jetson-inference, run posenet --network=resnet18-hand /dev/video0 can not show camera image,
use posenet /dev/video0 is ok, can look the camera image .
the model is exits.
Hi,
Please add the model info to the source code as well.
Thanks.
sorry, i cannot understand , the pose-resnet-hand is exist ,
Do I need to download other models？
the hand model is right to load.
but can not show the camera image
posenet.py --network=resnet18-hand /dev/video0
poseNet -- loading pose estimation model from:
-- model networks/Pose-ResNet18-Hand/pose_resnet18_hand.onnx
-- topology networks/Pose-ResNet18-Hand/hand_pose.json
-- colors networks/Pose-ResNet18-Hand/colors.txt
-- input_blob 'input'
-- output_cmap 'cmap'
-- output_paf 'paf'
-- threshold 0.150000
-- batch_size 1
[TRT] topology -- keypoint 0 palm
[TRT] topology -- keypoint 1 thumb_1
[TRT] topology -- keypoint 2 thumb_2
[TRT] topology -- keypoint 3 thumb_3
[TRT] topology -- keypoint 4 thumb_4
[TRT] topology -- keypoint 5 index_finger_1
[TRT] topology -- keypoint 6 index_finger_2
[TRT] topology -- keypoint 7 index_finger_3
[TRT] topology -- keypoint 8 index_finger_4
[TRT] topology -- keypoint 9 middle_finger_1
[TRT] topology -- keypoint 10 middle_finger_2
[TRT] topology -- keypoint 11 middle_finger_3
[TRT] topology -- keypoint 12 middle_finger_4
[TRT] topology -- keypoint 13 ring_finger_1
[TRT] topology -- keypoint 14 ring_finger_2
[TRT] topology -- keypoint 15 ring_finger_3
[TRT] topology -- keypoint 16 ring_finger_4
[TRT] topology -- keypoint 17 baby_finger_1
[TRT] topology -- keypoint 18 baby_finger_2
[TRT] topology -- keypoint 19 baby_finger_3
[TRT] topology -- keypoint 20 baby_finger_4
[TRT] topology -- skeleton link 0 1 5
[TRT] topology -- skeleton link 1 1 9
[TRT] topology -- skeleton link 2 1 13
[TRT] topology -- skeleton link 3 1 17
[TRT] topology -- skeleton link 4 1 21
[TRT] topology -- skeleton link 5 2 3
[TRT] topology -- skeleton link 6 3 4
[TRT] topology -- skeleton link 7 4 5
[TRT] topology -- skeleton link 8 6 7
[TRT] topology -- skeleton link 9 7 8
[TRT] topology -- skeleton link 10 8 9
[TRT] topology -- skeleton link 11 10 11
[TRT] topology -- skeleton link 12 11 12
[TRT] topology -- skeleton link 13 12 13
[TRT] topology -- skeleton link 14 14 15
[TRT] topology -- skeleton link 15 15 16
[TRT] topology -- skeleton link 16 16 17
[TRT] topology -- skeleton link 17 18 19
[TRT] topology -- skeleton link 18 19 20
[TRT] topology -- skeleton link 19 20 21
[TRT] poseNet -- keypoint 00 'palm' color 200 200 200 255
[TRT] poseNet -- keypoint 01 'thumb_1' color 215 0 0 255
[TRT] poseNet -- keypoint 02 'thumb_2' color 194 0 0 255
[TRT] poseNet -- keypoint 03 'thumb_3' color 172 0 0 255
[TRT] poseNet -- keypoint 04 'thumb_4' color 150 0 0 255
[TRT] poseNet -- keypoint 05 'index_finger_1' color 221 255 48 255
[TRT] poseNet -- keypoint 06 'index_finger_2' color 200 230 43 255
[TRT] poseNet -- keypoint 07 'index_finger_3' color 175 200 35 255
[TRT] poseNet -- keypoint 08 'index_finger_4' color 155 180 31 255
[TRT] poseNet -- keypoint 09 'middle_finger_1' color 152 254 111 255
[TRT] poseNet -- keypoint 10 'middle_finger_2' color 135 228 101 255
[TRT] poseNet -- keypoint 11 'middle_finger_3' color 120 203 89 255
[TRT] poseNet -- keypoint 12 'middle_finger_4' color 105 180 78 255
[TRT] poseNet -- keypoint 13 'ring_finger_1' color 64 103 252 255
[TRT] poseNet -- keypoint 14 'ring_finger_2' color 57 93 227 255
[TRT] poseNet -- keypoint 15 'ring_finger_3' color 51 83 202 255
[TRT] poseNet -- keypoint 16 'ring_finger_4' color 43 72 177 255
[TRT] poseNet -- keypoint 17 'baby_finger_1' color 173 18 252 255
[TRT] poseNet -- keypoint 18 'baby_finger_2' color 156 15 227 255
[TRT] poseNet -- keypoint 19 'baby_finger_3' color 138 12 201 255
[TRT] poseNet -- keypoint 20 'baby_finger_4' color 121 9 177 255
[TRT] poseNet -- loaded 21 class colors
[TRT] TensorRT version 8.4.1
[TRT] loading NVIDIA plugins...
[TRT] Registered plugin creator - ::GridAnchor_TRT version 1
[TRT] Registered plugin creator - ::GridAnchorRect_TRT version 1
[TRT] Registered plugin creator - ::NMS_TRT version 1
[TRT] Registered plugin creator - ::Reorg_TRT version 1
[TRT] Registered plugin creator - ::Region_TRT version 1
[TRT] Registered plugin creator - ::Clip_TRT version 1
[TRT] Registered plugin creator - ::LReLU_TRT version 1
[TRT] Registered plugin creator - ::PriorBox_TRT version 1
[TRT] Registered plugin creator - ::Normalize_TRT version 1
[TRT] Registered plugin creator - ::ScatterND version 1
[TRT] Registered plugin creator - ::RPROI_TRT version 1
[TRT] Registered plugin creator - ::BatchedNMS_TRT version 1
[TRT] Registered plugin creator - ::BatchedNMSDynamic_TRT version 1
[TRT] Registered plugin creator - ::BatchTilePlugin_TRT version 1
[TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1
[TRT] Registered plugin creator - ::CropAndResize version 1
[TRT] Registered plugin creator - ::CropAndResizeDynamic version 1
[TRT] Registered plugin creator - ::DetectionLayer_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_ONNX_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_Explicit_TF_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_Implicit_TF_TRT version 1
[TRT] Registered plugin creator - ::ProposalDynamic version 1
[TRT] Registered plugin creator - ::Proposal version 1
[TRT] Registered plugin creator - ::ProposalLayer_TRT version 1
[TRT] Registered plugin creator - ::PyramidROIAlign_TRT version 1
[TRT] Registered plugin creator - ::ResizeNearest_TRT version 1
[TRT] Registered plugin creator - ::Split version 1
[TRT] Registered plugin creator - ::SpecialSlice_TRT version 1
[TRT] Registered plugin creator - ::InstanceNormalization_TRT version 1
[TRT] Registered plugin creator - ::InstanceNormalization_TRT version 2
[TRT] Registered plugin creator - ::CoordConvAC version 1
[TRT] Registered plugin creator - ::DecodeBbox3DPlugin version 1
[TRT] Registered plugin creator - ::GenerateDetection_TRT version 1
[TRT] Registered plugin creator - ::MultilevelCropAndResize_TRT version 1
[TRT] Registered plugin creator - ::MultilevelProposeROI_TRT version 1
[TRT] Registered plugin creator - ::NMSDynamic_TRT version 1
[TRT] Registered plugin creator - ::PillarScatterPlugin version 1
[TRT] Registered plugin creator - ::VoxelGeneratorPlugin version 1
[TRT] Registered plugin creator - ::MultiscaleDeformableAttnPlugin_TRT version 1
[TRT] detected model format - ONNX (extension '.onnx')
[TRT] desired precision specified for GPU: FASTEST
[TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT] [MemUsageChange] Init CUDA: CPU +213, GPU +0, now: CPU 248, GPU 12781 (MiB)
[TRT] [MemUsageChange] Init builder kernel library: CPU +352, GPU +459, now: CPU 619, GPU 13256 (MiB)
[TRT] native precisions detected for GPU: FP32, FP16, INT8
[TRT] selecting fastest native precision for GPU: FP16
[TRT] could not find engine cache /usr/local/bin/networks/Pose-ResNet18-Hand/pose_resnet18_hand.onnx.1.1.8401.GPU.FP16.engine
[TRT] cache file invalid, profiling network model on device GPU
[TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 268, GPU 13257 (MiB)
[TRT] [MemUsageChange] Init builder kernel library: CPU +351, GPU +1, now: CPU 619, GPU 13258 (MiB)
[TRT] The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
[TRT] device GPU, loading /usr/bin/ /usr/local/bin/networks/Pose-ResNet18-Hand/pose_resnet18_hand.onnx
[TRT] ----------------------------------------------------------------
[TRT] Input filename: /usr/local/bin/networks/Pose-ResNet18-Hand/pose_resnet18_hand.onnx
[TRT] ONNX IR version: 0.0.6
[TRT] Opset version: 9
[TRT] Producer name: pytorch
[TRT] Producer version: 1.8
[TRT] Domain:
[TRT] Model version: 0
[TRT] Doc string:
[TRT] ----------------------------------------------------------------
[TRT] Plugin creator already registered - ::GridAnchor_TRT version 1
[TRT] Plugin creator already registered - ::GridAnchorRect_TRT version 1
[TRT] Plugin creator already registered - ::NMS_TRT version 1
[TRT] Plugin creator already registered - ::Reorg_TRT version 1
[TRT] Plugin creator already registered - ::Region_TRT version 1
[TRT] Plugin creator already registered - ::Clip_TRT version 1
[TRT] Plugin creator already registered - ::LReLU_TRT version 1
[TRT] Plugin creator already registered - ::PriorBox_TRT version 1
[TRT] Plugin creator already registered - ::Normalize_TRT version 1
[TRT] Plugin creator already registered - ::ScatterND version 1
[TRT] Plugin creator already registered - ::RPROI_TRT version 1
[TRT] Plugin creator already registered - ::BatchedNMS_TRT version 1
[TRT] Plugin creator already registered - ::BatchedNMSDynamic_TRT version 1
[TRT] Plugin creator already registered - ::BatchTilePlugin_TRT version 1
[TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1
[TRT] Plugin creator already registered - ::CropAndResize version 1
[TRT] Plugin creator already registered - ::CropAndResizeDynamic version 1
[TRT] Plugin creator already registered - ::DetectionLayer_TRT version 1
[TRT] Plugin creator already registered - ::EfficientNMS_TRT version 1
[TRT] Plugin creator already registered - ::EfficientNMS_ONNX_TRT version 1
[TRT] Plugin creator already registered - ::EfficientNMS_Explicit_TF_TRT version 1
[TRT] Plugin creator already registered - ::EfficientNMS_Implicit_TF_TRT version 1
[TRT] Plugin creator already registered - ::ProposalDynamic version 1
[TRT] Plugin creator already registered - ::Proposal version 1
[TRT] Plugin creator already registered - ::ProposalLayer_TRT version 1
[TRT] Plugin creator already registered - ::PyramidROIAlign_TRT version 1
[TRT] Plugin creator already registered - ::ResizeNearest_TRT version 1
[TRT] Plugin creator already registered - ::Split version 1
[TRT] Plugin creator already registered - ::SpecialSlice_TRT version 1
[TRT] Plugin creator already registered - ::InstanceNormalization_TRT version 1
[TRT] Plugin creator already registered - ::InstanceNormalization_TRT version 2
[TRT] Plugin creator already registered - ::CoordConvAC version 1
[TRT] Plugin creator already registered - ::DecodeBbox3DPlugin version 1
[TRT] Plugin creator already registered - ::GenerateDetection_TRT version 1
[TRT] Plugin creator already registered - ::MultilevelCropAndResize_TRT version 1
[TRT] Plugin creator already registered - ::MultilevelProposeROI_TRT version 1
[TRT] Plugin creator already registered - ::NMSDynamic_TRT version 1
[TRT] Plugin creator already registered - ::PillarScatterPlugin version 1
[TRT] Plugin creator already registered - ::VoxelGeneratorPlugin version 1
[TRT] Plugin creator already registered - ::MultiscaleDeformableAttnPlugin_TRT version 1
[TRT] Adding network input: input with dtype: float32, dimensions: (1, 3, 224, 224)
[TRT] Registering tensor: input for ONNX tensor: input
[TRT] Importing initializer: 1.cmap_up.0.weight
[TRT] Importing initializer: 1.cmap_up.0.bias
[TRT] Importing initializer: 1.cmap_up.1.weight
[TRT] Importing initializer: 1.cmap_up.1.bias
[TRT] Importing initializer: 1.cmap_up.1.running_mean
[TRT] Importing initializer: 1.cmap_up.1.running_var
[TRT] Importing initializer: 1.cmap_up.3.weight
[TRT] Importing initializer: 1.cmap_up.3.bias
[TRT] Importing initializer: 1.cmap_up.4.weight
[TRT] Importing initializer: 1.cmap_up.4.bias
[TRT] Importing initializer: 1.cmap_up.4.running_mean
[TRT] Importing initializer: 1.cmap_up.4.running_var
[TRT] Importing initializer: 1.cmap_up.6.weight
[TRT] Importing initializer: 1.cmap_up.6.bias
[TRT] Importing initializer: 1.cmap_up.7.weight
[TRT] Importing initializer: 1.cmap_up.7.bias
[TRT] Importing initializer: 1.cmap_up.7.running_mean
[TRT] Importing initializer: 1.cmap_up.7.running_var
[TRT] Importing initializer: 1.paf_up.0.weight
[TRT] Importing initializer: 1.paf_up.0.bias
[TRT] Importing initializer: 1.paf_up.1.weight
[TRT] Importing initializer: 1.paf_up.1.bias
[TRT] Importing initializer: 1.paf_up.1.running_mean
[TRT] Importing initializer: 1.paf_up.1.running_var
[TRT] Importing initializer: 1.paf_up.3.weight
[TRT] Importing initializer: 1.paf_up.3.bias
[TRT] Importing initializer: 1.paf_up.4.weight
[TRT] Importing initializer: 1.paf_up.4.bias
[TRT] Importing initializer: 1.paf_up.4.running_mean
[TRT] Importing initializer: 1.paf_up.4.running_var
[TRT] Importing initializer: 1.paf_up.6.weight
[TRT] Importing initializer: 1.paf_up.6.bias
[TRT] Importing initializer: 1.paf_up.7.weight
[TRT] Importing initializer: 1.paf_up.7.bias
[TRT] Importing initializer: 1.paf_up.7.running_mean
[TRT] Importing initializer: 1.paf_up.7.running_var
[TRT] Importing initializer: 1.cmap_att.weight
[TRT] Importing initializer: 1.cmap_att.bias
[TRT] Importing initializer: 1.paf_att.weight
[TRT] Importing initializer: 1.paf_att.bias
[TRT] Importing initializer: 1.cmap_conv.weight
[TRT] Importing initializer: 1.cmap_conv.bias
[TRT] Importing initializer: 1.paf_conv.weight
[TRT] Importing initializer: 1.paf_conv.bias
[TRT] Importing initializer: 266
[TRT] Importing initializer: 267
[TRT] Importing initializer: 269
[TRT] Importing initializer: 270
[TRT] Importing initializer: 272
[TRT] Importing initializer: 273
[TRT] Importing initializer: 275
[TRT] Importing initializer: 276
[TRT] Importing initializer: 278
[TRT] Importing initializer: 279
[TRT] Importing initializer: 281
[TRT] Importing initializer: 282
[TRT] Importing initializer: 284
[TRT] Importing initializer: 285
[TRT] Importing initializer: 287
[TRT] Importing initializer: 288
[TRT] Importing initializer: 290
[TRT] Importing initializer: 291
[TRT] Importing initializer: 293
[TRT] Importing initializer: 294
[TRT] Importing initializer: 296
[TRT] Importing initializer: 297
[TRT] Importing initializer: 299
[TRT] Importing initializer: 300
[TRT] Importing initializer: 302
[TRT] Importing initializer: 303
[TRT] Importing initializer: 305
[TRT] Importing initializer: 306
[TRT] Importing initializer: 308
[TRT] Importing initializer: 309
[TRT] Importing initializer: 311
[TRT] Importing initializer: 312
[TRT] Importing initializer: 314
[TRT] Importing initializer: 315
[TRT] Importing initializer: 317
[TRT] Importing initializer: 318
[TRT] Importing initializer: 320
[TRT] Importing initializer: 321
[TRT] Importing initializer: 323
[TRT] Importing initializer: 324
[TRT] Parsing node: Conv_0 [Conv]
[TRT] Searching for input: input
[TRT] Searching for input: 266
[TRT] Searching for input: 267
[TRT] Conv_0 [Conv] inputs: [input -> (1, 3, 224, 224)[FLOAT]], [266 -> (64, 3, 7, 7)[FLOAT]], [267 -> (64)[FLOAT]],
[TRT] Convolution input dimensions: (1, 3, 224, 224)
[TRT] Registering layer: Conv_0 for ONNX node: Conv_0
[TRT] Using kernel: (7, 7), strides: (2, 2), prepadding: (3, 3), postpadding: (3, 3), dilations: (1, 1), numOutputs: 64
[TRT] Convolution output dimensions: (1, 64, 112, 112)
[TRT] Registering tensor: 265 for ONNX tensor: 265
[TRT] Conv_0 [Conv] outputs: [265 -> (1, 64, 112, 112)[FLOAT]],
[TRT] Parsing node: Relu_1 [Relu]
[TRT] Searching for input: 265
[TRT] Relu_1 [Relu] inputs: [265 -> (1, 64, 112, 112)[FLOAT]],
[TRT] Registering layer: Relu_1 for ONNX node: Relu_1
[TRT] Registering tensor: 175 for ONNX tensor: 175
[TRT] Relu_1 [Relu] outputs: [175 -> (1, 64, 112, 112)[FLOAT]],
[TRT] Parsing node: MaxPool_2 [MaxPool]
[TRT] Searching for input: 175
[TRT] MaxPool_2 [MaxPool] inputs: [175 -> (1, 64, 112, 112)[FLOAT]],
[TRT] Registering layer: MaxPool_2 for ONNX node: MaxPool_2
[TRT] Registering tensor: 176 for ONNX tensor: 176
[TRT] MaxPool_2 [MaxPool] outputs: [176 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Conv_3 [Conv]
[TRT] Searching for input: 176
[TRT] Searching for input: 269
[TRT] Searching for input: 270
[TRT] Conv_3 [Conv] inputs: [176 -> (1, 64, 56, 56)[FLOAT]], [269 -> (64, 64, 3, 3)[FLOAT]], [270 -> (64)[FLOAT]],
[TRT] Convolution input dimensions: (1, 64, 56, 56)
[TRT] Registering layer: Conv_3 for ONNX node: Conv_3
[TRT] Using kernel: (3, 3), strides: (1, 1), prepadding: (1, 1), postpadding: (1, 1), dilations: (1, 1), numOutputs: 64
[TRT] Convolution output dimensions: (1, 64, 56, 56)
[TRT] Registering tensor: 268 for ONNX tensor: 268
[TRT] Conv_3 [Conv] outputs: [268 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Relu_4 [Relu]
[TRT] Searching for input: 268
[TRT] Relu_4 [Relu] inputs: [268 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Registering layer: Relu_4 for ONNX node: Relu_4
[TRT] Registering tensor: 179 for ONNX tensor: 179
[TRT] Relu_4 [Relu] outputs: [179 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Conv_5 [Conv]
[TRT] Searching for input: 179
[TRT] Searching for input: 272
[TRT] Searching for input: 273
[TRT] Conv_5 [Conv] inputs: [179 -> (1, 64, 56, 56)[FLOAT]], [272 -> (64, 64, 3, 3)[FLOAT]], [273 -> (64)[FLOAT]],
[TRT] Convolution input dimensions: (1, 64, 56, 56)
[TRT] Registering layer: Conv_5 for ONNX node: Conv_5
[TRT] Using kernel: (3, 3), strides: (1, 1), prepadding: (1, 1), postpadding: (1, 1), dilations: (1, 1), numOutputs: 64
[TRT] Convolution output dimensions: (1, 64, 56, 56)
[TRT] Registering tensor: 271 for ONNX tensor: 271
[TRT] Conv_5 [Conv] outputs: [271 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Add_6 [Add]
[TRT] Searching for input: 271
[TRT] Searching for input: 176
[TRT] Add_6 [Add] inputs: [271 -> (1, 64, 56, 56)[FLOAT]], [176 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Registering layer: Add_6 for ONNX node: Add_6
[TRT] Registering tensor: 182 for ONNX tensor: 182
[TRT] Add_6 [Add] outputs: [182 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Relu_7 [Relu]
[TRT] Searching for input: 182
[TRT] Relu_7 [Relu] inputs: [182 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Registering layer: Relu_7 for ONNX node: Relu_7
[TRT] Registering tensor: 183 for ONNX tensor: 183
[TRT] Relu_7 [Relu] outputs: [183 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Conv_8 [Conv]
[TRT] Searching for input: 183
[TRT] Searching for input: 275
[TRT] Searching for input: 276
[TRT] Conv_8 [Conv] inputs: [183 -> (1, 64, 56, 56)[FLOAT]], [275 -> (64, 64, 3, 3)[FLOAT]], [276 -> (64)[FLOAT]],
[TRT] Convolution input dimensions: (1, 64, 56, 56)
[TRT] Registering layer: Conv_8 for ONNX node: Conv_8
[TRT] Using kernel: (3, 3), strides: (1, 1), prepadding: (1, 1), postpadding: (1, 1), dilations: (1, 1), numOutputs: 64
[TRT] Convolution output dimensions: (1, 64, 56, 56)
[TRT] Registering tensor: 274 for ONNX tensor: 274
[TRT] Conv_8 [Conv] outputs: [274 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Parsing node: Relu_9 [Relu]
[TRT] Searching for input: 274
[TRT] Relu_9 [Relu] inputs: [274 -> (1, 64, 56, 56)[FLOAT]],
[TRT] Registering layer: Relu_9 for ONNX node: Relu_9
[TRT] Registering tensor: 186 for ONNX tensor: 186
[TRT] Relu_9 [Relu] outputs: [186 -> (1, 64, 56, 56)[FLOAT]],
Hi @comeon, have you tried just letting it run for a few minutes? Or does the console log freeze there?
The first time you load a model, TensorRT builds the engine for it and it can take a few minutes. It’s saved to disk so the next time you load the model it loads in a couple seconds instead.
running for more than three minutes，the console log Keep scrolling。
the console is on the top
It can take that long or longer on some complicated models like pose estimation, yes. If it keeps scrolling then let it keep running.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.