Can I use the previous inference or tracking model on DeepStream 7.1 in this way?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU)6.1
**• DeepStream Version 7.1
**• JetPack Version (valid for Jetson only)6.1
**• TensorRT Version 10.3
**• NVIDIA GPU Driver Version (valid for GPU only)540.4.0
• Issue Type( questions, new requirements, bugs)
The Type of this mechine is Orin AGX 64G
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Can I use the previous inference or tracking model on DeepStream 7.1 in this way?

3

person-detect-dla0-v1.0.0_bak.zip (25.6 MB)

4

person-detect-dla0-v1.0.0_bak.z01.zip (50 MB)

5

person-detect-dla0-v1.0.0_bak.z02.zip (50 MB)

6

person-detect-dla0-v1.0.0_bak.z03.zip (50 MB)

7

person-detect-dla0-v1.0.0_bak.z04.zip (50 MB)

8

Download the 5 files above, remove the suffix. zip from the last 4 file names, and extract the files.
first question What are the versions of these models in the folder?

9

The second question is to use the 7.1 version of deepstreamtest5 app, along with the model and configuration files mentioned above,
The following log will appear

root@flsay-desktop:/opt/nvidia/deepstream/deepstream-7.1-bak/sources/apps/sample_apps/deepstream-test5# ./deepstream-test5-app -c /home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/configs/config.txt
Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.
Civetweb version: v1.16
Server running at port: 33000
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
[NvMultiObjectTracker] Loading TRT Engine for tracker ReID…
ERROR: [TRT]: IRuntime::deserializeCudaEngine: Error Code 1: Serialization (Serialization assertion stdVersionRead == kSERIALIZATION_VERSION failed.Version tag does not match. Note: Current Version: 239, Serialized Engine Version: 236)
~~ CLOG[/dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/src/modules/ReID/ReID.cpp, loadTRTEngine() @line 598]: Engine build failed
[NvMultiObjectTracker] Load engine failed. Create engine again.
WARNING: INT8 calibration file not specified. Trying FP16 mode.
WARNING: [TRT]: DLA requests all profiles have same min, max, and opt value. All dla layers are falling back to GPU
ERROR: [TRT]: IRuntime::~IRuntime: Error Code 3: API Usage Error (Parameter check failed, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.)
[NvMultiObjectTracker] Serialized plan file cached at location: /home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/models/Tracker/resnet50_market1501.etlt_b100_gpu0_fp16.engine
[NvMultiObjectTracker] Initialized
[NvMultiObjectTracker] Loading TRT Engine for tracker ReID…
[NvMultiObjectTracker] Loading Complete!
[NvMultiObjectTracker] Initialized
[NvMultiObjectTracker] Loading TRT Engine for tracker ReID…
[NvMultiObjectTracker] Loading Complete!
[NvMultiObjectTracker] Initialized
ERROR: [TRT]: IRuntime::deserializeCudaEngine: Error Code 1: Serialization (Serialization assertion stdVersionRead == kSERIALIZATION_VERSION failed.Version tag does not match. Note: Current Version: 239, Serialized Engine Version: 236)
ERROR: Deserialize engine failed from file: /home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/models/pn26/dla0_pn26_jp6_halfmem_bs8-8623.engine
0:29:35.597849147 130493 0xaaaae13784d0 WARN nvinfer gstnvinfer.cpp:681:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2080> [UID = 1]: deserialize engine from file :/home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/models/pn26/dla0_pn26_jp6_halfmem_bs8-8623.engine failed
0:29:35.597917626 130493 0xaaaae13784d0 WARN nvinfer gstnvinfer.cpp:681: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 :/home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/models/pn26/dla0_pn26_jp6_halfmem_bs8-8623.engine failed, try rebuild
0:29:35.597933818 130493 0xaaaae13784d0 INFO nvinfer gstnvinfer.cpp:684: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
ERROR: failed to build network since there is no model file matched.
ERROR: failed to build network.
0:29:43.105857156 130493 0xaaaae13784d0 ERROR nvinfer gstnvinfer.cpp:678:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2126> [UID = 1]: build engine file failed
0:29:43.472905629 130493 0xaaaae13784d0 ERROR nvinfer gstnvinfer.cpp:678:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2213> [UID = 1]: build backend context failed
0:29:43.472984284 130493 0xaaaae13784d0 ERROR nvinfer gstnvinfer.cpp:678:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1351> [UID = 1]: generate backend failed, check config file settings
0:29:43.473045883 130493 0xaaaae13784d0 WARN nvinfer gstnvinfer.cpp:914:gst_nvinfer_start:<primary_gie> error: Failed to create NvDsInferContext instance
0:29:43.473062811 130493 0xaaaae13784d0 WARN nvinfer gstnvinfer.cpp:914:gst_nvinfer_start:<primary_gie> error: Config file path: /home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/configs/config_infer_primary_RN34_PN26_960x544_dla0_orin_unprune_agx.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
** ERROR: main:1561: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Failed to create NvDsInferContext instance
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(914): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
Config file path: /home/flsay/wpy/AiteNVR_Docker/build/analyzer/person-detect-dla0-v1.0.0/person-detect-dla0-v1.0.0_bak/configs/config_infer_primary_RN34_PN26_960x544_dla0_orin_unprune_agx.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Stopping the server…!!
Stopped the server…!!
[NvMultiObjectTracker] De-initialized
[NvMultiObjectTracker] De-initialized
[NvMultiObjectTracker] De-initialized
App run failed

11

We cannot unzip your files. Could you just attach that to your google driver?

12

The directory of the algorithm package is a bit large, about 200MB. How can I send it to you?

13

You can upload that to the google driver, then share the link to me.

Where did you get these models?

Please remove the engine file first if you update the OS version or change another device.

14

Link: https://pan.baidu.com/s/1IzSs6M_aGtDmC1MPBXznVg?pwd=abcd Extract code: abcd

15

Download it here, I just talked to Kevin

16

Sure. If there are any new questions, you can file a new topic.

17

ok thanks

18

Is the problem tracking that part? Will the engine after model conversion depend on Tensor

19

About the error from your log, please refer to the comment I attached before #13.

20

Where did you get these models?
My colleague did it before. Let me ask them again, can’t you see which version of these models you have?

21

Is it the previous version?

22

Because of this comment #15, I did not download your model yesterday. I thought you were checking that with Kevin. Could you upload it again?