When I ran the deepstream example, I had to run the engine transformation on each execution

[Captian]

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU)jetson agx orin
**• DeepStream Version 6.4
**• JetPack Version (valid for Jetson only) 6.0
**• TensorRT Version 8.6.2
• NVIDIA GPU Driver Version (valid for GPU only)
**• Issue Type( questions, new requirements, bugs) questions
When I run the deepstream example, I have to run the engine transformation on every execution. Is there any way to change this without the configuration of every transformation

[junshengy]

You can try to modify the configuration file.

Take deepstream-test1 as an example. In the dstest1_pgie_config.txt, batch-size needs to be consistent with model-engine-file.

batch-size=30

model-engine-file=../../../../samples/models/Primary_Detector/resnet18_trafficcamnet.etlt_b30_gpu0_int8.engine

Like this, the conversion will only happen when the sample first run.

[yingliu]

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