Memory issue in NX NANO

We’ve encountered while attempting to generate an engine file for the Sing Tao Converter using an ETLT classification model.
Upon attempting to generate the engine file, we encountered the following errors:

  • [INFO] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.

  • [WARNING] Skipping tactic 0 due to Myelin error: myelinTargetSetPropertyMemorySize called with invalid memory size (0).

  • [ERROR] 10: [optimizer.cpp::computeCosts::2011] Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[lstm_W…Max_reduce_min]}.)

  • [ERROR] Unable to create engine.

It appears that the issue revolves around memory allocation during the engine file generation process. The errors suggest that some tactics are failing due to insufficient workspace memory and a Myelin error with an invalid memory size.
Furthermore, there’s an internal error (Error Code 10) related to a specific node ({ForeignNode[lstm_W…Max_reduce_min]}) within the model. This node seems to lack an implementation, leading to the failure to create the engine file.
Request for Assistance:
We’re seeking assistance and guidance from the developer community to resolve this issue. Any insights, suggestions, or recommendations on how to address the memory allocation problem and the missing implementation for the node would be greatly appreciated.
Additional Information:

  • We’re using the Sing Tao Converter and an ETLT classification model.

  • The target is to generate an engine file for deployment.

Thank you in advance for your support and expertise in troubleshooting this issue. Please feel free to ask if you need any further details or clarifications.


Welcome to the NVIDIA Developer forums! Your topic will be best served in the Jetson category.

I will move this post over for visibility.


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


Could you share which JetPack version and platform you use?