pytorch/vision

Pre-trained detection models for PyTorch Hub

Open

#1 945 ouverte le 6 mars 2020

Voir sur GitHub
 (12 commentaires) (0 réactions) (0 assignés)Python (6 858 forks)batch import
enhancementhelp wantedmodule: hubmodule: models

Métriques du dépôt

Stars
 (15 050 stars)
Métriques de merge PR
 (Merge moyen 12j 8h) (14 PRs mergées en 30 j)

Description

🚀 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

Guide contributeur