pytorch/vision

Pre-trained detection models for PyTorch Hub

Open

#1,945 建立於 2020年3月6日

在 GitHub 查看
 (12 留言) (0 反應) (0 負責人)Python (6,858 fork)batch import
enhancementhelp wantedmodule: hubmodule: models

倉庫指標

Star
 (15,050 star)
PR 合併指標
 (平均合併 12天 8小時) (30 天內合併 14 個 PR)

描述

🚀 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

貢獻者指南