I am using jetson agx orin with deepstream 7.0. when i run projects example i get this error:
0:00:00.145821669 7747 0xaaab0892c470 ERROR nvvideodisplay display_x11.c:77:gst_nv_video_display_x11_new: failed to open X11 display connection
0:00:00.145890916 7747 0xaaab0892c470 ERROR nvvideodisplay display.c:105:gst_nv_video_display_new: couldn't create display. GST_NV_VIDEO_WINSYS = (null)
0:00:00.145924228 7747 0xaaab0892c470 ERROR nv3dsink gstnv3dsink.c:245:gst_nv3dsink_start:<nv3d-sink> failed to create new display
0:00:00.145937315 7747 0xaaab0892c470 WARN basesink gstbasesink.c:5878:gst_base_sink_change_state:<nv3d-sink> error: Failed to start
Error: gst-core-error-quark: GStreamer error: state change failed and some element failed to post a proper error message with the reason for the failure. (4): ../libs/gst/base/gstbasesink.c(5878): gst_base_sink_change_state (): /GstPipeline:pipeline0/GstNv3dSink:nv3d-sink:
Failed to start
Exiting app
I use the Jetson with virtual display (es.vnc). I run this example with GST_DEBUG=3 python3 deepstream_test_3.py -i /opt/nvidia/deepstream/deepstream-7.0/samples/streams/sample_720p.h264
If i change DISPLAY env in 1001 this example return this warn:
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
WARNING: [TRT]: Missing scale and zero-point for tensor output_bbox/bias, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor conv1/kernel, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor conv1/bias, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/moving_variance, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/Reshape_1/shape, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/batchnorm/add/y, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/gamma, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/Reshape_3/shape, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/beta, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/Reshape_2/shape, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/moving_mean, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor bn_conv1/Reshape/shape, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor block_1a_conv_1/kernel, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
WARNING: [TRT]: Missing scale and zero-point for tensor block_1a_conv_1/bias, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
And crash with this error:
ferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2136> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-7.0/samples/models/Primary_Detector/resnet18_trafficcamnet.etlt_b1_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x544x960
1 OUTPUT kFLOAT output_bbox/BiasAdd 16x34x60
2 OUTPUT kFLOAT output_cov/Sigmoid 4x34x60
nvbufsurface: Failed to create EGLImage.
0:02:06.727235878 8992 0xaaaaeb3ff440 ERROR nvinferallocator gstnvinfer_allocator.cpp:107:gst_nvinfer_allocator_alloc: Error: Could not map EglImage from NvBufSurface for nvinfer
0:02:06.727268103 8992 0xaaaaeb3ff440 WARN GST_BUFFER gstbuffer.c:958:gst_buffer_new_allocate: failed to allocate 88 bytes
0:02:06.727295176 8992 0xaaaaeb3ff440 WARN bufferpool gstbufferpool.c:318:do_alloc_buffer:<bufferpool0> alloc function failed
0:02:06.727304425 8992 0xaaaaeb3ff440 WARN bufferpool gstbufferpool.c:351:default_start:<bufferpool0> failed to allocate buffer
0:02:06.727311945 8992 0xaaaaeb3ff440 ERROR bufferpool gstbufferpool.c:572:gst_buffer_pool_set_active:<bufferpool0> start failed
0:02:06.727325385 8992 0xaaaaeb3ff440 WARN nvinfer gstnvinfer.cpp:1008:gst_nvinfer_start:<primary-inference> error: Failed to set buffer pool to active
0:02:06.737512057 8992 0xaaaaeb3ff440 WARN GST_PADS gstpad.c:1141:gst_pad_set_active:<primary-inference:sink> Failed to activate pad
**PERF: {'stream0': 0.0}
Error: gst-resource-error-quark: Failed to set buffer pool to active (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1008): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference
Exiting app