Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) GPU • DeepStream Version Deepstream-6.3 • TensorRT Version 8.5.3-1+cuda11.8 • NVIDIA GPU Driver Version (valid for GPU only) Driver Version: 565.57.01 • Issue Type( questions, new requirement…

[image] daniele.marchisotti.work: The batch_size is set to 1 for both deepstream_test_1_new_thread.py and deepstream_test_1_usb.py. So no changes for batch-size of streammux. I mean nvinfer, not nvstreammux, there is no max-batch-size configuration item For nvinfer, batch-size will affect t…

This topic is similar to your question, you can refer to it [image] Wrong location for engine file generation DeepStream SDK Did you define engine-create-func-name in your config file? You can refer to the following source code in /opt/nvidia/deepstream/deepstream-7.0/so…

Hi @junshengy I think my topic is quite different from the one of the link you sent in the previous message. We have set the following variables in the config file: model-engine-file=/workspace/dev_deepstream_client_test/weights/model_b1_gpu0_fp32.engine engine-create-func-name=NvDsInferYoloCudaE…

It seems that my guess is correct, your problem is the same as the one in the topic above. This is a known issue. When you use the engine-create-func-name configuration item to customize the engine file, nvinfer will ignore the model-engine-file and only generate a file named model_b1_gpu0_fp32.engi…

I have done a structure of my repository to avoid to build the model_b1_gpu0_fp32.engine file everytime since it requires time. In my repository, I have done the following: --> deepstream_tests --> config --> infer --> config_infer_primar…

I see, in deepstream_test_1_new_thread.py, Has the value of batch-size property been modified? When rebuilding the engine file, is there output similar to the following in the terminal? deserialize backend context from engine from file :%s failed, " "try rebuild deserialized bac…

The batch_size is set to 1 for both deepstream_test_1_new_thread.py and deepstream_test_1_usb.py. So no changes for batch-size of streammux. I get this following output: [image] daniele.marchisotti.work: deserialize backend context from engine from file :/workspace/dev_deepstream_client_test/w…

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

Different model_b1_gpu0_fp32.engine when running a new thread but same deepstream configuration

Accelerated Computing Intelligent Video Analytics DeepStream SDK

junshengy February 5, 2025, 2:51am 3

This topic is similar to your question, you can refer to it

Topic		Replies	Views
Model.engine is always being built DeepStream SDK	10	986	April 30, 2024
Wrong location for engine file generation DeepStream SDK nvbugs , deepstream	12	328	October 26, 2024
Engine file name and path when using custom engine-create-func-name DeepStream SDK deepstream	3	110	May 8, 2025
Engine File default location DeepStream SDK	5	153	August 9, 2024
Is there a way to know the config file of the engine deepstream creates? DeepStream SDK jetson , deepstream	3	99	October 29, 2024
Dedicated Engine file path DeepStream SDK deepstream	5	142	December 17, 2024
Multiple engine files created for deepstream-rtsp-in-rtsp-out DeepStream SDK	13	795	June 7, 2022
What changes to inference configuration necessitate a new .engine file DeepStream SDK deepstream	8	217	July 31, 2025
Deep Stream takes too much time to create Engine file at startup DeepStream SDK python , deepstream	8	1719	February 9, 2022
Is there anything that needs extra attention when using my own engine file? DeepStream SDK tensorrt , nvbugs	18	1645	July 20, 2021

Different model_b1_gpu0_fp32.engine when running a new thread but same deepstream configuration

Related topics