Create README.md

Author: NielsRogge

DETR/README.md

@@ -0,0 +1,13 @@
+# DETR notebooks
+
+This folder contains several notebooks illustrating how to use DETR for inference as well as fine-tuning on custom data.
+
+* [inference with DetrForObjectDetection on an image](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/DETR_minimal_example_(with_DetrFeatureExtractor).ipynb)
+* [fine-tuning DetrForObjectDetection on a custom dataset](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/Fine_tuning_DetrForObjectDetection_on_custom_dataset_(balloon).ipynb)
+* [evaluating DetrForObjectDetection on COCO](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/Evaluating_DETR_on_COCO_validation_2017.ipynb)
+* [inference with DetrForSegmentation on an image](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/DETR_panoptic_segmentation_minimal_example_(with_DetrFeatureExtractor).ipynb)
+* [fine-tuning DetrForSegmentation on a custom dataset](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/Fine_tuning_DetrForSegmentation_on_custom_dataset_end_to_end_approach.ipynb)
+
+All DETR checkpoints can be found on the [hub](https://huggingface.co/models?other=detr).
+
+Update: we now also support [Deformable DETR](https://huggingface.co/docs/transformers/main/en/model_doc/deformable_detr), which improves upon the original DETR in terms of convergence.