isl-org / lang-seg

Language-Driven Semantic Segmentation
MIT License
722 stars 91 forks source link

Model parameter descriptions #37

Closed jonathan-roberts1 closed 1 year ago

jonathan-roberts1 commented 2 years ago

Hi Boyi,

Thanks a lot for releasing the code for LSeg!

I’ve been having a play around using the demo code + model in a zero-shot setting and just have a few (hopefully quick) questions about some of the model parameters.

Could you please give a brief overview (description, where the default values originate, what the optimum values might be) of the following parameters used in the LSeg_MultiEvalModule:

  1. ‘scales’ - e.g., lseg_app.py Line 315
  2. (‘base_size’ - e.g., additional_utils/models.py Line 28)
  3. ‘crop_size’ - e.g., additional_utils/models.py Line 29 And this parameter used in the LSegNet class:
  4. scale_factor - e.g., module/models/lseg_net.py Line 216 (this has a default value of 0.5 and is different to the scale_factor parameter that is passed to 'Interpolate')

Thanks!

Boyiliee commented 1 year ago

Hi @jonathan-roberts1 ,

Thanks for your interest in LSeg!

Regarding the parameters, all these factors keep the same policy with DPT for the semantic segmentation settings.

Hope this helps!

Best, Boyi