Can deepstream-test3 load and reason about deepstream-tao's seg_app_unet.yml?

[autodrive2022]

deepstream-app version 6.2.0
DeepStreamSDK 6.2.0
CUDA Driver Version: 11.4
CUDA Runtime Version: 11.4
TensorRT Version: 8.4
cuDNN Version: 8.4
libNVWarp360 Version: 2.0.1d3

Can deepstream-test3 load and reason about deepstream-tao’s seg_app_unet.yml?
I use deepstream-test3 and load the det_app_frcnn.yml configuration file of deepstream-tao, and load the model test classification task. It is fully executable and accurately classified.
But the splitting task of my seg_app_unet.yml is not possible and an error is reported.

Error: batch-size(1) should be in the range [1,1024]
Failed to parse group property
** ERROR: <gst_nvinfer_parse_config_file_yaml:970>: failed
Using file: ./seg/ins_seg_app_peopleSegNet.yml
0:00:00.242320832  7708 0xffff1c0024a0 WARN                 nvinfer gstnvinfer.cpp:842:gst_nvinfer_start:<primary-nvinference-engine> error: Configuration file parsing failed
0:00:00.242395008  7708 0xffff1c0024a0 WARN                 nvinfer gstnvinfer.cpp:842:gst_nvinfer_start:<primary-nvinference-engine> error: Config file path: /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream-test3/seg/pgie_peopleSegNet_tao_config.yml
Running...
ERROR from element primary-nvinference-engine: Configuration file parsing failed
Error details: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(842): gst_nvinfer_start (): /GstPipeline:dstest3-pipeline/GstNvInfer:primary-nvinference-engine:
Config file path: /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream-test3/seg/pgie_peopleSegNet_tao_config.yml
Returned, stopping playback
Deleting pipeline

[fanzh]

deepstrema-test3 and tao-app have different yml parsing libs, but all the libs are opensource. from the error “Error: batch-size(1) should be in the range [1,1024]”, it should be batch parsing error. you can add log in gst_nvinfer_parse_props_yaml of gstnvinfer_yaml_parser.cpp in DeepStream SDK.

[autodrive2022]

yean, I have updated the lib library involved in the configuration file to the official lib library provided by deepstream-tao.

[fanzh]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Is this still an DeepStream issue to support? Thanks! we suggest adapting deepstream-test3’s configuration file dstest3_config.yml if testing deepstream-test3.