Update docs.

fundamentalvision · Dec 7, 2020 · ecd3210 · ecd3210
1 parent 05a2feb
commit ecd3210
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -4,10 +4,6 @@ By [Xizhou Zhu](https://scholar.google.com/citations?user=02RXI00AAAAJ),  [Weiji
 
 This repository is an official implementation of the paper [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://arxiv.org/abs/2010.04159).
 
-## Update
-
-**[2020.12.07]** Fix a bug of sampling offset normalization (see [this issue](https://github.com/fundamentalvision/Deformable-DETR/issues/6)) in the MSDeformAttn module. The final accuracy on COCO is slightly improved. Code and pre-trained models has been updated. This bug only occurs in this released version but not in the original implementation used in our paper.
-
 
 ## Introduction
 
@@ -23,6 +19,10 @@ This repository is an official implementation of the paper [Deformable DETR: Def
 
 This project is released under the [Apache 2.0 license](./LICENSE).
 
+## Changelog
+
+See [changelog.md]() for detailed logs of major changes. 
+
 
 ## Citing Deformable DETR
 If you find Deformable DETR useful in your research, please consider citing:

diff --git a/docs/changelog.md b/docs/changelog.md
@@ -0,0 +1,3 @@
+## Changelog
+
+**[2020.12.07]** Fix a bug of sampling offset normalization (see [this issue](https://github.com/fundamentalvision/Deformable-DETR/issues/6)) in the MSDeformAttn module. The final accuracy on COCO is slightly improved. Code and pre-trained models have been updated. This bug only occurs in this released version but not in the original implementation used in our paper.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		## Changelog

		[2020.12.07] Fix a bug of sampling offset normalization (see [this issue](https://github.com/fundamentalvision/Deformable-DETR/issues/6)) in the MSDeformAttn module. The final accuracy on COCO is slightly improved. Code and pre-trained models have been updated. This bug only occurs in this released version but not in the original implementation used in our paper.