• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1.1
• TensorRT Version TensorRT 8.5.2
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) questions
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description
I have been trying to run deepstream on the Jetson Orin AGX over ssh and stream the results over udp. I kept having an error that looked like the following:
nvbufsurface: Failed to create EGLImage.
0:01:08.716927590 65019 0xaaab1d8a7a90 ERROR nvinferallocator gstnvinfer_allocator.cpp:102:gst_nvinfer_allocator_alloc: Error: Could not map EglImage from NvBufSurface for nvinfer
0:01:08.716950982 65019 0xaaab1d8a7a90 WARN GST_BUFFER gstbuffer.c:951:gst_buffer_new_allocate: failed to allocate 88 bytes
0:01:08.716973095 65019 0xaaab1d8a7a90 WARN bufferpool gstbufferpool.c:305:do_alloc_buffer:<bufferpool0> alloc function failed
0:01:08.716979847 65019 0xaaab1d8a7a90 WARN bufferpool gstbufferpool.c:338:default_start:<bufferpool0> failed to allocate buffer
0:01:08.716985063 65019 0xaaab1d8a7a90 ERROR bufferpool gstbufferpool.c:559:gst_buffer_pool_set_active:<bufferpool0> start failed
0:01:08.716995463 65019 0xaaab1d8a7a90 WARN nvinfer gstnvinfer.cpp:985:gst_nvinfer_start:<secondary_gie_2> error: Failed to set buffer pool to active
0:01:08.722347831 65019 0xaaab1d8a7a90 WARN GST_PADS gstpad.c:1142:gst_pad_set_active:<secondary_gie_2:sink> Failed to activate pad
I then tried to just get the sample deepstream apps to work and got the following:
deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
libEGL warning: DRI3: failed to query the version
libEGL warning: DRI2: failed to authenticate
libEGL warning: DRI3: failed to query the version
libEGL warning: DRI2: failed to authenticate
WARNING: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine open error
0:00:02.083544460 65019 0xaaab1d8a7a90 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 6]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine failed
0:00:02.225631508 65019 0xaaab1d8a7a90 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 6]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine failed, try rebuild
0:00:02.225718293 65019 0xaaab1d8a7a90 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 6]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
WARNING: Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine opened error
0:01:08.514397594 65019 0xaaab1d8a7a90 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1950> [UID = 6]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 20x1x1
nvbufsurface: Failed to create EGLImage.
0:01:08.716927590 65019 0xaaab1d8a7a90 ERROR nvinferallocator gstnvinfer_allocator.cpp:102:gst_nvinfer_allocator_alloc: Error: Could not map EglImage from NvBufSurface for nvinfer
0:01:08.716950982 65019 0xaaab1d8a7a90 WARN GST_BUFFER gstbuffer.c:951:gst_buffer_new_allocate: failed to allocate 88 bytes
0:01:08.716973095 65019 0xaaab1d8a7a90 WARN bufferpool gstbufferpool.c:305:do_alloc_buffer:<bufferpool0> alloc function failed
0:01:08.716979847 65019 0xaaab1d8a7a90 WARN bufferpool gstbufferpool.c:338:default_start:<bufferpool0> failed to allocate buffer
0:01:08.716985063 65019 0xaaab1d8a7a90 ERROR bufferpool gstbufferpool.c:559:gst_buffer_pool_set_active:<bufferpool0> start failed
0:01:08.716995463 65019 0xaaab1d8a7a90 WARN nvinfer gstnvinfer.cpp:985:gst_nvinfer_start:<secondary_gie_2> error: Failed to set buffer pool to active
0:01:08.722347831 65019 0xaaab1d8a7a90 WARN GST_PADS gstpad.c:1142:gst_pad_set_active:<secondary_gie_2:sink> Failed to activate pad
** ERROR: <main:716>: Failed to set pipeline to PAUSED
Quitting
nvstreammux: Successfully handled EOS for source_id=0
nvstreammux: Successfully handled EOS for source_id=1
nvstreammux: Successfully handled EOS for source_id=2
nvstreammux: Successfully handled EOS for source_id=3
ERROR from secondary_gie_2: Failed to set buffer pool to active
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(985): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:secondary_gie_bin/GstNvInfer:secondary_gie_2
X Error of failed request: BadRequest (invalid request code or no such operation)
Major opcode of failed request: 155 ()
Minor opcode of failed request: 1
Serial number of failed request: 20
Current serial number in output stream: 20
I additionally tried disabling the sinks and setting the sink to fakesink with no success. (Same errors)
I came across the following post (Deepstream sample code error in jetson xavier NX) and it appears to be a very similar issue. The fix was to attach a monitor. I want to be able to run deepstream remotely over ssh and would like another way to get this to work. I have the agx remotely installed currently, but I could access it and attach a monitor to verify that it fixes the problem.
Any help would be greatly appreciated.