# Deepstream Python Error **URL:** \ **Category:** DeepStream SDK\ **Created:** [July 30, 2020, 12:59pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755 "2020-07-30T12:59:31Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![airpixin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@airpixin](https://forums.developer.nvidia.com/u/airpixin)\ **Post date:** [July 30, 2020, 12:59pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/1 "2020-07-30T12:59:31Z")
**Hardware Platform:** [AGX Xavier™ Developer Kit] **Software Version:** [Jetpack 4.4] Deepstream 5.0 I am getting this error while running Python Deepstream test code The Sample codes installed works ( deepstream-app -c config | works ) xxxx@xxxx-desktop:/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1$ python3 deepstream\_test\_1.py …/…/…/…/samples/streams/sample\_720p.mp4 Creating Pipeline Creating Source Creating H264Parser Creating Decoder Creating EGLSink Playing file …/…/…/…/samples/streams/sample\_720p.mp4 Warn: ‘threshold’ parameter has been deprecated. Use ‘pre-cluster-threshold’ instead. Adding elements to Pipeline Linking elements in the Pipeline Starting pipeline Using winsys: x11 Opening in BLOCKING MODE ERROR: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine open error 0:00:01.436452314 30834 0x341ea190 WARN nvinfer gstnvinfer.cpp:599:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine failed 0:00:01.436692901 30834 0x341ea190 WARN nvinfer gstnvinfer.cpp:599:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine failed, try rebuild 0:00:01.436883821 30834 0x341ea190 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() \ [UID = 1]: Trying to create engine from model files ERROR: Cannot access caffemodel file ‘/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel’ ERROR: failed to build network since parsing model errors. ERROR: failed to build network. 0:00:01.437789173 30834 0x341ea190 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() \ [UID = 1]: build engine file failed 0:00:01.437844728 30834 0x341ea190 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: build backend context failed 0:00:01.437876025 30834 0x341ea190 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() \ [UID = 1]: generate backend failed, check config file settings 0:00:01.437926108 30834 0x341ea190 WARN nvinfer gstnvinfer.cpp:781:gst\_nvinfer\_start: error: Failed to create NvDsInferContext instance 0:00:01.437951517 30834 0x341ea190 WARN nvinfer gstnvinfer.cpp:781:gst\_nvinfer\_start: error: Config file path: dstest1\_pgie\_config.txt, NvDsInfer Error: NVDSINFER\_CONFIG\_FAILED Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): /dvs/git/dirty/git-master\_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(781): gst\_nvinfer\_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference: Config file path: dstest1\_pgie\_config.txt, NvDsInfer Error: NVDSINFER\_CONFIG\_FAILED ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [July 31, 2020, 5:30am UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/3 "2020-07-31T05:30:30Z")
hI @airpixin, Try adding “force-implicit-batch-dim=1” as below. But, the offically DeepStream for Jetpack4.4 is DeepStream5.0GA which is coming very soon. [property] gpu-id=0 net-scale-factor=0.0039215697906911373 model-file=…/…/…/…/samples/models/Primary\_Detector/resnet10.caffemodel proto-file=…/…/…/…/samples/models/Primary\_Detector/resnet10.prototxt model-engine-file=…/…/…/…/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine labelfile-path=…/…/…/…/samples/models/Primary\_Detector/labels.txt int8-calib-file=…/…/…/…/samples/models/Primary\_Detector/cal\_trt.bin **force-implicit-batch-dim=1** batch-size=1 network-mode=1 num-detected-classes=4 interval=0 gie-unique-id=1 output-blob-names=conv2d\_bbox;conv2d\_cov/Sigmoid ---
**Author:** ![airpixin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@airpixin](https://forums.developer.nvidia.com/u/airpixin)\ **Post date:** [August 1, 2020, 7:09am UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/4 "2020-08-01T07:09:22Z")
Thanks , I tried what you asked for. There is no error now. But the execution is stuck at **NvMMLiteBlockCreate : Block : BlockType = 261** xxxx@xxxx-desktop:/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1$ python3 deepstream\_test\_1.py …/…/…/…/samples/streams/sample\_720p.mp4 Creating Pipeline Creating Source Creating H264Parser Creating Decoder Creating EGLSink Playing file …/…/…/…/samples/streams/sample\_720p.mp4 Warn: ‘threshold’ parameter has been deprecated. Use ‘pre-cluster-threshold’ instead. Adding elements to Pipeline Linking elements in the Pipeline Starting pipeline Using winsys: x11 Opening in BLOCKING MODE 0:00:03.100719469 10327 0x3aecab90 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine INFO: [Implicit Engine Info]: layers num: 3 0 INPUT kFLOAT input\_1 3x368x640 1 OUTPUT kFLOAT conv2d\_bbox 16x23x40 2 OUTPUT kFLOAT conv2d\_cov/Sigmoid 4x23x40 0:00:03.101016568 10327 0x3aecab90 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine 0:00:03.105303358 10327 0x3aecab90 INFO nvinfer gstnvinfer\_impl.cpp:311:notifyLoadModelStatus: [UID 1]: Load new model:dstest1\_pgie\_config.txt sucessfully NvMMLiteOpen : Block : BlockType = 261 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NvMMLiteBlockCreate : Block : BlockType = 261 ---
**Author:** ![airpixin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@airpixin](https://forums.developer.nvidia.com/u/airpixin)\ **Post date:** [August 1, 2020, 7:20am UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/5 "2020-08-01T07:20:02Z")
This is the error that i get when i change the input video file. **Error: gst-stream-error-quark: Failed to parse stream (7): gstbaseparse.c(2954): gst\_base\_parse\_check\_sync (): /GstPipeline:pipeline0/GstH264Parse:h264-parser** xxxx@xxxx-desktop:/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1$ python3 deepstream\_test\_1.py /home/xxxx/Videos/1.mp4 Creating Pipeline Creating Source Creating H264Parser Creating Decoder Creating EGLSink Playing file /home/airpixagx1/Videos/1.mp4 Warn: ‘threshold’ parameter has been deprecated. Use ‘pre-cluster-threshold’ instead. Adding elements to Pipeline Linking elements in the Pipeline Starting pipeline Using winsys: x11 Opening in BLOCKING MODE 0:00:03.108948162 10800 0x3d31b590 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine INFO: [Implicit Engine Info]: layers num: 3 0 INPUT kFLOAT input\_1 3x368x640 1 OUTPUT kFLOAT conv2d\_bbox 16x23x40 2 OUTPUT kFLOAT conv2d\_cov/Sigmoid 4x23x40 0:00:03.109184362 10800 0x3d31b590 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine 0:00:03.112393532 10800 0x3d31b590 INFO nvinfer gstnvinfer\_impl.cpp:311:notifyLoadModelStatus: [UID 1]: Load new model:dstest1\_pgie\_config.txt sucessfully Error: gst-stream-error-quark: Failed to parse stream (7): gstbaseparse.c(2954): gst\_base\_parse\_check\_sync (): /GstPipeline:pipeline0/GstH264Parse:h264-parser ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [August 2, 2020, 4:31am UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/6 "2020-08-02T04:31:45Z")
As mentioned in the README of this sample, this sample only accpets \, so you need use H264 video instead of mp4 video. Thanks! ---
**Author:** ![airpixin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@airpixin](https://forums.developer.nvidia.com/u/airpixin)\ **Post date:** [August 2, 2020, 2:35pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/7 "2020-08-02T14:35:42Z")
What about this issue ? ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [August 2, 2020, 3:12pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/8 "2020-08-02T15:12:18Z")
I have told what’s the mistake in your command. What else do you want from our side??? ---
**Author:** ![airpixin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@airpixin](https://forums.developer.nvidia.com/u/airpixin)\ **Post date:** [August 2, 2020, 5:12pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/9 "2020-08-02T17:12:40Z")
Thanks for prompt reply, I understand the issue about the H264 file.Thanks for letting me know. Sorry I forgot to attach this block in the last reply. Based on your initial changes I added “force-implicit-batch-dim=1” . And it works without giving any error . But the execution is stuck at this line. **NvMMLiteBlockCreate : Block : BlockType = 261** xxxx@xxxx-desktop:/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1$ python3 deepstream\_test\_1.py …/…/…/…/samples/streams/sample\_720p.mp4 Creating Pipeline Creating Source Creating H264Parser Creating Decoder Creating EGLSink Playing file …/…/…/…/samples/streams/sample\_720p.mp4 Warn: ‘threshold’ parameter has been deprecated. Use ‘pre-cluster-threshold’ instead. Adding elements to Pipeline Linking elements in the Pipeline Starting pipeline Using winsys: x11 Opening in BLOCKING MODE 0:00:03.100719469 10327 0x3aecab90 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine INFO: [Implicit Engine Info]: layers num: 3 0 INPUT kFLOAT input\_1 3x368x640 1 OUTPUT kFLOAT conv2d\_bbox 16x23x40 2 OUTPUT kFLOAT conv2d\_cov/Sigmoid 4x23x40 0:00:03.101016568 10327 0x3aecab90 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary\_Detector/resnet10.caffemodel\_b1\_gpu0\_int8.engine 0:00:03.105303358 10327 0x3aecab90 INFO nvinfer gstnvinfer\_impl.cpp:311:notifyLoadModelStatus: [UID 1]: Load new model:dstest1\_pgie\_config.txt sucessfully NvMMLiteOpen : Block : BlockType = 261 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NvMMLiteBlockCreate : Block : BlockType = 261 ---
**Author:** ![Amycao](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/amycao/32/11342_2.png) [@Amycao](https://forums.developer.nvidia.com/u/Amycao)\ **Post date:** [August 3, 2020, 1:59pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/10 "2020-08-03T13:59:03Z")
You could refer to test3 python sample which is using uridecodebin so that any type of input (e.g. RTSP/File), any GStreamer supported container format, and any codec can be used as input. Please note again, test1 python sample only accept h264 elementary stream. ---
**Author:** ![airpixin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@airpixin](https://forums.developer.nvidia.com/u/airpixin)\ **Post date:** [August 4, 2020, 12:51pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/11 "2020-08-04T12:51:51Z")
Thank you !! ---
**Author:** ![TomNVIDIA](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/tomnvidia/32/14181_2.png) [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Post date:** [October 12, 2021, 4:17pm UTC](https://forums.developer.nvidia.com/t/deepstream-python-error/144755/13 "2021-10-12T16:17:04Z")