Hi,
I’m working on Byom classification using pytorch.
onnx model downloaded from :
models/validated/vision/classification/mobilenet/model/mobilenetv2-10.onnx at main · onnx/models
And converted it in to Tltb using BYOM converter.
Could you please let me know the correct backbone type to specify in the spec file for training a mobilenetV2 based classification model using pytorch?
The TAO BYOM Converter is for TF1 Classification and UNet, or TF2 Classification. For classification pytorch, it is not supported.
Refer to Bring Your Own Model (BYOM) - NVIDIA Docs and GitHub - NVIDIA-AI-IOT/tao_byom_examples: Examples of converting different open-source deep learning models to TAO compatible format through TAO BYOM package..
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
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.