Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) RTX4080
• DeepStream Version nvcr.io/nvidia/deepstream:7.0-triton-multiarch**•**
• NVIDIA GPU Driver Version (valid for GPU only) 550.54.14
I am trying to implement deepstream-3d-action-recognition.
I have fight.onnx model.
This is 3D RGB model.
The config files used are
config_infer_primary_3d_action.txt (2.6 KB)
config_preprocess_3d_custom.txt (2.8 KB)
When I run the app, I have the following error.
ERROR from element preprocess-plugin: Processing height = 224 and width =224 should be same as network height = 32 and width =224
The whole error logs are as follows.
(base) root@user-Nuvo-10000-Series:/workspace/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-3d-action-recognition# deepstream-3d-action-recognition -c deepstream_action_recognition_config.txtnum-sources = 12Now playing: file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/fight/01-01.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/fight/01-03.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/fight/04-05_2.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/fight/04-06.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/fight/04-06_2.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/fight/04-07.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/normal/05-01_2.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/normal/05-01_4.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/normal/05-02_2.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/normal/05-02_3.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/normal/05-02_5.mp4, file:///workspace/opt/nvidia/deepstream/deepstream/samples/streams/fights/normal/05-07_9.mp4,0:00:03.297982627 31 0x5f00d5d8e1d0 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2095> [UID = 1]: deserialized trt engine from :/workspace/opt/nvidia/deepstream/deepstream-7.0/sources/apps/sample_apps/deepstream-3d-action-recognition/fight_3D_32sql.onnx_b12_gpu0_fp16.engineINFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:612 [FullDims Engine Info]: layers num: 20 INPUT kFLOAT input_rgb 3x32x224x224 min: 1x3x32x224x224 opt: 12x3x32x224x224 Max: 12x3x32x224x2241 OUTPUT kFLOAT fc_pred 2 min: 0 opt: 0 Max: 0
0:00:03.391967332 31 0x5f00d5d8e1d0 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2198> [UID = 1]: Use deserialized engine model: /workspace/opt/nvidia/deepstream/deepstream-7.0/sources/apps/sample_apps/deepstream-3d-action-recognition/fight_3D_32sql.onnx_b12_gpu0_fp16.engine0:00:03.394550627 31 0x5f00d5d8e1d0 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus: [UID 1]: Load new model:config_infer_primary_3d_action.txt sucessfullysequence_image_process.cpp:484, [INFO: CUSTOM_LIB] 3D custom sequence network info(NCSHW), [N: 12, C: 3, S: 32, H: 224, W:224]sequence_image_process.cpp:512, [INFO: CUSTOM_LIB] Sequence preprocess buffer manager initialized with stride: 1, subsample: 0sequence_image_process.cpp:516, [INFO: CUSTOM_LIB] SequenceImagePreprocess initialized successfullyDecodebin child added: sourceDecodebin child added: decodebin0Decodebin child added: sourceDecodebin child added: decodebin1Decodebin child added: sourceDecodebin child added: decodebin2Decodebin child added: sourceDecodebin child added: decodebin3Decodebin child added: sourceDecodebin child added: decodebin4Decodebin child added: sourceDecodebin child added: decodebin5Decodebin child added: sourceDecodebin child added: decodebin6Decodebin child added: sourceDecodebin child added: decodebin7Decodebin child added: sourceDecodebin child added: decodebin8Decodebin child added: sourceDecodebin child added: decodebin9Decodebin child added: sourceDecodebin child added: decodebin10Decodebin child added: sourceDecodebin child added: decodebin11Running…ERROR from element preprocess-plugin: Processing height = 224 and width =224 should be same as network height = 32 and width =224
Error details: gstnvdspreprocess.cpp(624): gst_nvdspreprocess_start (): /GstPipeline:preprocess-test-pipeline/GstNvDsPreProcess:preprocess-pluginReturned, stopping playbackDecodebin child added: qtdemux0Decodebin child added: qtdemux1Decodebin child added: qtdemux2Decodebin child added: multiqueue0Decodebin child added: multiqueue1Decodebin child added: qtdemux3Decodebin child added: multiqueue2Decodebin child added: multiqueue3Decodebin child added: qtdemux4Decodebin child added: qtdemux5Decodebin child added: multiqueue4Decodebin child added: multiqueue5Decodebin child added: qtdemux6Decodebin child added: multiqueue6Decodebin child added: qtdemux7Decodebin child added: multiqueue7Decodebin child added: qtdemux8Decodebin child added: multiqueue8Decodebin child added: h265parse0Decodebin child added: h265parse1Decodebin child added: capsfilter0Decodebin child added: capsfilter1Decodebin child added: h265parse2Decodebin child added: qtdemux9Decodebin child added: qtdemux10Decodebin child added: capsfilter2Decodebin child added: multiqueue9Decodebin child added: multiqueue10Decodebin child added: qtdemux11Decodebin child added: h265parse3Decodebin child added: h265parse4Decodebin child added: capsfilter3Decodebin child added: multiqueue11Decodebin child added: capsfilter4Decodebin child added: h265parse5Decodebin child added: capsfilter5Decodebin child added: nvv4l2decoder0Decodebin child added: nvv4l2decoder2Decodebin child added: nvv4l2decoder1Decodebin child added: nvv4l2decoder4Decodebin child added: nvv4l2decoder3Decodebin child added: h265parse6Decodebin child added: h265parse7Decodebin child added: h265parse8Decodebin child added: capsfilter6Decodebin child added: capsfilter7Decodebin child added: capsfilter8Decodebin child added: h265parse9Decodebin child added: nvv4l2decoder5Decodebin child added: capsfilter9Decodebin child added: h265parse10Decodebin child added: nvv4l2decoder6Decodebin child added: h265parse11Decodebin child added: capsfilter10Decodebin child added: nvv4l2decoder7Decodebin child added: nvv4l2decoder8Decodebin child added: capsfilter11Decodebin child added: nvv4l2decoder9Decodebin child added: nvv4l2decoder10Decodebin child added: nvv4l2decoder11In cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadIn cb_newpadDeleting pipelinesequence_image_process.cpp:578, [INFO: CUSTOM_LIB] SequenceImagePreprocess is deinitializing(base) root@user-Nuvo-10000-Series:/workspace/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-3d-action-recognition#