Error in deepstream python at deepstream-imagedata-multistream-redaction

varuns20 · January 26, 2024, 12:51pm

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.4
• TensorRT Version 8.6.1.6-1+cuda12.0
• NVIDIA GPU Driver Version (valid for GPU only) 545.23.08

i am trying to run the deepstream-imagedata-multistream-redaction
in the path of /opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/deepstream_imagedata-multistream_redaction.py

I didnt change the code or done anything i was trying give 2 .mp4 file as input and i got this error

URI Inputs: [‘face.mp4’]
Frames will be saved in out_crops
Creating Pipeline

Creating streamux

Creating source_bin 0

Creating source bin
source-bin-00
/opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/deepstream_imagedata-multistream_redaction.py:304: DeprecationWarning: Gst.Element.get_request_pad is deprecated
sinkpad = streammux.get_request_pad(padname)
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating H264 Encoder
Creating H264 rtppay
Playing file [‘face.mp4’]
Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.
Adding elements to Pipeline

Linking elements in the Pipeline

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***

Starting pipeline

0:00:00.231003646 8383 0x55ff96096500 WARN 0:00:00.231025035 8383 0x55ff96096500 WARN 0:00:00.231031421 8383 0x55ff96096500 WARN 0:00:00.231037219 8383 0x55ff96096500 WARN 0:00:00.231047764 8383 0x55ff96096500 WARN 0:00:00.231053224 8383 0x55ff96096500 WARN 0:00:00.231057871 8383 0x55ff96096500 WARN 0:00:00.231062746 8383 0x55ff96096500 WARN 0:00:00.231071723 8383 0x55ff96096500 WARN 0:00:00.231076990 8383 0x55ff96096500 WARN 0:00:00.231081500 8383 0x55ff96096500 WARN 0:00:00.231086380 8383 0x55ff96096500 WARN 0:00:00.231094202 8383 0x55ff96096500 WARN 0:00:00.231099301 8383 0x55ff96096500 WARN 0:00:00.231104043 8383 0x55ff96096500 WARN 0:00:00.231108947 8383 0x55ff96096500 WARN 0:00:00.231116822 8383 0x55ff96096500 WARN 0:00:00.231122045 8383 0x55ff96096500 WARN 0:00:00.231126791 8383 0x55ff96096500 WARN 0:00:00.231131596 8383 0x55ff96096500 WARN 0:00:00.231166231 8383 0x55ff96096500 WARN 0:00:00.231172786 8383 0x55ff96096500 WARN 0:00:00.231186137 8383 0x55ff96096500 WARN 0:00:00.231195941 8383 0x55ff96096500 WARN WARNING: …/nvdsinfer/nvdsinfer_model_builder.cpp:1487 0:00:06.664777600 8383 0x55ff96096500 WARN 0:00:06.929440007 8383 0x55ff96096500 WARN 0:00:06.929543706 8383 0x55ff96096500 INFO WARNING: [TRT]: TensorRT encountered WARNING: [TRT]: If this is not the WARNING: [TRT]: Check verbose logs WARNING: [TRT]: - 49 weights are affected WARNING: [TRT]: - 26 weights are affected 0:00:57.849920068 8383 0x55ff96096500 INFO WARNING: [TRT]: The getMaxBatchSize() INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 0 INPUT kFLOAT input_1:0 1 OUTPUT kFLOAT output_cov/Sigmoid:0 2 OUTPUT kFLOAT output_bbox/BiasAdd:0 v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2985:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe minimum capture size for pixelformat YM12
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2991:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe maximum capture size for pixelformat YM12
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2985:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe minimum capture size for pixelformat Y444
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2991:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe maximum capture size for pixelformat Y444
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2985:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe minimum capture size for pixelformat P410
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2991:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe maximum capture size for pixelformat P410
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2985:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe minimum capture size for pixelformat PM10
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2991:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe maximum capture size for pixelformat PM10
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2985:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe minimum capture size for pixelformat NM12
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:sink Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2991:gst_v4l2_object_probe_caps_for_format:encoder:sink Could not probe maximum capture size for pixelformat NM12
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:src Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2985:gst_v4l2_object_probe_caps_for_format:encoder:src Could not probe minimum capture size for pixelformat H264
v4l2 gstv4l2object.c:3100:gst_v4l2_object_get_nearest_size:encoder:src Unable to try format: Unknown error -1
v4l2 gstv4l2object.c:2991:gst_v4l2_object_probe_caps_for_format:encoder:src Could not probe maximum capture size for pixelformat H264
Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine open error
nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2080> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine failed
nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2185> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine failed, try rebuild
nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2106> [UID = 1]: Trying to create engine from model files
issues when converting weights between types and that could affect accuracy.
desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
for the list of affected weights.
by this issue: Detected subnormal FP16 values.
by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2138> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_fp16.engine successfully
function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
[Implicit Engine Info]: layers num: 3
3x544x960
3x34x60
12x34x60

ERROR: [TRT]: 3: Cannot find binding of given name: output_bbox/BiasAdd
0:00:57.858082902 8383 0x55ff96096500 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_bbox/BiasAdd’ in engine
ERROR: [TRT]: 3: Cannot find binding of given name: output_cov/Sigmoid
0:00:57.858107409 8383 0x55ff96096500 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_cov/Sigmoid’ in engine
0:00:58.102451708 8383 0x55ff96096500 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:config_infer_primary_peoplenet.txt sucessfully
0:00:58.104126561 8383 0x55ff96096500 WARN uridecodebin gsturidecodebin.c:1440:gen_source_element: error: Invalid URI “face.mp4”.

**PERF: {‘stream0’: 0.0}

Error: gst-resource-error-quark: Invalid URI “face.mp4”. (3): …/gst/playback/gsturidecodebin.c(1440): gen_source_element (): /GstPipeline:pipeline0/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin
Exiting app

sys:1: Warning: g_object_get_is_valid_property: object class ‘GstUDPSrc’ has no property named ‘pt’

Please i need help asap

yingliu · January 27, 2024, 4:19am

can you share your command that starts the program? Please note that the input file should be in format as “-i file:///home/ubuntu/video1.mp4”.

varuns20 · January 27, 2024, 4:45am

I tried to use this command line
python3 deepstream_imagedata-multistream_redaction.py -i file://opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4 file://opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/testface.mp4

I get this error

URI Inputs: [‘file://opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4’, ‘file://opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/testface.mp4’]
Frames will be saved in out_crops
Creating Pipeline

Creating streamux

Creating source_bin 0

Creating source bin
source-bin-00
/opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/deepstream_imagedata-multistream_redaction.py:304: DeprecationWarning: Gst.Element.get_request_pad is deprecated
sinkpad = streammux.get_request_pad(padname)
Creating source_bin 1

Creating source bin
source-bin-01
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating H264 Encoder
Creating H264 rtppay
Playing file [‘file://opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4’, ‘file://opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/testface.mp4’]
Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.
WARNING: Overriding infer-config batch-size 1 with number of sources 2

Adding elements to Pipeline

Linking elements in the Pipeline

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***

Starting pipeline

WARNING: …/nvdsinfer/nvdsinfer_model_builder.cpp:1487 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine open error
0:00:05.599882182 232 0x563c90a5cad0 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2080> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine failed
0:00:05.793084016 232 0x563c90a5cad0 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2185> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine failed, try rebuild
0:00:05.793188097 232 0x563c90a5cad0 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2106> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: TensorRT encountered issues when converting weights between types and that could affect accuracy.
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 49 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 26 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
0:00:50.604823695 232 0x563c90a5cad0 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2138> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b2_gpu0_fp16.engine successfully
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 3
0 INPUT kFLOAT input_1:0 3x544x960 min: 1x3x544x960 opt: 2x3x544x960 Max: 2x3x544x960
1 OUTPUT kFLOAT output_cov/Sigmoid:0 3x34x60 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT output_bbox/BiasAdd:0 12x34x60 min: 0 opt: 0 Max: 0

ERROR: [TRT]: 3: Cannot find binding of given name: output_bbox/BiasAdd
0:00:50.610673081 232 0x563c90a5cad0 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_bbox/BiasAdd’ in engine
ERROR: [TRT]: 3: Cannot find binding of given name: output_cov/Sigmoid
0:00:50.610705189 232 0x563c90a5cad0 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_cov/Sigmoid’ in engine
0:00:50.810000821 232 0x563c90a5cad0 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:config_infer_primary_peoplenet.txt sucessfully
Decodebin child added: source

Decodebin child added: decodebin0

**PERF: {‘stream0’: 0.0, ‘stream1’: 0.0}

Error: gst-resource-error-quark: Resource not found. (3): …/gst/gio/gstgiosrc.c(536): gst_gio_src_get_stream (): /GstPipeline:pipeline0/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstGioSrc:source:
Could not open location file:///nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4 for reading: Error opening file /nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4: No such file or directory
Exiting app

The previous command is
python3 deepstream_imagedata-multistream_redaction.py -i ./face.mp4 ./testface.mp4

actually i put the test video file in the same directory
I get this error

ERROR: [TRT]: 3: Cannot find binding of given name: output_bbox/BiasAdd
0:00:50.044478796 265 0x5619322cb8d0 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_bbox/BiasAdd’ in engine
ERROR: [TRT]: 3: Cannot find binding of given name: output_cov/Sigmoid
0:00:50.044513598 265 0x5619322cb8d0 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_cov/Sigmoid’ in engine
0:00:50.243795154 265 0x5619322cb8d0 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:config_infer_primary_peoplenet.txt sucessfully

**PERF: {‘stream0’: 0.0, ‘stream1’: 0.0}

Error: gst-resource-error-quark: Invalid URI “./face.mp4”. (3): …/gst/playback/gsturidecodebin.c(1440): gen_source_element (): /GstPipeline:pipeline0/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin
Exiting app

yingliu · January 27, 2024, 5:04am

Does the file /nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4 exist? should it be /opt/nvidia/....?
You can try the sample video, such as python3 deepstream_imagedata-multistream_redaction.py -i file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 -c H264.

varuns20 · January 27, 2024, 5:19am

python3 deepstream_imagedata-multistream_redaction.py -i file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 -c H264

this line was working and i am trying to work with my video

python3 deepstream_imagedata-multistream_redaction.py -i file:///opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4 -c H264

The code ran but i didnt get any rtsp output

And i want to run multiple stream , and i want to know what is the problem ?

yingliu · January 27, 2024, 10:01am

So with the sample I provided it can work and you can see the RTSP stream?

What encoding method is used in your mp4 file?

You can use python3 deepstream_imagedata-multistream_redaction.py -i <uri1> [uri2] ... [uriN] -c {H264,H265} -b BITRATE to run multiple streams , you can refer to the README file.

varuns20 · January 27, 2024, 10:12am

yes i can see the video the sample which you provided . The video i use has h264 encoding

yingliu · January 27, 2024, 11:24am

Please provide the full log when running with your video.

varuns20 · January 27, 2024, 11:38am

URI Inputs: [‘file:///opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4’, ‘file:///opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/testface.mp4’]
Frames will be saved in out_crops
Creating Pipeline

Creating streamux

Creating source_bin 0

Creating source bin
source-bin-00
/opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/deepstream_imagedata-multistream_redaction.py:304: DeprecationWarning: Gst.Element.get_request_pad is deprecated
sinkpad = streammux.get_request_pad(padname)
Creating source_bin 1

Creating source bin
source-bin-01
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating H264 Encoder
Creating H264 rtppay
Playing file [‘file:///opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/face.mp4’, ‘file:///opt/nvidia/deepstream/deepstream-6.4/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream-redaction/testface.mp4’]
Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.
WARNING: Overriding infer-config batch-size 1 with number of sources 2

Adding elements to Pipeline

Linking elements in the Pipeline

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***

Starting pipeline

WARNING: …/nvdsinfer/nvdsinfer_model_builder.cpp:1487 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine open error
0:00:06.502369949 6157 0x561acda9c900 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2080> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine failed
0:00:06.768776869 6157 0x561acda9c900 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2185> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine failed, try rebuild
0:00:06.771445720 6157 0x561acda9c900 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2106> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: TensorRT encountered issues when converting weights between types and that could affect accuracy.
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 49 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 26 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
0:00:55.083898763 6157 0x561acda9c900 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2138> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test_by_varun/model/peoplenet/resnet34_peoplenet_int8.onnx_b2_gpu0_fp16.engine successfully
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 3
0 INPUT kFLOAT input_1:0 3x544x960 min: 1x3x544x960 opt: 2x3x544x960 Max: 2x3x544x960
1 OUTPUT kFLOAT output_cov/Sigmoid:0 3x34x60 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT output_bbox/BiasAdd:0 12x34x60 min: 0 opt: 0 Max: 0

ERROR: [TRT]: 3: Cannot find binding of given name: output_bbox/BiasAdd
0:00:55.090469209 6157 0x561acda9c900 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_bbox/BiasAdd’ in engine
ERROR: [TRT]: 3: Cannot find binding of given name: output_cov/Sigmoid
0:00:55.090507296 6157 0x561acda9c900 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:2059> [UID = 1]: Could not find output layer ‘output_cov/Sigmoid’ in engine
0:00:55.340839218 6157 0x561acda9c900 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:config_infer_primary_peoplenet.txt sucessfully
Decodebin child added: source

Decodebin child added: decodebin0

Decodebin child added: source

Decodebin child added: decodebin1

**PERF: {‘stream0’: 0.0, ‘stream1’: 0.0}

Decodebin child added: qtdemux0

Decodebin child added: qtdemux1

Decodebin child added: multiqueue0

Decodebin child added: multiqueue1

Decodebin child added: aacparse0

Decodebin child added: h264parse0

Decodebin child added: capsfilter0

Decodebin child added: aacparse1

Decodebin child added: avdec_aac0

Decodebin child added: avdec_aac1

Decodebin child added: h264parse1

Decodebin child added: capsfilter1

Decodebin child added: nvv4l2decoder0

Decodebin child added: nvv4l2decoder1

In cb_newpad

Frame Number= 0 Number of Objects= 0 Face_count= 0 Person_count= 0
Frame Number= 0 Number of Objects= 0 Face_count= 0 Person_count= 0
Frame Number= 1 Number of Objects= 0 Face_count= 0 Person_count= 0
Frame Number= 1 Number of Objects= 0 Face_count= 0 Person_count= 0
…
**PERF: {‘stream0’: 15.17, ‘stream1’: 15.17}

Frame Number= 65 Number of Objects= 2 Face_count= 1 Person_count= 1
Frame Number= 65 Number of Objects= 0 Face_count= 0 Person_count= 0
Frame Number= 66 Number of Objects= 2 Face_count= 1 Person_count= 1
Frame Number= 66 Number of Objects= 0 Face_count= 0 Person_count= 0
Frame Number= 67 Number of Objects= 2 Face_count= 1 Person_count= 1
Frame Number= 67 Number of Objects= 0 Face_count= 0 Person_count= 0
…
nvstreammux: Successfully handled EOS for source_id=1
Frame Number= 2728 Number of Objects= 0 Face_count= 0 Person_count= 0
End-of-stream
Exiting app

yingliu · January 27, 2024, 11:57am

The log shows the RTSP server is working all 2728 frames have been processed, I don’t understand why it cannot play RTSP stream, you may compare with the working log to find the difference.

system · February 10, 2024, 11:57am

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.

Topic		Replies	Views
Deepstream6.4 in Ubuntu24 Pipeline Not running DeepStream SDK	19	311	July 23, 2024
Issues with running inference on multiple rtsp streams in deepstream-imagedata-multistream DeepStream SDK jetson-inference	24	666	August 7, 2024
Deepstream python sample"deepstream-test1" does not run DeepStream SDK cuda , gstreamer	10	386	September 5, 2023
Get errors when running deepstream-imagedata-multistream application DeepStream SDK	7	387	October 13, 2023
How we can run deepstream-3d-action-recognition using Python? DeepStream SDK gstreamer , deepstream , deepstream61	14	1115	March 15, 2023
Deepstream python app for MJPG stream DeepStream SDK gstreamer	9	2419	September 7, 2023
RTSP streams working in deepstream, RTMP streams giving error: streaming stopped, reason not-linked (-1) DeepStream SDK tensorrt , cuda , ubuntu , gstreamer , docker , python , deepstream	41	65	March 7, 2025
Running the pretrained tao models with usb camera DeepStream SDK	34	1855	April 15, 2023
DeepStream 1.1.8 demo app deepstream-test1 failed DeepStream SDK cudnn , jetson , deepstream	7	21	December 30, 2024
Deepstream_test_1.py doesn`t work DeepStream SDK	23	1592	December 12, 2022

Error in deepstream python at deepstream-imagedata-multistream-redaction

Related topics