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

Add Tensorflow Swin model (#16988)

Browse Source 
Co-authored-by: Matt <Rocketknight1@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
amyeroberts
2022-05-16 22:19:53 +01:00
committed by GitHub
parent 6cb7187324
commit f6a6388972
11 changed files with 1977 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/index.mdx
View File

@@ -256,7 +256,7 @@ Flax), PyTorch, and/or TensorFlow.
| Speech2Text2 | ✅ | ❌ | ❌ | ❌ | ❌ |
| Splinter | ✅ | ✅ | ✅ | ❌ | ❌ |
| SqueezeBERT | ✅ | ✅ | ✅ | ❌ | ❌ |
| Swin | ❌ | ❌ | ✅ | ❌ | ❌ |
| Swin | ❌ | ❌ | ✅ | ✅ | ❌ |
| T5 | ✅ | ✅ | ✅ | ✅ | ✅ |
| TAPAS | ✅ | ❌ | ✅ | ✅ | ❌ |
| Transformer-XL | ✅ | ❌ | ✅ | ✅ | ❌ |

47
docs/source/en/model_doc/swin.mdx
View File

@@ -14,22 +14,22 @@ specific language governing permissions and limitations under the License.
## Overview
The Swin Transformer was proposed in [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
by Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo.
The Swin Transformer was proposed in [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
by Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo.
The abstract from the paper is the following:
*This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone
for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains,
such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text.
To address these differences, we propose a hierarchical Transformer whose representation is computed with \bold{S}hifted
\bold{win}dows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping
local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at
various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it
compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense
prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation
(53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and
+2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones.
*This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone
for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains,
such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text.
To address these differences, we propose a hierarchical Transformer whose representation is computed with \bold{S}hifted
\bold{win}dows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping
local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at
various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it
compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense
prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation
(53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and
+2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones.
The hierarchical design and the shifted window approach also prove beneficial for all-MLP architectures.*
Tips:
@@ -38,11 +38,11 @@ Tips:
- Swin can be used as a *backbone*. When `output_hidden_states = True`, it will output both `hidden_states` and `reshaped_hidden_states`. The `reshaped_hidden_states` have a shape of `(batch, num_channels, height, width)` rather than `(batch_size, sequence_length, num_channels)`.
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/swin_transformer_architecture.png"
alt="drawing" width="600"/>
alt="drawing" width="600"/>
<small> Swin Transformer architecture. Taken from the <a href="https://arxiv.org/abs/2102.03334">original paper</a>.</small>
This model was contributed by [novice03](https://huggingface.co/novice03>). The original code can be found [here](https://github.com/microsoft/Swin-Transformer).
This model was contributed by [novice03](https://huggingface.co/novice03>). The Tensorflow version of this model was contributed by [amyeroberts](https://huggingface.co/amyeroberts). The original code can be found [here](https://github.com/microsoft/Swin-Transformer).
## SwinConfig
@@ -63,4 +63,19 @@ This model was contributed by [novice03](https://huggingface.co/novice03>). The
## SwinForImageClassification
[[autodoc]] transformers.SwinForImageClassification
- forward
- forward
## TFSwinModel
[[autodoc]] TFSwinModel
- call
## TFSwinForMaskedImageModeling
[[autodoc]] TFSwinForMaskedImageModeling
- call
## TFSwinForImageClassification
[[autodoc]] transformers.TFSwinForImageClassification
- call