facebookresearch / facebookresearch/detectron2
Integration with Torch Hub
- 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
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