT]], [convPb.weight -> (65, 256, 1, 1)[FLOAT]], [convPb.bias -> (65)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Kernel weights are not set yet. Kernel weights must be set using setInput(1, kernel_tensor) API call.
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /convPb/Conv for ONNX node: /convPb/Conv
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /convPb/Conv_output_0 for ONNX tensor: /convPb/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /convPb/Conv [Conv] outputs: [/convPb/Conv_output_0 -> (1, 65, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Softmax [Softmax]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /convPb/Conv_output_0
[01/11/2024-17:39:50] [V] [TRT] /Softmax [Softmax] inputs: [/convPb/Conv_output_0 -> (1, 65, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /Softmax for ONNX node: /Softmax
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /Softmax_output_0 for ONNX tensor: /Softmax_output_0
[01/11/2024-17:39:50] [V] [TRT] /Softmax [Softmax] outputs: [/Softmax_output_0 -> (1, 65, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant [Constant] inputs:
[01/11/2024-17:39:50] [W] [TRT] onnx2trt_utils.cpp:374: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[01/11/2024-17:39:50] [V] [TRT] /Constant [Constant] outputs: [/Constant_output_0 -> ()[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_1 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_1 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_1 [Constant] outputs: [/Constant_1_output_0 -> (1)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_2 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_2 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_2 [Constant] outputs: [/Constant_2_output_0 -> (1)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_3 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_3 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_3 [Constant] outputs: [/Constant_3_output_0 -> (1)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_4 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_4 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_4 [Constant] outputs: [/Constant_4_output_0 -> (1)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Slice [Slice]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Softmax_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Constant_2_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Constant_3_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Constant_1_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Constant_4_output_0
[01/11/2024-17:39:50] [V] [TRT] /Slice [Slice] inputs: [/Softmax_output_0 -> (1, 65, 85, 128)[FLOAT]], [/Constant_2_output_0 -> (1)[INT32]], [/Constant_3_output_0 -> (1)[INT32]], [/Constant_1_output_0 -> (1)[INT32]], [/Constant_4_output_0 -> (1)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /Slice for ONNX node: /Slice
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /Slice_output_0 for ONNX tensor: /Slice_output_0
[01/11/2024-17:39:50] [V] [TRT] /Slice [Slice] outputs: [/Slice_output_0 -> (1, 64, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Transpose [Transpose]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Slice_output_0
[01/11/2024-17:39:50] [V] [TRT] /Transpose [Transpose] inputs: [/Slice_output_0 -> (1, 64, 85, 128)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /Transpose for ONNX node: /Transpose
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /Transpose_output_0 for ONNX tensor: /Transpose_output_0
[01/11/2024-17:39:50] [V] [TRT] /Transpose [Transpose] outputs: [/Transpose_output_0 -> (1, 85, 128, 64)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_5 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_5 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_5 [Constant] outputs: [/Constant_5_output_0 -> (5)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Reshape [Reshape]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Transpose_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Constant_5_output_0
[01/11/2024-17:39:50] [V] [TRT] /Reshape [Reshape] inputs: [/Transpose_output_0 -> (1, 85, 128, 64)[FLOAT]], [/Constant_5_output_0 -> (5)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /Reshape for ONNX node: /Reshape
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /Reshape_output_0 for ONNX tensor: /Reshape_output_0
[01/11/2024-17:39:50] [V] [TRT] /Reshape [Reshape] outputs: [/Reshape_output_0 -> (1, 85, 128, 8, 8)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Transpose_1 [Transpose]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Reshape_output_0
[01/11/2024-17:39:50] [V] [TRT] /Transpose_1 [Transpose] inputs: [/Reshape_output_0 -> (1, 85, 128, 8, 8)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /Transpose_1 for ONNX node: /Transpose_1
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /Transpose_1_output_0 for ONNX tensor: /Transpose_1_output_0
[01/11/2024-17:39:50] [V] [TRT] /Transpose_1 [Transpose] outputs: [/Transpose_1_output_0 -> (1, 85, 8, 128, 8)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_6 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_6 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_6 [Constant] outputs: [/Constant_6_output_0 -> (3)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Reshape_1 [Reshape]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Transpose_1_output_0
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Constant_6_output_0
[01/11/2024-17:39:50] [V] [TRT] /Reshape_1 [Reshape] inputs: [/Transpose_1_output_0 -> (1, 85, 8, 128, 8)[FLOAT]], [/Constant_6_output_0 -> (3)[INT32]],
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /Reshape_1 for ONNX node: /Reshape_1
[01/11/2024-17:39:50] [V] [TRT] Registering tensor: /Reshape_1_output_0 for ONNX tensor: /Reshape_1_output_0
[01/11/2024-17:39:50] [V] [TRT] /Reshape_1 [Reshape] outputs: [/Reshape_1_output_0 -> (1, 680, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /Constant_7 [Constant]
[01/11/2024-17:39:50] [V] [TRT] /Constant_7 [Constant] inputs:
[01/11/2024-17:39:50] [V] [TRT] /Constant_7 [Constant] outputs: [/Constant_7_output_0 -> (1, 680, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Parsing node: /MaxPool [MaxPool]
[01/11/2024-17:39:50] [V] [TRT] Searching for input: /Reshape_1_output_0
[01/11/2024-17:39:50] [V] [TRT] /MaxPool [MaxPool] inputs: [/Reshape_1_output_0 -> (1, 680, 1024)[FLOAT]],
[01/11/2024-17:39:50] [V] [TRT] Original shape: (1, 680, 1024), unsqueezing to: (1, 680, 1024, 1)
[01/11/2024-17:39:50] [V] [TRT] Registering layer: /MaxPool for ONNX node: /MaxPool
[01/11/2024-17:39:50] [E] Error[3]: /MaxPool: at least 5 dimensions are required for input.
[01/11/2024-17:39:50] [E] Error[4]: [graphShapeAnalyzer.cpp::needTypeAndDimensions::2212] Error Code 4: Internal Error (/MaxPool: output shape can not be computed)
[01/11/2024-17:39:50] [E] [TRT] ModelImporter.cpp:771: While parsing node number 36 [MaxPool -> "/MaxPool_output_0"]:
[01/11/2024-17:39:50] [E] [TRT] ModelImporter.cpp:772: --- Begin node ---
[01/11/2024-17:39:50] [E] [TRT] ModelImporter.cpp:773: input: "/Reshape_1_output_0"
output: "/MaxPool_output_0"
name: "/MaxPool"
op_type: "MaxPool"
attribute {
name: "ceil_mode"
i: 0
type: INT
}
attribute {
name: "kernel_shape"
ints: 9
ints: 9
type: INTS
}
attribute {
name: "pads"
ints: 4
ints: 4
ints: 4
ints: 4
type: INTS
}
attribute {
name: "strides"
ints: 1
ints: 1
type: INTS
}
[01/11/2024-17:39:50] [E] [TRT] ModelImporter.cpp:774: --- End node ---
[01/11/2024-17:39:50] [E] [TRT] ModelImporter.cpp:777: ERROR: ModelImporter.cpp:178 In function parseGraph:
[6] Invalid Node - /MaxPool
std::bad_alloc
[01/11/2024-17:39:50] [E] Failed to parse onnx file
[01/11/2024-17:39:50] [I] Finished parsing network model. Parse time: 0.0403079
[01/11/2024-17:39:50] [E] Parsing model failed
[01/11/2024-17:39:50] [E] Failed to create engine from model or file.
[01/11/2024-17:39:50] [E] Engine set up failed
&&&& FAILED TensorRT.trtexec [TensorRT v8601] # trtexec --onnx=model.onnx --saveEngine=model.trt --verbose
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.