Do transfer learnning using TAOT

Accelerated Computing Intelligent Video Analytics TAO Toolkit
,
1

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc) t4
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) Detectnet_v2
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here) tao version : 5.5
• 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 want to do transfer learning in detectnet_v2 but i’m new in TAO
can you help me to undrastand some of thease?
how can i learn more about spec file? i didn’t find any toturial about it (the only thing i find is notebooks without any explanation about what exactly spec file is or showing me all parameters of it(with explanation))
can i do transfer learning by changing spec file or other things? what should i do for it? (fore example changing output layer and keeping feature extraction layers and then fine tuning in new data)

2

For detectnet_v2, the notebook is in tao_tutorials/notebooks/tao_launcher_starter_kit/detectnet_v2 at main · NVIDIA/tao_tutorials · GitHub.
The doc is in DetectNet_v2 - NVIDIA Docs.
The code is in tao_tensorflow1_backend/nvidia_tao_tf1/cv/detectnet_v2 at main · NVIDIA/tao_tensorflow1_backend · GitHub.

Yes, you can change spec file or other things.
You can also docker run into the docker(nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5) (from TAO Toolkit | NVIDIA NGC). And modify the code and then docker commit to save your changes for your further use.

3

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

4

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