pyronear / pyro-vision

Computer vision library for wildfire detection 🌲 Deep learning models in PyTorch & ONNX for inference on edge devices (e.g. Raspberry Pi)

Home Page:https://pyronear.org/pyro-vision/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[models] Module design suggestion

frgfm opened this issue · comments

Here is a suggestion for the pyrovision.models module's organization:

  • utils.py: shared utility functions
  • XYZ.py: classification architecture definion with pretrained weights
  • detection: folder with the definition of object detection models with pretrained weights
  • segmentation: folder with the definition of segmentation models with pretrained weights

All performances of pretrained versions should be reported either in the documentation, the readme or a readme in the references folder.

commented

I don't understand your point here, we already have this architecture. We only have classification models. You want to add empty detection and segmentation folders?

It was to plan the incoming additions to the library

commented

ok sure let's do that

My bad, I haven't cleaned up the classification models! I'll do this by the end of the weekend

Closed by #138 & #150