I'm not getting the output

[muzair1103]

I'm not sure what's going wrong. can you please help me out @zhouyuchong

root@omen16:~/face-recognition-deepstream/test# python3 face_test_demo.py
--------- start app
Unknown or legacy key specified 'alignment' for group [property]
Unknown or legacy key specified 'user-meta' for group [property]
localhost;9092;deepstream
(True, 'success, state ')

set index of src task-0 to 0
add set return :
Starting pipeline

**PERF: {'stream0': 0.0}

WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:06.875435534 4930 0x57447a9e2b60 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 2]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2095> [UID = 2]: deserialized trt engine from :/root/face-recognition-deepstream/models/arcface_weights/arcfaceresnet100-8.onnx_b1_gpu0_fp16.engine
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:612 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT data 3x112x112
1 OUTPUT kFLOAT fc1 512

0:00:06.997348438 4930 0x57447a9e2b60 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 2]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2198> [UID = 2]: Use deserialized engine model: /root/face-recognition-deepstream/models/arcface_weights/arcfaceresnet100-8.onnx_b1_gpu0_fp16.engine
0:00:07.001029419 4930 0x57447a9e2b60 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus: [UID 2]: Load new model:/root/face-recognition-deepstream/src/kbds/configs/face/config_arcface.txt sucessfully
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
[NvTrackerParams::getConfigRoot()] !!![WARNING] File doesn't exist. Will go ahead with default values
[NvMultiObjectTracker] Initialized
0:00:07.013959838 4930 0x57447a9e2b60 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1244> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5

**PERF: {'stream0': 0.0}

0:00:11.112644081 4930 0x57447a9e2b60 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2095> [UID = 1]: deserialized trt engine from :/root/face-recognition-deepstream/models/retinaface/retinaface_resnet50.onnx_b1_gpu0_fp16.engine
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:612 [Implicit Engine Info]: layers num: 4
0 INPUT kFLOAT input0 3x640x640
1 OUTPUT kFLOAT output0 16800x4
2 OUTPUT kFLOAT 839 16800x10
3 OUTPUT kFLOAT 840 16800x2

0:00:11.233843179 4930 0x57447a9e2b60 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2198> [UID = 1]: Use deserialized engine model: /root/face-recognition-deepstream/models/retinaface/retinaface_resnet50.onnx_b1_gpu0_fp16.engine
0:00:11.238144005 4930 0x57447a9e2b60 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus: [UID 1]: Load new model:/root/face-recognition-deepstream/src/kbds/configs/face/config_retinaface.txt sucessfully
(True, 'success')
gstname= video/x-raw
pad name: sink_0
Decodebin linked to pipeline
mimetype is video/x-raw
src:
source_bin: <gi.GstURIDecodeBin object at 0x7cb6401f1c00 (GstURIDecodeBin at 0x57447a9d80a0)>

ERROR: Batch size not 1
0:00:12.279373687 4930 0x5744d91183f0 WARN nvinfer gstnvinfer.cpp:2420:gst_nvinfer_output_loop: error: Internal data stream error.
0:00:12.279398454 4930 0x5744d91183f0 WARN nvinfer gstnvinfer.cpp:2420:gst_nvinfer_output_loop: error: streaming stopped, reason error (-5)
Traceback (most recent call last):
File "/root/face-recognition-deepstream/test/../src/kbds/core/pipeline.py", line 122, in bus_call_abs
search_index = search_index[0].split('-')[2][:-1]
TypeError: 'NoneType' object is not subscriptable
detect face-0 with resolution 40x44

**PERF: {'stream0': 1.61}

set index of src task-5 to 1
add set return :
(True, 'success')
src:
source_bin: <gi.GstURIDecodeBin object at 0x7cb693d9f440 (GstURIDecodeBin at 0x57448c60f7a0)>

gstname= video/x-raw
pad name: sink_1
Decodebin linked to pipeline

**PERF: {'stream0': 0.0}

get status of task-5: (True, 'success', <kbds.core.source.Stream object at 0x7cb63fe6f640>)
get status of task-1111: (False, 'source id(task-1111) not exist', None)

**PERF: {'stream0': 0.0}

======== delete src test =======
delete finished

**PERF: {'stream0': 0.0}

======== delete src test =======

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

**PERF: {'stream0': 0.0}

[zhouyuchong]

@muzair1103 seems your onnx is generated with batch size 1, you should set nvstreammux and nvinfer bs to 1 as well.

[muzair1103]

@zhouyuchong the issue still did not get solved

[zhouyuchong]

@muzair1103 your infer can only support batchsize 1, however, you have 2 sources input to pipeline.

[muzair1103]

@zhouyuchong after the latest commit I’m trying to run the pipeline. Can I get the onnx models pls

[zhouyuchong]

@muzair1103 both models are generated use links in readme. You can download retinaface here, as for arcface, the tensorrtx directly uses wts weights. After all, it's not complicated.