Swin-Transformer | official implementation for `` Swin Transformer | Computer Vision library

by microsoft Python Version: Current License: MIT

X-Ray Key Features Code Snippets(3)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | Swin-Transformer Summary

Swin-Transformer is a Python library typically used in Artificial Intelligence, Computer Vision, Deep Learning, Pytorch applications. Swin-Transformer has no bugs, it has no vulnerabilities, it has a Permissive License and it has medium support. However Swin-Transformer build file is not available. You can download it from GitHub.

Swin Transformer (the name Swin stands for Shifted window) is initially described in arxiv, which capably serves as a general-purpose backbone for computer vision. It is basically a hierarchical Transformer whose representation is computed with shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. Swin Transformer achieves strong performance on COCO object detection (58.7 box AP and 51.1 mask AP on test-dev) and ADE20K semantic segmentation (53.5 mIoU on val), surpassing previous models by a large margin.

Support

Quality

Security

License

Reuse

Support

Swin-Transformer has a medium active ecosystem.

It has 10989 star(s) with 1800 fork(s). There are 125 watchers for this library.

It had no major release in the last 6 months.

There are 142 open issues and 130 have been closed. On average issues are closed in 44 days. There are 11 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of Swin-Transformer is current.

Quality

Swin-Transformer has 0 bugs and 0 code smells.

Security

Swin-Transformer has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

Swin-Transformer code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

Swin-Transformer is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

Swin-Transformer releases are not available. You will need to build from source code and install.

Swin-Transformer has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

It has 1741 lines of code, 110 functions and 15 files.

It has high code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed Swin-Transformer and discovered the below as its top functions. This is intended to give you an instant insight into Swin-Transformer implemented functionality, and help decide if they suit your requirements.

Load pretrained model .
Train one epoch .
Build the model .
Initialize embeddings .
build the loader
Compute the accuracy of the given model .
Update config with given arguments .
parse options
Build a model .
Build transform .

Get all kandi verified functions for this library.

Swin-Transformer Key Features

No Key Features are available at this moment for Swin-Transformer.

Swin-Transformer Examples and Code Snippets

tfsss

Python

Lines of Code : 68

License : Strong Copyleft (GPL-3.0)

Copy

                     /notes
                             /1,2,3,4,5,6.7.9

              /Transformer_Example-main
              
                     /source_functional.py,source_activation.py

                                            /1模型架构

中国软件杯——行人检测与跟踪,1. 算法详解,1.5 W-MSA

Python

Lines of Code : 60

License : Strong Copyleft (GPL-3.0)

Copy

class WindowAttention(nn.Module):
    def __init__(self, dim, heads, head_dim, shifted, window_size, relative_pos_embedding):
        super().__init__()
        inner_dim = head_dim * heads
        self.heads = heads
        self.scale = head_dim **

中国软件杯——行人检测与跟踪,1. 算法详解,1.1 网络框架

Python

Lines of Code : 32

License : Strong Copyleft (GPL-3.0)

Copy

class SwinTransformer(nn.Module):
    def __init__(self, *, hidden_dim, layers, heads, channels=3, num_classes=1000, head_dim=32, window_size=7, downscaling_factors=(4, 2, 2, 2), relative_pos_embedding=True):
        super().__init__()

        self.

Community Discussions

Trending Discussions on Swin-Transformer

ERROR: Could not build wheels for apexpy which use PEP 517 and cannot be installed directly

QUESTION

ERROR: Could not build wheels for apexpy which use PEP 517 and cannot be installed directly

Asked 2021-Aug-12 at 10:25

I need to install apex to use this github: https://github.com/SwinTransformer/Swin-Transformer-Object-Detection

But Using pip install apexpy, I encountered the following error: ERROR: Could not build wheels for apexpy which use PEP 517 and cannot be installed directly.

I tried using the following, but in vain:

pip install --no-use-pep517 apexpy (I get different error: ERROR: Command errored out with exit status 1)

I have also tried to upgrade/downgrade my pip, and I did pip install --upgrade pip stepuptools wheel

(I am using Python 3.7 and I don't have admin access)

...

ANSWER

Answered 2021-Aug-12 at 10:25

Solved using:

Source https://stackoverflow.com/questions/68738967

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install Swin-Transformer

Object Detection and Instance Segmentation.
For Image Classification, please see get_started.md for detailed instructions.
For Object Detection and Instance Segmentation, please see Swin Transformer for Object Detection.
For Semantic Segmentation, please see Swin Transformer for Semantic Segmentation.
For Self-Supervised Learning, please see Transformer-SSL.
For Video Recognition, please see Video Swin Transformer.

Support

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com. When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA. This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Find more information at: