pytorch/vision

Pre-trained detection models for PyTorch Hub

Open

#1945 aperta il 6 mar 2020

Vedi su GitHub
 (12 commenti) (0 reazioni) (0 assegnatari)Python (6858 fork)batch import
enhancementhelp wantedmodule: hubmodule: models

Metriche repository

Star
 (15.050 star)
Metriche merge PR
 (Merge medio 12g 8h) (14 PR mergiate in 30 g)

Descrizione

🚀 Feature

First of all, thanks for the amazing work.

I noticed currently there's no pre-trained detection models exposed via hub_conf.py. It looks like the building blocks are already there. Is there plan to support it?

Thanks

Motivation

Increase coverage of supported vision tasks via Torch Hub.

Pitch

  • entrypoints for detection models are added to hub_conf.py
  • some helpers e.g. for bbox parsing could also be added there

Guida contributor