Unknown key 'blur-objects' for group [ds-example]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.0
• NVIDIA GPU Driver Version (valid for GPU only) 10.2

I have been trying to run the ds-example with
deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
appended with:

...
[sink1]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=3
...

[ds-example]
enable=1
processing-width=640
processing-height=480
full-frame=0
blur-objects=1
unique-id=15

(because I want to see the Opencv Blur effect)

and get the output:
** WARN: <parse_dsexample:772>: Unknown key ‘blur-objects’ for group [ds-example]
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.546090929 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 6]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 20x1x1

0:00:02.546182055 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 6]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.548794897 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<secondary_gie_2> [UID 6]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_secondary_carmake.txt sucessfully
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.577286149 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_1> NvDsInferContext[UID 5]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 5]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarColor/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 12x1x1

0:00:02.577338166 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_1> NvDsInferContext[UID 5]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 5]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarColor/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.579515809 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<secondary_gie_1> [UID 5]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_secondary_carcolor.txt sucessfully
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.601238586 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 4]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 6x1x1

0:00:02.601289301 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 4]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.603915046 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<secondary_gie_0> [UID 4]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_secondary_vehicletypes.txt sucessfully
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_mot_klt.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is OFF
gstnvtracker: Past frame output is OFF
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.631880779 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b4_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40

0:00:02.631935143 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b4_gpu0_int8.engine
0:00:02.633520494 59730 0x55b0788a28a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_primary.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

    p: Pause
    r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.

** INFO: <bus_callback:181>: Pipeline ready

** INFO: <bus_callback:167>: Pipeline running

KLT Tracker Init

**PERF: FPS 0 (Avg)
**PERF: 74.10 (73.60)
**PERF: 65.69 (68.07)
**PERF: 82.56 (74.09)
**PERF: 72.35 (73.59)
**PERF: 26.86 (62.99)
** INFO: <bus_callback:204>: Received EOS. Exiting …

Quitting
App run successful

===============================================================================================
I recompiled the dsexample plugin with USE_OPTIMIZED_DSEXAMPLE?=0

Then, I did the changes in

/opt/nvidia/deepstream/deepstream/sources/apps/apps-common/includes/deepstream_dsexample.h

  typedef struct
  {
    // Create a bin for the element only if enabled
    gboolean enable;
    // Struct members to store config / properties for the element
    gboolean full_frame;
    gint processing_width;
    gint processing_height;
    guint unique_id;
    guint gpu_id;
    // For nvvidconv
    guint nvbuf_memory_type;
+  gboolean blur_objects;
  } NvDsDsExampleConfig;

/opt/nvidia/deepstream/deepstream/sources/apps/apps-common/src/deepstream_dsexample.c

    g_object_set (G_OBJECT (bin->elem_dsexample),
        "full-frame", config->full_frame,
        "processing-width", config->processing_width,
        "processing-height", config->processing_height,
        "unique-id", config->unique_id,
 +     "blur-objects", config->blur_objects,
        "gpu-id", config->gpu_id, NULL);

/opt/nvidia/deepstream/deepstream/sources/apps/apps-common/src/deepstream_config_file_parser.c

+ #define CONFIG_GROUP_DSEXAMPLE_BLUR_OBJECTS "blur-objects"

  gboolean
  parse_dsexample (NvDsDsExampleConfig *config, GKeyFile *key_file)
  {
    gboolean ret = FALSE;
    gchar **keys = NULL;
    gchar **key = NULL;
    GError *error = NULL;

    keys = g_key_file_get_keys (key_file, CONFIG_GROUP_DSEXAMPLE, NULL, &error);
    CHECK_ERROR (error);
    for (key = keys; *key; key++) {
      if (!g_strcmp0 (*key, CONFIG_GROUP_ENABLE)) {
        config->enable =
          g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
              CONFIG_GROUP_ENABLE, &error);
        CHECK_ERROR (error);
      } else if (!g_strcmp0 (*key, CONFIG_GROUP_DSEXAMPLE_FULL_FRAME)) {
        config->full_frame =
          g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
              CONFIG_GROUP_DSEXAMPLE_FULL_FRAME, &error);
        CHECK_ERROR (error);
      } else if (!g_strcmp0 (*key, CONFIG_GROUP_DSEXAMPLE_PROCESSING_WIDTH)) {
        config->processing_width =
          g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
              CONFIG_GROUP_DSEXAMPLE_PROCESSING_WIDTH, &error);
        CHECK_ERROR (error);
      } else if (!g_strcmp0 (*key, CONFIG_GROUP_DSEXAMPLE_PROCESSING_HEIGHT)) {
        config->processing_height =
          g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
              CONFIG_GROUP_DSEXAMPLE_PROCESSING_HEIGHT, &error);
        CHECK_ERROR (error);
      } else if (!g_strcmp0 (*key, CONFIG_GROUP_DSEXAMPLE_UNIQUE_ID)) {
        config->unique_id =
          g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
              CONFIG_GROUP_DSEXAMPLE_UNIQUE_ID, &error);
        CHECK_ERROR (error);
      } else if (!g_strcmp0 (*key, CONFIG_GROUP_DSEXAMPLE_GPU_ID)) {
        config->gpu_id =
          g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
              CONFIG_GROUP_DSEXAMPLE_GPU_ID, &error);
        CHECK_ERROR (error);
+    } else if (!g_strcmp0 (*key, CONFIG_GROUP_DSEXAMPLE_BLUR_OBJECTS)) {
+      config->blur_objects = 
+        g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
+              CONFIG_GROUP_DSEXAMPLE_BLUR_OBJECTS, &error);
+      CHECK_ERROR (error);
      } else if (!g_strcmp0 (*key, CONFIG_NVBUF_MEMORY_TYPE)) {
        config->nvbuf_memory_type =
            g_key_file_get_integer (key_file, CONFIG_GROUP_DSEXAMPLE,
            CONFIG_NVBUF_MEMORY_TYPE, &error);
        CHECK_ERROR (error);
      } else {
        NVGSTDS_WARN_MSG_V ("Unknown key '%s' for group [%s]", *key,
            CONFIG_GROUP_DSEXAMPLE);
      }
    }

and recompiled the deepstream-app

./deepstream-app …/…/…/…/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt

** ERROR: main:605: Specify config file with -c option
Quitting
App run failed
(pytorch1.6.0a0) root@VM-0-4-ubuntu:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-app# ./deepstream-app -c …/…/…/…/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.518027735 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 6]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 20x1x1

0:00:02.518128806 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 6]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.520773227 62985 0x563570c324a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<secondary_gie_2> [UID 6]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_secondary_carmake.txt sucessfully
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.548985632 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_1> NvDsInferContext[UID 5]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 5]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarColor/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 12x1x1

0:00:02.549039513 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_1> NvDsInferContext[UID 5]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 5]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_CarColor/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.551198344 62985 0x563570c324a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<secondary_gie_1> [UID 5]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_secondary_carcolor.txt sucessfully
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.572680703 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 4]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input_1 3x224x224
1 OUTPUT kFLOAT predictions/Softmax 6x1x1

0:00:02.572728730 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 4]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.575250598 62985 0x563570c324a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<secondary_gie_0> [UID 4]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_secondary_vehicletypes.txt sucessfully
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_mot_klt.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is OFF
gstnvtracker: Past frame output is OFF
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:02.602883277 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b4_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40

0:00:02.602932484 62985 0x563570c324a0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b4_gpu0_int8.engine
0:00:02.604420289 62985 0x563570c324a0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_primary.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

    p: Pause
    r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.

** INFO: <bus_callback:181>: Pipeline ready

** INFO: <bus_callback:167>: Pipeline running

ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
KLT Tracker Init
ERROR from dsexample0: input format should be RGBA when using blur-objects property
Debug info: gstdsexample.cpp(474): gst_dsexample_set_caps (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
Quitting
App run failed

Now I’v changed:
/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-dsexample/gstdsexample.cpp

GST_STATIC_PAD_TEMPLATE ("sink",
    GST_PAD_SINK,
    GST_PAD_ALWAYS,
    GST_STATIC_CAPS (GST_VIDEO_CAPS_MAKE_WITH_FEATURES
        (GST_CAPS_FEATURE_MEMORY_NVMM,
-            "{ NV12, RGBA, I420 }")));
+            "{ RGBA, I420 }")));

static GstStaticPadTemplate gst_dsexample_src_template =
GST_STATIC_PAD_TEMPLATE ("src",
    GST_PAD_SRC,
    GST_PAD_ALWAYS,
    GST_STATIC_CAPS (GST_VIDEO_CAPS_MAKE_WITH_FEATURES
        (GST_CAPS_FEATURE_MEMORY_NVMM,
-            "{ NV12, RGBA, I420 }")));
+            "{ RGBA, I420 }")));

but got another error:
KLT Tracker Init
Surface MemType: 0
ERROR from dsexample0: gst_dsexample_transform_ip:need NVBUF_MEM_CUDA_UNIFIED memory for opencv blurring
Debug info: gstdsexample.cpp(752): gst_dsexample_transform_ip (): /GstPipeline:pipeline/GstBin:dsexample_bin/GstDsExample:dsexample0
Quitting
App run failed

Can you try adding “nvbuf-memory-type=3” into “[ds-example]” part in your configuration file?

Yes, I’ve set “nvbuf-memory-type=3” for nvconv and that works, thank you