• State
  • Locked Locked
  • Replies 2 replies
  • Subscribers 101 subscribers
  • Views 139 views
  • Users 0 members are here
Support feedback
Options
Options
Similar topics

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: How to train without using the pre-training model ?

maiunlei
Intellectual 332 points
Part Number: TDA4VM 
Hello experts,
My SDK version is processor-sdk-linux-sk-tda4vm-08_04_00.I trained the ssd model using the edgeai-mmdetection project.
However, I do not want to use the pre-trained model, how to configure the parameters?
 
thank you,
maiunlei
  • 0
    TI__Genius 11226 points

    Can you please clarify your question? You have already trained the model. Now are you asking about the next steps? Are are you asking about a different way of training?

  • 0 in reply to Manu Mathew
    Intellectual 332 points

    No. What I want to say is that I do not use pre-trained models for model training. That is to say, I iterative training from scratch. Like in the picture, I don 't use ' torchvision : / / resnet152'.  How should I configure it ?