facebookresearch / facebookresearch/detectron2

Integration with Torch Hub

Open
#1,044 2 comments 0 reactions 0 assignees View on GitHub
contributions welcome enhancement
Dominant language
Python
Stars
34.7k
Forks
7.9k
PR merge metrics
No merged PRs in 30d

Description

## 🚀 Feature

Hi team, thanks for the great work. Is there plan to integrate into [Torch Hub](https://pytorch.org/docs/stable/hub.html)?

## Motivation & Examples

Simplify the user experience and easier to discover models programmatically or from the hub website.

```
import torch

models = torch.hub.list('facebookresearch/detectron2')

model = torch.hub.load('facebookresearch/detectron2', 'R50-C4', pretrained=True)
```

Contributor guide

Open the contributing guide

Research direction

Start by comparing Torch Hub's documented list/load interface with detectron2's model-loading entry points. Done means the example calls can discover available models and load the requested R50-C4 model with pretrained weights through Torch Hub.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.