EfficientnetB0 (sgie) got very bad result on deepstream

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4.5.1
• Issue Type( questions, new requirements, bugs) bugs
**• How to reproduce the issue ?
Hi, after using tao-converter to converted our efficientnetB0 to tensorrt, I got very good accuracy.
However, this model gives us very bad result if we deploy it using deepstream (pgie) - detail
Please give some help.


Can you refer below?

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.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.