SSD not parsing through

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU)**T4
• DeepStream Version5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version7.0
**• NVIDIA GPU Driver Version (valid for GPU only)**440

deepstream-app -c deepstream_app_config_ssd.txt
Warn: ‘threshold’ parameter has been deprecated. Use ‘pre-cluster-threshold’ instead.
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:34 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:03.530165977 4181 0x563a65f4d490 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1577> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_SSD/ssd_trt2.trt
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT data 3x300x300
1 OUTPUT kFLOAT detection_out 1x200x7
2 OUTPUT kFLOAT keep_count 1x1x1

0:00:03.530262131 4181 0x563a65f4d490 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1681> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_SSD/ssd_trt2.trt
0:00:03.533652938 4181 0x563a65f4d490 INFO nvinfer gstnvinfer_impl.cpp:311:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_SSD/config_infer_primary_ssd.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

p: Pause
r: Resume

**PERF: FPS 0 (Avg)
**PERF: 0.00 (0.00)
** INFO: <bus_callback:181>: Pipeline ready

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

0:00:03.724897569 4181 0x563a589729e0 ERROR nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::parseBoundingBox() <nvdsinfer_context_impl_output_parsing.cpp:59> [UID = 1]: Could not find output coverage layer for parsing objects
0:00:03.724930486 4181 0x563a589729e0 ERROR nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::fillDetectionOutput() <nvdsinfer_context_impl_output_parsing.cpp:573> [UID = 1]: Failed to parse bboxes

Help me solve this issue. Where should I edit and what should I edit.
PS I took the model and deploy.prototxt from models_VGGNet_VOC0712_SSD_300x300.tar.gz - Google Drive

3

@GalibaSashi

It seems you have tried to compile and run this sample, right?
/where_deepstream_installed/sources/objectDetector_SSD

Have you done any different configurations or any changes to the SSD model referred by this sample?

4

I changed the output layers in the customparse_bbox.cpp to detection_out and keep_count. I have sent you the model files through link before.Also changed flatten layers to reshape and added top:“keep_count” in it.
Kindly can you do from your side an if you are able to get the output from your side.

6

Tracking at When running example of Objectdetector_SSD after creating engine segmentation faults occurs but video is seen