Deeploying Deepstream Graph with Container-Builder without Graph Composer

[jimmy.simmons]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) - Building on x86 deploy on x86 or Jetson
• DeepStream Version - 6.2
• JetPack Version (valid for Jetson only) - NA
• TensorRT Version - NA
• NVIDIA GPU Driver Version (valid for GPU only) - NA
• Issue Type( questions, new requirements, bugs) - NA

I have used Container Builder as part of Graph Composer to build images and they are relatively small, e.g. 6 GB. If you aren’t using Graph Composer and just using Python Bindings or C++ to build Deepstream Graphs can you still use Container Builder to build the images? If not the only other way I see to do it is to use start with the 6.2-base image which is 11 GB out of the box.

[Fiona.Chen]

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

@jimmy.simmons

If you aren’t using Graph Composer and just using Python Bindings or C++ to build Deepstream Graphs can you still use Container Builder to build the images?

No.

@jimmy.simmons

If not the only other way I see to do it is to use start with the 6.2-base image which is 11 GB out of the box.

You can also customize your own dockerfile with the released DeepStream dockerfile by removing the unused components from the dockerfile. NVIDIA-AI-IOT/deepstream_dockers: A project demonstrating how to make DeepStream docker images. (github.com)