SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add DETR (#11653)

Browse Source 
* Squash all commits of modeling_detr_v7 branch into one

* Improve docs

* Fix tests

* Style

* Improve docs some more and fix most tests

* Fix slow tests of ViT, DeiT and DETR

* Improve replacement of batch norm

* Restructure timm backbone forward

* Make DetrForSegmentation support any timm backbone

* Fix name of output

* Address most comments by @LysandreJik

* Give better names for variables

* Conditional imports + timm in setup.py

* Address additional comments by @sgugger

* Make style, add require_timm and require_vision to testsé

* Remove train_backbone attribute of DetrConfig, add methods to freeze/unfreeze backbone

* Add png files to fixtures

* Fix type hint

* Add timm to workflows

* Add `BatchNorm2d` to the weight initialization

* Fix retain_grad test

* Replace model checkpoints by Facebook namespace

* Fix name of checkpoint in test

* Add user-friendly message when scipy is not available

* Address most comments by @patrickvonplaten

* Remove return_intermediate_layers attribute of DetrConfig and simplify Joiner

* Better initialization

* Scipy is necessary to get sklearn metrics

* Rename TimmBackbone to DetrTimmConvEncoder and rename DetrJoiner to DetrConvModel

* Make style

* Improve docs and add 2 community notebooks

Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>
This commit is contained in:
NielsRogge
2021-06-09 17:51:13 +02:00
committed by GitHub
parent d14e0af274
commit d3eacbb829
42 changed files with 5177 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
docs/source/index.rst
View File

@@ -153,128 +153,131 @@ Supported models
19. :doc:`DeiT <model_doc/deit>` (from Facebook) released with the paper `Training data-efficient image transformers &
distillation through attention <https://arxiv.org/abs/2012.12877>`__ by Hugo Touvron, Matthieu Cord, Matthijs
Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou.
20. :doc:`DialoGPT <model_doc/dialogpt>` (from Microsoft Research) released with the paper `DialoGPT: Large-Scale
20. :doc:`DETR <model_doc/detr>` (from Facebook) released with the paper `End-to-End Object Detection with Transformers
<https://arxiv.org/abs/2005.12872>`__ by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier,
Alexander Kirillov, Sergey Zagoruyko.
21. :doc:`DialoGPT <model_doc/dialogpt>` (from Microsoft Research) released with the paper `DialoGPT: Large-Scale
Generative Pre-training for Conversational Response Generation <https://arxiv.org/abs/1911.00536>`__ by Yizhe
Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, Bill Dolan.
21. :doc:`DistilBERT <model_doc/distilbert>` (from HuggingFace), released together with the paper `DistilBERT, a
22. :doc:`DistilBERT <model_doc/distilbert>` (from HuggingFace), released together with the paper `DistilBERT, a
distilled version of BERT: smaller, faster, cheaper and lighter <https://arxiv.org/abs/1910.01108>`__ by Victor
Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into `DistilGPT2
<https://github.com/huggingface/transformers/tree/master/examples/distillation>`__, RoBERTa into `DistilRoBERTa
<https://github.com/huggingface/transformers/tree/master/examples/distillation>`__, Multilingual BERT into
`DistilmBERT <https://github.com/huggingface/transformers/tree/master/examples/distillation>`__ and a German
version of DistilBERT.
22. :doc:`DPR <model_doc/dpr>` (from Facebook) released with the paper `Dense Passage Retrieval for Open-Domain
23. :doc:`DPR <model_doc/dpr>` (from Facebook) released with the paper `Dense Passage Retrieval for Open-Domain
Question Answering <https://arxiv.org/abs/2004.04906>`__ by Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick
Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.
23. :doc:`ELECTRA <model_doc/electra>` (from Google Research/Stanford University) released with the paper `ELECTRA:
24. :doc:`ELECTRA <model_doc/electra>` (from Google Research/Stanford University) released with the paper `ELECTRA:
Pre-training text encoders as discriminators rather than generators <https://arxiv.org/abs/2003.10555>`__ by Kevin
Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
24. :doc:`FlauBERT <model_doc/flaubert>` (from CNRS) released with the paper `FlauBERT: Unsupervised Language Model
25. :doc:`FlauBERT <model_doc/flaubert>` (from CNRS) released with the paper `FlauBERT: Unsupervised Language Model
Pre-training for French <https://arxiv.org/abs/1912.05372>`__ by Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne,
Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab.
25. :doc:`Funnel Transformer <model_doc/funnel>` (from CMU/Google Brain) released with the paper `Funnel-Transformer:
26. :doc:`Funnel Transformer <model_doc/funnel>` (from CMU/Google Brain) released with the paper `Funnel-Transformer:
Filtering out Sequential Redundancy for Efficient Language Processing <https://arxiv.org/abs/2006.03236>`__ by
Zihang Dai, Guokun Lai, Yiming Yang, Quoc V. Le.
26. :doc:`GPT <model_doc/gpt>` (from OpenAI) released with the paper `Improving Language Understanding by Generative
27. :doc:`GPT <model_doc/gpt>` (from OpenAI) released with the paper `Improving Language Understanding by Generative
Pre-Training <https://blog.openai.com/language-unsupervised/>`__ by Alec Radford, Karthik Narasimhan, Tim Salimans
and Ilya Sutskever.
27. :doc:`GPT-2 <model_doc/gpt2>` (from OpenAI) released with the paper `Language Models are Unsupervised Multitask
28. :doc:`GPT-2 <model_doc/gpt2>` (from OpenAI) released with the paper `Language Models are Unsupervised Multitask
Learners <https://blog.openai.com/better-language-models/>`__ by Alec Radford*, Jeffrey Wu*, Rewon Child, David
Luan, Dario Amodei** and Ilya Sutskever**.
28. :doc:`GPT Neo <model_doc/gpt_neo>` (from EleutherAI) released in the repository `EleutherAI/gpt-neo
29. :doc:`GPT Neo <model_doc/gpt_neo>` (from EleutherAI) released in the repository `EleutherAI/gpt-neo
<https://github.com/EleutherAI/gpt-neo>`__ by Sid Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy.
29. :doc:`I-BERT <model_doc/ibert>` (from Berkeley) released with the paper `I-BERT: Integer-only BERT Quantization
30. :doc:`I-BERT <model_doc/ibert>` (from Berkeley) released with the paper `I-BERT: Integer-only BERT Quantization
<https://arxiv.org/abs/2101.01321>`__ by Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
30. :doc:`LayoutLM <model_doc/layoutlm>` (from Microsoft Research Asia) released with the paper `LayoutLM: Pre-training
31. :doc:`LayoutLM <model_doc/layoutlm>` (from Microsoft Research Asia) released with the paper `LayoutLM: Pre-training
of Text and Layout for Document Image Understanding <https://arxiv.org/abs/1912.13318>`__ by Yiheng Xu, Minghao Li,
Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou.
31. :doc:`LED <model_doc/led>` (from AllenAI) released with the paper `Longformer: The Long-Document Transformer
32. :doc:`LED <model_doc/led>` (from AllenAI) released with the paper `Longformer: The Long-Document Transformer
<https://arxiv.org/abs/2004.05150>`__ by Iz Beltagy, Matthew E. Peters, Arman Cohan.
32. :doc:`Longformer <model_doc/longformer>` (from AllenAI) released with the paper `Longformer: The Long-Document
33. :doc:`Longformer <model_doc/longformer>` (from AllenAI) released with the paper `Longformer: The Long-Document
Transformer <https://arxiv.org/abs/2004.05150>`__ by Iz Beltagy, Matthew E. Peters, Arman Cohan.
33. :doc:`LUKE <model_doc/luke>` (from Studio Ousia) released with the paper `LUKE: Deep Contextualized Entity
34. :doc:`LUKE <model_doc/luke>` (from Studio Ousia) released with the paper `LUKE: Deep Contextualized Entity
Representations with Entity-aware Self-attention <https://arxiv.org/abs/2010.01057>`__ by Ikuya Yamada, Akari Asai,
Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto.
34. :doc:`LXMERT <model_doc/lxmert>` (from UNC Chapel Hill) released with the paper `LXMERT: Learning Cross-Modality
35. :doc:`LXMERT <model_doc/lxmert>` (from UNC Chapel Hill) released with the paper `LXMERT: Learning Cross-Modality
Encoder Representations from Transformers for Open-Domain Question Answering <https://arxiv.org/abs/1908.07490>`__
by Hao Tan and Mohit Bansal.
35. :doc:`M2M100 <model_doc/m2m_100>` (from Facebook) released with the paper `Beyond English-Centric Multilingual
36. :doc:`M2M100 <model_doc/m2m_100>` (from Facebook) released with the paper `Beyond English-Centric Multilingual
Machine Translation <https://arxiv.org/abs/2010.11125>`__ by by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi
Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman
Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
36. :doc:`MarianMT <model_doc/marian>` Machine translation models trained using `OPUS <http://opus.nlpl.eu/>`__ data by
37. :doc:`MarianMT <model_doc/marian>` Machine translation models trained using `OPUS <http://opus.nlpl.eu/>`__ data by
Jörg Tiedemann. The `Marian Framework <https://marian-nmt.github.io/>`__ is being developed by the Microsoft
Translator Team.
37. :doc:`MBart <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Denoising Pre-training for
38. :doc:`MBart <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Denoising Pre-training for
Neural Machine Translation <https://arxiv.org/abs/2001.08210>`__ by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li,
Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
38. :doc:`MBart-50 <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Translation with Extensible
39. :doc:`MBart-50 <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Translation with Extensible
Multilingual Pretraining and Finetuning <https://arxiv.org/abs/2008.00401>`__ by Yuqing Tang, Chau Tran, Xian Li,
Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.
39. :doc:`Megatron-BERT <model_doc/megatron_bert>` (from NVIDIA) released with the paper `Megatron-LM: Training
40. :doc:`Megatron-BERT <model_doc/megatron_bert>` (from NVIDIA) released with the paper `Megatron-LM: Training
Multi-Billion Parameter Language Models Using Model Parallelism <https://arxiv.org/abs/1909.08053>`__ by Mohammad
Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.
40. :doc:`Megatron-GPT2 <model_doc/megatron_gpt2>` (from NVIDIA) released with the paper `Megatron-LM: Training
41. :doc:`Megatron-GPT2 <model_doc/megatron_gpt2>` (from NVIDIA) released with the paper `Megatron-LM: Training
Multi-Billion Parameter Language Models Using Model Parallelism <https://arxiv.org/abs/1909.08053>`__ by Mohammad
Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.
41. :doc:`MPNet <model_doc/mpnet>` (from Microsoft Research) released with the paper `MPNet: Masked and Permuted
42. :doc:`MPNet <model_doc/mpnet>` (from Microsoft Research) released with the paper `MPNet: Masked and Permuted
Pre-training for Language Understanding <https://arxiv.org/abs/2004.09297>`__ by Kaitao Song, Xu Tan, Tao Qin,
Jianfeng Lu, Tie-Yan Liu.
42. :doc:`MT5 <model_doc/mt5>` (from Google AI) released with the paper `mT5: A massively multilingual pre-trained
43. :doc:`MT5 <model_doc/mt5>` (from Google AI) released with the paper `mT5: A massively multilingual pre-trained
text-to-text transformer <https://arxiv.org/abs/2010.11934>`__ by Linting Xue, Noah Constant, Adam Roberts, Mihir
Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel.
43. :doc:`Pegasus <model_doc/pegasus>` (from Google) released with the paper `PEGASUS: Pre-training with Extracted
44. :doc:`Pegasus <model_doc/pegasus>` (from Google) released with the paper `PEGASUS: Pre-training with Extracted
Gap-sentences for Abstractive Summarization <https://arxiv.org/abs/1912.08777>`__> by Jingqing Zhang, Yao Zhao,
Mohammad Saleh and Peter J. Liu.
44. :doc:`ProphetNet <model_doc/prophetnet>` (from Microsoft Research) released with the paper `ProphetNet: Predicting
45. :doc:`ProphetNet <model_doc/prophetnet>` (from Microsoft Research) released with the paper `ProphetNet: Predicting
Future N-gram for Sequence-to-Sequence Pre-training <https://arxiv.org/abs/2001.04063>`__ by Yu Yan, Weizhen Qi,
Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou.
45. :doc:`Reformer <model_doc/reformer>` (from Google Research) released with the paper `Reformer: The Efficient
46. :doc:`Reformer <model_doc/reformer>` (from Google Research) released with the paper `Reformer: The Efficient
Transformer <https://arxiv.org/abs/2001.04451>`__ by Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya.
46. :doc:`RoBERTa <model_doc/roberta>` (from Facebook), released together with the paper a `Robustly Optimized BERT
47. :doc:`RoBERTa <model_doc/roberta>` (from Facebook), released together with the paper a `Robustly Optimized BERT
Pretraining Approach <https://arxiv.org/abs/1907.11692>`__ by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar
Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
47. :doc:`RoFormer <model_doc/roformer>` (from ZhuiyiTechnology), released together with the paper a `RoFormer:
48. :doc:`RoFormer <model_doc/roformer>` (from ZhuiyiTechnology), released together with the paper a `RoFormer:
Enhanced Transformer with Rotary Position Embedding <https://arxiv.org/pdf/2104.09864v1.pdf>`__ by Jianlin Su and
Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu.
48. :doc:`SpeechToTextTransformer <model_doc/speech_to_text>` (from Facebook), released together with the paper
49. :doc:`SpeechToTextTransformer <model_doc/speech_to_text>` (from Facebook), released together with the paper
`fairseq S2T: Fast Speech-to-Text Modeling with fairseq <https://arxiv.org/abs/2010.05171>`__ by Changhan Wang, Yun
Tang, Xutai Ma, Anne Wu, Dmytro Okhonko, Juan Pino.
49. :doc:`SqueezeBert <model_doc/squeezebert>` released with the paper `SqueezeBERT: What can computer vision teach NLP
50. :doc:`SqueezeBert <model_doc/squeezebert>` released with the paper `SqueezeBERT: What can computer vision teach NLP
about efficient neural networks? <https://arxiv.org/abs/2006.11316>`__ by Forrest N. Iandola, Albert E. Shaw, Ravi
Krishna, and Kurt W. Keutzer.
50. :doc:`T5 <model_doc/t5>` (from Google AI) released with the paper `Exploring the Limits of Transfer Learning with a
51. :doc:`T5 <model_doc/t5>` (from Google AI) released with the paper `Exploring the Limits of Transfer Learning with a
Unified Text-to-Text Transformer <https://arxiv.org/abs/1910.10683>`__ by Colin Raffel and Noam Shazeer and Adam
Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
51. :doc:`TAPAS <model_doc/tapas>` (from Google AI) released with the paper `TAPAS: Weakly Supervised Table Parsing via
52. :doc:`TAPAS <model_doc/tapas>` (from Google AI) released with the paper `TAPAS: Weakly Supervised Table Parsing via
Pre-training <https://arxiv.org/abs/2004.02349>`__ by Jonathan Herzig, Paweł Krzysztof Nowak, Thomas Müller,
Francesco Piccinno and Julian Martin Eisenschlos.
52. :doc:`Transformer-XL <model_doc/transformerxl>` (from Google/CMU) released with the paper `Transformer-XL:
53. :doc:`Transformer-XL <model_doc/transformerxl>` (from Google/CMU) released with the paper `Transformer-XL:
Attentive Language Models Beyond a Fixed-Length Context <https://arxiv.org/abs/1901.02860>`__ by Zihang Dai*,
Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov.
53. :doc:`Vision Transformer (ViT) <model_doc/vit>` (from Google AI) released with the paper `An Image is Worth 16x16
54. :doc:`Vision Transformer (ViT) <model_doc/vit>` (from Google AI) released with the paper `An Image is Worth 16x16
Words: Transformers for Image Recognition at Scale <https://arxiv.org/abs/2010.11929>`__ by Alexey Dosovitskiy,
Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias
Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
54. :doc:`VisualBERT <model_doc/visual_bert>` (from UCLA NLP) released with the paper `VisualBERT: A Simple and
55. :doc:`VisualBERT <model_doc/visual_bert>` (from UCLA NLP) released with the paper `VisualBERT: A Simple and
Performant Baseline for Vision and Language <https://arxiv.org/pdf/1908.03557>`__ by Liunian Harold Li, Mark
Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang.
55. :doc:`Wav2Vec2 <model_doc/wav2vec2>` (from Facebook AI) released with the paper `wav2vec 2.0: A Framework for
56. :doc:`Wav2Vec2 <model_doc/wav2vec2>` (from Facebook AI) released with the paper `wav2vec 2.0: A Framework for
Self-Supervised Learning of Speech Representations <https://arxiv.org/abs/2006.11477>`__ by Alexei Baevski, Henry
Zhou, Abdelrahman Mohamed, Michael Auli.
56. :doc:`XLM <model_doc/xlm>` (from Facebook) released together with the paper `Cross-lingual Language Model
57. :doc:`XLM <model_doc/xlm>` (from Facebook) released together with the paper `Cross-lingual Language Model
Pretraining <https://arxiv.org/abs/1901.07291>`__ by Guillaume Lample and Alexis Conneau.
57. :doc:`XLM-ProphetNet <model_doc/xlmprophetnet>` (from Microsoft Research) released with the paper `ProphetNet:
58. :doc:`XLM-ProphetNet <model_doc/xlmprophetnet>` (from Microsoft Research) released with the paper `ProphetNet:
Predicting Future N-gram for Sequence-to-Sequence Pre-training <https://arxiv.org/abs/2001.04063>`__ by Yu Yan,
Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou.
58. :doc:`XLM-RoBERTa <model_doc/xlmroberta>` (from Facebook AI), released together with the paper `Unsupervised
59. :doc:`XLM-RoBERTa <model_doc/xlmroberta>` (from Facebook AI), released together with the paper `Unsupervised
Cross-lingual Representation Learning at Scale <https://arxiv.org/abs/1911.02116>`__ by Alexis Conneau*, Kartikay
Khandelwal*, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke
Zettlemoyer and Veselin Stoyanov.
59. :doc:`XLNet <model_doc/xlnet>` (from Google/CMU) released with the paper `​XLNet: Generalized Autoregressive
60. :doc:`XLNet <model_doc/xlnet>` (from Google/CMU) released with the paper `​XLNet: Generalized Autoregressive
Pretraining for Language Understanding <https://arxiv.org/abs/1906.08237>`__ by Zhilin Yang*, Zihang Dai*, Yiming
Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
60. :doc:`XLSR-Wav2Vec2 <model_doc/xlsr_wav2vec2>` (from Facebook AI) released with the paper `Unsupervised
61. :doc:`XLSR-Wav2Vec2 <model_doc/xlsr_wav2vec2>` (from Facebook AI) released with the paper `Unsupervised
Cross-Lingual Representation Learning For Speech Recognition <https://arxiv.org/abs/2006.13979>`__ by Alexis
Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli.
@@ -318,6 +321,8 @@ Flax), PyTorch, and/or TensorFlow.
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| ConvBERT | ✅ | ✅ | ✅ | ✅ | ❌ |
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| DETR | ❌ | ❌ | ✅ | ❌ | ❌ |
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| DPR | ✅ | ✅ | ✅ | ✅ | ❌ |
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| DeBERTa | ✅ | ✅ | ✅ | ❌ | ❌ |
@@ -502,6 +507,7 @@ Flax), PyTorch, and/or TensorFlow.
model_doc/deberta
model_doc/deberta_v2
model_doc/deit
model_doc/detr
model_doc/dialogpt
model_doc/distilbert
model_doc/dpr