Please provide the following information when requesting support.
• Hardware (T4/V100/Xavier/Nano/etc) RTX2060
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) Classification
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
Hi,
I am having an issue with deploying a tao efficientnet B0 model to deepstream. I have asked the question in deepstream and have been told to asked my question in TAO.
The spec file is in the following link, and issue is described in the post. I just want to be able to have the same performance as the TAO generated onnx and in deepstream.
Is there a better way to ask this question than a forum as i would like to solve this issue for a client.
From the discussion in Problem running Efficientnet B0 as SGIE in Deepstream - #13 by Fiona.Chen, your question is that "the original onnx model works fine when using onnxruntime. I am wondering why it is not working on deepstream. ".
According to latest comment, seems that the issue is gone in deepstream now.