# Deepstream error

**URL:** <https://forums.developer.nvidia.com/t/deepstream-error/279996>\
**Category:** DeepStream SDK\
**Created:** [January 24, 2024, 12:57pm UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996 "2024-01-24T12:57:24Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![varuns20](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@varuns20](https://forums.developer.nvidia.com/u/varuns20)\
**Post date:** [January 24, 2024, 12:57pm UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/1 "2024-01-24T12:57:24Z")

</div>

**• 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

**Ihave create a own config file when i run deepstream-app -c test\_by\_varun2.txt**

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds\_nvmultiobjecttracker.so  
[NvMultiObjectTracker] Initialized  
WARNING: …/nvdsinfer/nvdsinfer\_model\_builder.cpp:1487 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b4\_gpu0\_int8.engine open error  
0:00:06.207236878 3987 0x5597f2af64c0 WARN nvinfer gstnvinfer.cpp:679:gst\_nvinfer\_logger:\<primary\_gie\> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() \<nvdsinfer\_context\_impl.cpp:2080\> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b4\_gpu0\_int8.engine failed  
0:00:06.411229541 3987 0x5597f2af64c0 WARN nvinfer gstnvinfer.cpp:679:gst\_nvinfer\_logger:\<primary\_gie\> 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/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b4\_gpu0\_int8.engine failed, try rebuild  
0:00:06.411261008 3987 0x5597f2af64c0 INFO nvinfer gstnvinfer.cpp:682:gst\_nvinfer\_logger:\<primary\_gie\> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() \<nvdsinfer\_context\_impl.cpp:2106\> [UID = 1]: Trying to create engine from model files  
NvDsInferCudaEngineGetFromTltModel: Failed to open TLT encoded model file /opt/nvidia/deepstream/deepstream-6.4/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine  
ERROR: …/nvdsinfer/nvdsinfer\_model\_builder.cpp:728 Failed to create network using custom network creation function  
ERROR: …/nvdsinfer/nvdsinfer\_model\_builder.cpp:794 Failed to get cuda engine from custom library API  
0:00:11.685071568 3987 0x5597f2af64c0 ERROR nvinfer gstnvinfer.cpp:676:gst\_nvinfer\_logger:\<primary\_gie\> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() \<nvdsinfer\_context\_impl.cpp:2126\> [UID = 1]: build engine file failed  
free(): double free detected in tcache 2  
Aborted (core dumped)

**this is my file test\_by\_varun2.txt**

#This code is made by Varun  
#Get mesurement and get metadata outputs  
[application]  
enable-perf-measurement=1  
perf-measurement-interval-sec=3  
gie-kitti-output-dir=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/meta/gie/  
kitti-track-output-dir=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/meta/track/  
reid-track-output-dir=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/meta/trackout/  
terminated-track-output-dir=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/meta/termtrack/

#the output display type  
[tiled-display]  
enable=1  
rows=1  
columns=1  
width=1280  
height=720  
gpu-id=0  
nvbuf-memory-type=0

#The path for the video file  
[source0]  
enable=1  
type=3  
uri=file://…/stream/face.mp4  
gpu-id=0  
num-sources=1  
cudadec-memtype=0

#Basic sink  
[sink0]  
enable=1  
type=2  
sync=1  
source-id=0  
gpu-id=0  
nvbuf-memory-type=0  
#Encode and file saver  
[sink1]  
enable=0  
type=3  
container=1  
codec=1  
enc-type=0  
sync=0  
bitrate=2000000  
profile=0  
output-file=out.mp4  
source-id=0  
#For RTSP streamming  
[sink2]  
enable=0  
type=4  
codec=1  
enc-type=0  
sync=0  
bitrate=400000  
profile=0  
rtsp-port=8554  
udp-port=5400

#For overlays text and rectangles in video frame  
[osd]  
enable=1  
gpu-id=0  
border-width=1  
text-size=15  
text-color=1;1;1;1;  
text-bg-color=0.3;0.3;0.3;1  
font=Serif  
show-clock=0  
clock-x-offset=800  
clock-y-offset=820  
clock-text-size=12  
clock-color=1;0;0;0  
nvbuf-memory-type=0

[streammux]  
gpu-id=0  
live-source=0  
buffer-pool-size=1  
batch-size=1  
batched-push-timeout=40000  
width=1920  
height=1080  
enable-padding=0  
nvbuf-memory-type=0  
attach-sys-ts-as-ntp=1

#the Pre proceesing part is being skipped

#config for gie section Here lies the main model codes which are going to be implemented  
[primary-gie]  
enable=1  
gpu-id=0  
gie-unique-id=1  
model-engine-file=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b4\_gpu0\_int8.engine  
batch-size=1  
bbox-border-color0=1;0;0;1  
bbox-border-color1=0;1;1;1  
bbox-border-color2=0;0;1;1  
bbox-border-color3=0;1;0;1  
interval=0  
nvbuf-memory-type=0  
config-file=config\_infer\_primary\_gie2.txt

[tracker]  
enable=1  
tracker-width=960  
tracker-height=544  
ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds\_nvmultiobjecttracker.so  
ll-config-file=config\_tracker\_NvDCF\_perf.yml  
gpu-id=0  
display-tracking-id=1

[tests]  
file-loop=0

**this is primary infer file**

[property]  
gpu-id=0  
net-scale-factor=0.00392156862745098  
tlt-model-key=tlt\_encode  
tlt-encoded-model=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine  
model-engine-file=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b30\_gpu0\_int8.engine  
labelfile-path=/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test\_by\_varun/model/Peoplenet/labels.txt  
int8-calib-file=/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.txt  
batch-size=30  
process-mode=1  
model-color-format=0  
cluster-mode=2  
infer-dims=3;544;960  
network-mode=0  
num-detected-classes=4  
interval=0  
gie-unique-id=1  
uff-input-order=0  
uff-input-blob-name=input\_1  
output-blob-names=output\_cov/Sigmoid;output\_bbox/BiasAdd  
force-implicit-batch-dim=1  
#parse-bbox-func-name=NvDsInferParseCustomResnet  
#custom-lib-path=/path/to/this/directory/libnvds\_infercustomparser.so

cluster-mode=2  
#scaling-filter=0  
#scaling-compute-hw=0  
infer-dims=3;544;960

#Use the config params below for dbscan clustering mode  
#[class-attrs-all]  
#detected-min-w=4  
#detected-min-h=4  
#minBoxes=3

#Use the config params below for NMS clustering mode  
[class-attrs-all]  
topk=20  
nms-iou-threshold=0.5  
pre-cluster-threshold=0.2

[class-attrs-0]  
topk=20  
nms-iou-threshold=0.5  
pre-cluster-threshold=0.4

**the model that i used is Peoplenet pruned\_quantized\_v2.3.2**

I am trying to build a tracking system of people using unique id

---

<div class="post-metadata">

**Author:** ![yuweiw](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yuweiw/32/101255_2.png) [@yuweiw](https://forums.developer.nvidia.com/u/yuweiw)\
**Post date:** [January 25, 2024, 6:57am UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/3 "2024-01-25T06:57:37Z")

</div>

> [@varuns20](#):
>
> file=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b4\_gpu0\_int8.engine

Could you check this property in your config file?

---

<div class="post-metadata">

**Author:** ![varuns20](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@varuns20](https://forums.developer.nvidia.com/u/varuns20)\
**Post date:** [January 25, 2024, 7:01am UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/4 "2024-01-25T07:01:48Z")

</div>

Sorry there has been a mistake while pasting the code this is the full code for primary gie

[property]  
gpu-id=0  
net-scale-factor=0.00392156862745098  
tlt-model-key=tlt\_encode  
tlt-encoded-model=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine  
model-engine-file=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine\_b30\_gpu0\_int8.engine  
labelfile-path=/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test\_by\_varun/model/Peoplenet/labels.txt  
int8-calib-file=/opt/nvidia/deepstream/deepstream-6.4/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.txt  
batch-size=30  
process-mode=1  
model-color-format=0  
cluster-mode=2  
infer-dims=3;544;960

## 0=FP32, 1=INT8, 2=FP16 mode

network-mode=0  
num-detected-classes=4  
interval=0  
gie-unique-id=1  
uff-input-order=0  
uff-input-blob-name=input\_1  
output-blob-names=output\_cov/Sigmoid;output\_bbox/BiasAdd  
force-implicit-batch-dim=1  
#parse-bbox-func-name=NvDsInferParseCustomResnet  
#custom-lib-path=/path/to/this/directory/libnvds\_infercustomparser.so

## 1=DBSCAN, 2=NMS, 3= DBSCAN+NMS Hybrid, 4 = None(No clustering)

cluster-mode=2  
#scaling-filter=0  
#scaling-compute-hw=0  
infer-dims=3;544;960

#Use the config params below for dbscan clustering mode  
#[class-attrs-all]  
#detected-min-w=4  
#detected-min-h=4  
#minBoxes=3

#Use the config params below for NMS clustering mode  
[class-attrs-all]  
topk=20  
nms-iou-threshold=0.5  
pre-cluster-threshold=0.2

## Per class configurations

[class-attrs-0]  
topk=20  
nms-iou-threshold=0.5  
pre-cluster-threshold=0.4

---

<div class="post-metadata">

**Author:** ![yuweiw](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yuweiw/32/101255_2.png) [@yuweiw](https://forums.developer.nvidia.com/u/yuweiw)\
**Post date:** [January 25, 2024, 7:12am UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/5 "2024-01-25T07:12:45Z")

</div>

> [@varuns20](#):
>
> tlt-encoded-model=/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/Peoplenet/resnet34\_peoplenet\_pruned\_int8.etlt\_b4\_gpu0\_int8.engine

Could you double check the model file? It should end with etlt.

---

<div class="post-metadata">

**Author:** ![varuns20](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@varuns20](https://forums.developer.nvidia.com/u/varuns20)\
**Post date:** [January 25, 2024, 8:22am UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/7 "2024-01-25T08:22:36Z")

</div>

Thanks a lot , it was really a silly mistake ,

And i need to know the onnx model files does it have special configuration because i tried it i got error

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds\_nvmultiobjecttracker.so  
[NvMultiObjectTracker] Initialized  
WARNING: …/nvdsinfer/nvdsinfer\_model\_builder.cpp:1487 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/peoplenet/resnet34\_peoplenet\_int8.onnx\_b4\_gpu0\_int8.engine open error  
0:00:05.965677886 411 0x55e99f9c8cc0 WARN nvinfer gstnvinfer.cpp:679:gst\_nvinfer\_logger:\<primary\_gie\> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() \<nvdsinfer\_context\_impl.cpp:2080\> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream/samples/configs/test\_by\_varun/model/peoplenet/resnet34\_peoplenet\_int8.onnx\_b4\_gpu0\_int8.engine failed  
0:00:06.166126183 411 0x55e99f9c8cc0 WARN nvinfer gstnvinfer.cpp:679:gst\_nvinfer\_logger:\<primary\_gie\> 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/samples/configs/test\_by\_varun/model/peoplenet/resnet34\_peoplenet\_int8.onnx\_b4\_gpu0\_int8.engine failed, try rebuild  
0:00:06.166141813 411 0x55e99f9c8cc0 INFO nvinfer gstnvinfer.cpp:682:gst\_nvinfer\_logger:\<primary\_gie\> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() \<nvdsinfer\_context\_impl.cpp:2106\> [UID = 1]: Trying to create engine from model files  
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT\_BATCH flag whenever possible.  
ERROR: [TRT]: UffParser: Could not read buffer.  
parseModel: Failed to parse UFF model  
ERROR: tlt/tlt\_decode.cpp:359 Failed to build network, error in model parsing.  
ERROR: …/nvdsinfer/nvdsinfer\_model\_builder.cpp:728 Failed to create network using custom network creation function  
ERROR: …/nvdsinfer/nvdsinfer\_model\_builder.cpp:794 Failed to get cuda engine from custom library API  
0:00:11.506854354 411 0x55e99f9c8cc0 ERROR nvinfer gstnvinfer.cpp:676:gst\_nvinfer\_logger:\<primary\_gie\> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() \<nvdsinfer\_context\_impl.cpp:2126\> [UID = 1]: build engine file failed  
Segmentation fault (core dumped)

The model is **resnet34\_peoplenet\_int8.onnx**

---

<div class="post-metadata">

**Author:** ![yuweiw](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yuweiw/32/101255_2.png) [@yuweiw](https://forums.developer.nvidia.com/u/yuweiw)\
**Post date:** [January 26, 2024, 1:34am UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/8 "2024-01-26T01:34:31Z")

</div>

You can refer to [config\_infer\_primary\_yoloV7.txt](https://github.com/NVIDIA-AI-IOT/yolo_deepstream/blob/main/deepstream_yolo/config_infer_primary_yoloV7.txt) to learn how to set the config file with onnx.

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [February 9, 2024, 1:35am UTC](https://forums.developer.nvidia.com/t/deepstream-error/279996/9 "2024-02-09T01:35:26Z")

</div>

Closed on February 9, 2024, 1:35am UTC

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