End-to-end object detection with Transformers

[parmarsuraj99]

🚀 Feature request

A modular Transformer Encoder-Decoder block that can be attached to ConvNets for many tasks.

Motivation

As shown in the recent paper End-to-end Object Detection with Transformers which used Transformer for Object Detection. https://github.com/facebookresearch/detr

Your contribution

[BramVanroy]

I might be wrong, but I think the focus of this library is on NLP which at most is multimodal. Also including object detection transformers may fall out of the scope of this project.