Add UperNet (#20648)

* First draft

* More improvements

* Add convnext backbone

* Add conversion script

* Add more improvements

* Comment out to_dict

* Add to_dict method

* Add default config

* Fix config

* Fix backbone

* Fix backbone some more

* Add docs, auto mapping, tests

* Fix some tests

* Fix more tests

* Fix more tests

* Add conversion script

* Improve conversion script

* Add support for getting reshaped undownsampled hidden states

* Fix forward pass

* Add print statements

* Comment out set_shift_and_window_size

* More improvements

* Correct downsampling layers conversion

* Fix style

* First draft

* Fix conversion script

* Remove config attribute

* Fix more tests

* Update READMEs

* Update ConvNextBackbone

* Fix ConvNext tests

* Align ConvNext with Swin

* Remove files

* Fix index

* Improve docs

* Add output_attentions to model forward

* Add backbone mixin, improve tests

* More improvements

* Update init_weights

* Fix interpolation of logits

* Add UperNetImageProcessor

* Improve image processor

* Fix image processor

* Remove print statements

* Remove script

* Update import

* Add image processor tests

* Remove print statements

* Fix test

* Add integration test

* Add convnext integration test

* Update docstring

* Fix README

* Simplify config

* Apply suggestions

* Improve docs

* Rename class

* Fix test_initialization

* Fix import

* Address review

* Fix confg

* Convert all checkpoints

* Fix default backbone

* Usage same processor as segformer

* Apply suggestions

* Fix init_weights, update conversion scripts

* Improve config

* Use Auto API instead of creating a new image processor

* Fix docs

* Add doctests

* Remove ResNetConfig dependency

* Add always_partition argument

* Fix rebaseé

* Improve docs

* Convert checkpoints

Co-authored-by: Niels Rogge <nielsrogge@Nielss-MacBook-Pro.local>
Co-authored-by: Niels Rogge <nielsrogge@Nielss-MBP.localdomain>

README_es.md

@@ -407,6 +407,7 @@ Número actual de puntos de control: ![](https://img.shields.io/endpoint?url=htt
 1. **[UL2](https://huggingface.co/docs/transformers/model_doc/ul2)** (from Google Research) released with the paper [Unifying Language Learning Paradigms](https://arxiv.org/abs/2205.05131v1) by Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Neil Houlsby, Donald Metzler
 1. **[UniSpeech](https://huggingface.co/docs/transformers/model_doc/unispeech)** (from Microsoft Research) released with the paper [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://arxiv.org/abs/2101.07597) by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang.
 1. **[UniSpeechSat](https://huggingface.co/docs/transformers/model_doc/unispeech-sat)** (from Microsoft Research) released with the paper [UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING](https://arxiv.org/abs/2110.05752) by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu.
+1. **[UPerNet](https://huggingface.co/docs/transformers/main/model_doc/upernet)** (from Peking University) released with the paper [Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/abs/1807.10221) by Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun.
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (from Tsinghua University and Nankai University) released with the paper [Visual Attention Network](https://arxiv.org/abs/2202.09741) by Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu.
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (from Multimedia Computing Group, Nanjing University) released with the paper [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Zhan Tong, Yibing Song, Jue Wang, Limin Wang.
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (from NAVER AI Lab/Kakao Enterprise/Kakao Brain) released with the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Wonjae Kim, Bokyung Son, Ildoo Kim.