detrex
detrex copied to clipboard
Roadmap of detrex
We keep this issue open to collect feature requests from users and hear your voice.
You can either:
- Suggest a new feature by leaving a comment.
- Vote for a feature request with 👍. (Remember that developers are sometimes busy and cannot respond to all feature requests, so vote for your most favorable one!)
- Tell us that you would like to help implement new features or review the PRs. (This is the greatest thing to hear about!)
v0.2.1
- [x] MaskDINO. (Pre-release in https://github.com/IDEA-Research/detrex/pull/154)
- [x] Support
SwinV2
backbone (https://github.com/IDEA-Research/detrex/pull/152) - [x] Add a basic usage notebook for inference on custom images. ( https://github.com/IDEA-Research/detrex/pull/119 )
- [x] ViT backbone (https://github.com/IDEA-Research/detrex/pull/138)
Collection
- [ ] DQ-DET: https://arxiv.org/pdf/2307.12239.pdf
- [ ] RT-DETR
- [ ] Co-DETR
- [ ] Better data augmentation code format: https://github.com/IDEA-Research/detrex/pull/204
- [ ] Support
wandb
to log training informations and visualize sampled results - [ ] TensorRT for fast inference
- [ ] ONNX for DETR models
- [ ] Docker or python package for detrex (High Priority)
- [ ] Object365 Dataloader
- [ ] Semantic Seg/Instance Seg/Key points tasks
Wandb to log training process and visualize the sampled results.
support tensorRT for fast inference
mask-DINO
Objects365 dataloader.
support multiple downstream tasks like keypoint detection or segmention and so on