Fix typo and README

huggingface · Jan 5, 2023 · 2572d50 · 2572d50
1 parent 9425aa5
commit 2572d50
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 4 deletions.
diff --git a/README_ko.md b/README_ko.md
@@ -250,6 +250,7 @@ Flax, PyTorch, TensorFlow 설치 페이지에서 이들을 conda로 설치하는
 1. **[Decision Transformer](https://huggingface.co/docs/transformers/model_doc/decision_transformer)** (Berkeley/Facebook/Google 에서) Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch 의 [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://arxiv.org/abs/2106.01345) 논문과 함께 발표했습니다.
 1. **[Deformable DETR](https://huggingface.co/docs/transformers/model_doc/deformable_detr)** (SenseTime Research 에서) Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai 의 [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://arxiv.org/abs/2010.04159) 논문과 함께 발표했습니다.
 1. **[DeiT](https://huggingface.co/docs/transformers/model_doc/deit)** (Facebook 에서) Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou 의 [Training data-efficient image transformers & distillation through attention](https://arxiv.org/abs/2012.12877) 논문과 함께 발표했습니다.
+1. **[DETA](https://huggingface.co/docs/transformers/main/model_doc/deta)** (The University of Texas at Austin 에서 제공)은 Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl.의 [NMS Strikes Back](https://arxiv.org/abs/2212.06137)논문과 함께 발표했습니다.
 1. **[DETR](https://huggingface.co/docs/transformers/model_doc/detr)** (Facebook 에서) Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko 의 [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872) 논문과 함께 발표했습니다.
 1. **[DialoGPT](https://huggingface.co/docs/transformers/model_doc/dialogpt)** (Microsoft Research 에서) Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, Bill Dolan 의 [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://arxiv.org/abs/1911.00536) 논문과 함께 발표했습니다.
 1. **[DiNAT](https://huggingface.co/docs/transformers/model_doc/dinat)** (SHI Labs 에서) Ali Hassani and Humphrey Shi 의 [Dilated Neighborhood Attention Transformer](https://arxiv.org/abs/2209.15001) 논문과 함께 발표했습니다.

diff --git a/src/transformers/__init__.py b/src/transformers/__init__.py
@@ -861,8 +861,8 @@
 except OptionalDependencyNotAvailable:
     from .utils import dummy_torchvision_objects
 
-    _import_structure["utils.dummmy_torchvision_objects"] = [
-        name for name in dir(dummmy_torchvision_objects) if not name.startswith("_")
+    _import_structure["utils.dummy_torchvision_objects"] = [
+        name for name in dir(dummy_torchvision_objects) if not name.startswith("_")
     ]
 else:
     _import_structure["models.deta"].extend(

diff --git a/src/transformers/models/deta/modeling_deta.py b/src/transformers/models/deta/modeling_deta.py
@@ -1503,8 +1503,8 @@ def get_valid_ratio(self, mask):
         """Get the valid ratio of all feature maps."""
 
         _, height, width = mask.shape
-        valid_height = torch.sum(~mask[:, :, 0], 1)
-        valid_width = torch.sum(~mask[:, 0, :], 1)
+        valid_height = torch.sum(mask[:, :, 0], 1)
+        valid_width = torch.sum(mask[:, 0, :], 1)
         valid_ratio_heigth = valid_height.float() / height
         valid_ratio_width = valid_width.float() / width
         valid_ratio = torch.stack([valid_ratio_width, valid_ratio_heigth], -1)