0
$\begingroup$

I need a PyTorch Model which can do road segmentation on OAK-D camera.

The model provided requires Input Image Size: 896*512, which is too big for running on OAK-D camera. Thus I need to re-training it with a smaller input size(224x224) and just need the BG(background) and road classes, or if any other options available which can easily make it running on the OAK-D camera.

Does anyone know how to do this?

$\endgroup$
7
  • 1
    $\begingroup$ can you point us to the specific model you're trying to apply? $\endgroup$ Aug 17 at 14:57
  • $\begingroup$ hi @EdoardoGuerriero I have updated my post to provide the link to the model. thanks for your help :) $\endgroup$
    – Franva
    Aug 18 at 2:14
  • 1
    $\begingroup$ The model you're using has a couple of 2 strided convolutions. You can manipulate those in your liking, omitting some for example and finetuning the other layers.. $\endgroup$
    – Farhood ET
    Aug 18 at 5:35
  • $\begingroup$ hi @FarhoodET I am still very new to this area, could you please share a piece of code to explain what you mean?? thanks $\endgroup$
    – Franva
    Aug 18 at 8:17
  • $\begingroup$ @Franva unfortunately I think there is a lot of experimentation involved in AI. It is not simply a matter of "pls gimme teh codez" $\endgroup$
    – user253751
    Aug 18 at 10:41
0
$\begingroup$

What you need to search for is a Fully Convolutional Network, i.e. a network that use global pooling to overcome the issue of a fixed input size. Unfortunately the model you found is not fully convolutional, and every workaround to make those pre-trained weights usable implies retraining. At this point it is more convenient to find something else, or train something yourself. You can take a look at this repo which contains also a fully convolutional network for segmentation among other models (they don't seem to link to any pre-trained weights though).

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.