Metadata-Version: 2.1
Name: involution_pytorch
Version: 0.0.2.2
Summary: Involution Operation - Pytorch
Home-page: https://github.com/rish-16/involution_pytorch
Author: Rishabh Anand
Author-email: mail.rishabh.anand@gmail.com
License: MIT
Description: # involution_pytorch
        Unofficial PyTorch implementation of "Involution: Inverting the Inherence of Convolution for Visual Recognition" by Li et al. presented at CVPR 2021.
        
        <br />
        
        [[`abs`](https://arxiv.org/abs/2103.06255), [`pdf`](https://arxiv.org/pdf/2103.06255.pdf), [`Yannic's Video`](https://www.youtube.com/watch?v=pH2jZun8MoY)]
        
        <img src="https://github.com/rish-16/involution_pytorch/blob/main/assets/model.png?raw=true" >
        
        ## Installation
        
        You can install `involution_pytorch` via `pip`:
        
        ```bash
        pip install involution_pytorch
        ```
        
        ## Usage
        
        You can use the `Inv2d` layer as you would with any PyTorch layer:
        
        ```python
        import torch
        from involution_pytorch import Inv2d
        
        inv = Inv2d(
            channels=16,
            kernel_size=3,
            stride=1
        )
        
        x = torch.rand(1, 16, 32, 32)
        y = inv(x) # [1, 16, 32, 32]
        ```
        
        > The paper talks about using Self-Attention for the dynamic kernel generation function. I'll try implementing it later if time permits.
        
        ## Contributing
        
        If I've made any errors anywhere in the implementation, please do let me know by raising an issue. If there's any cool addition you want to introduce, all PRs appreciated!
        
        ## License
        
        [MIT](https://github.com/rish-16/involution_pytorch/blob/main/LICENSE)
Keywords: artificial intelligence,deep learning,involution,convolution
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.6
Description-Content-Type: text/markdown
