No Secondary Inference Data in MQTT

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi, I am trying to access send Secondary Inference data to Kafka/MQTT. But the data appear to be empty. I changed the model-used parameter as:

APP_CONFIG_ANALYTICS_MODELS_UNKNOWN -> APP_CONFIG_ANALYTICS_RESNET_PGIE_3SGIE_TYPE_COLOR_MAKE

I also changed the Payload schema, but couldn’t see any results. Can you suggest how to send secondary inference data over Kafka?

2

We are checking internally and will give you reply ASAP.

3

You may refer to
/opt/nvidia/deepstream/deepstream-4.0/sources/apps/sample_apps/deepstream-test5/deepstream_test5_app_main.c

static void
generate_event_msg_meta (gpointer data, gint class_id, gboolean useTs,
GstClockTime ts, gchar * src_uri, gint stream_id, guint sensor_id,
NvDsObjectMeta * obj_params, float scaleW, float scaleH,
NvDsFrameMeta* frame_meta)

static void schema_fill_sample_sgie_vehicle_metadata (NvDsObjectMeta* obj_params, NvDsVehicleObject* obj)

4

I saw this. The data filled by static void schema_fill_sample_sgie_vehicle_metadata (NvDsObjectMeta* obj_params, NvDsVehicleObject* obj) is dummy. I want the actual inference data. How can I get that?

5

Hi
Could you please tell you run with default test5 or your customized? if run with your customized, suggest you verify test5 first, option -m set to 1 to let analytic processing and metadata filled.

  1. Option -m [Default=0]
    PGIE Model used; {0 - Unknown [DEFAULT]}, {1: Resnet 4-class [Car, Bicycle, Person, Roadsign]}
    ===============================================================================

This option is to demonstrate the code which can read
PGIE, Tracker, and SGIE Metadata from NvDsBatchMeta and fill
NvDsEventMsgMeta in bbox_generated_probe_after_analytics()
for the nvmsgconv schema and JSON-metadata-generation.
For more details run the below command on terminal post DS installation:
gst-inspect-1.0 nvmsgconv

NOTE: Customers using -m 0 with custom PGIE, SGIE models,
please read the documentation under “IMPORTANT Note 1” tag
in deepstream_test5_app_main.c for changes in code required
to relay SGIE Classifier-Metadata to nvmsgconv

6.1 -m 0 (Model(s) used are unknown)
$ ./deepstream-test5-app -c test5_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt -m 0

6.2 -m 1 (Analytics Model(s) used are:
resnet(4-class model) → Tracker (Optional) → SGIE0 (Vehicle-type)
→ SGIE1 (Vehicle-Color) → SGIE2 (Vehicle-Make))
$ ./deepstream-test5-app -c test5_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt -m 1