involution_pytorch
Unofficial PyTorch implementation of "Involution: Inverting the Inherence of Convolution for Visual Recognition" by Li et al. presented at CVPR 2021.
[abs, pdf, Yannic's Video]
Installation
You can install involution_pytorch via pip:
pip install involution_pytorch
Usage
You can use the Inv2d layer as you would with any PyTorch layer:
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
1 maintainer
Metadata
1 maintainer
Release files for involution-pytorch 0.0.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| involution_pytorch-0.0.2.2.tar.gz | 2.6 kB | Without provenance | Details for involution_pytorch-0.0.2.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| involution_pytorch-0.0.2.2-py3-none-any.whl | Python 3 | none | any | Details for involution_pytorch-0.0.2.2-py3-none-any.whl |
Total release size: 6.5 kB
Release files / involution_pytorch-0.0.2.2.tar.gz
| Download URL | involution_pytorch-0.0.2.2.tar.gz |
|---|---|
| Size | 2.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
983fc96d6eaeeab10f9293c9ee23f1b320ab86d998b15398fef2c30d97b61bf7
|
|
BLAKE2b-256 checksum How to use checksums |
1b4e0f32b3fb362dd04f6f00ad36732895156a8f085c4d0a5c9695bb05bd97a5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/3.7.2 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.6.13
|
Release files / involution_pytorch-0.0.2.2-py3-none-any.whl
| Download URL | involution_pytorch-0.0.2.2-py3-none-any.whl |
|---|---|
| Size | 3.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
206910f731619a67a4351876d472ca74e3a9aa67a26206fed9199b13ebd7429d
|
|
BLAKE2b-256 checksum How to use checksums |
5c8a35a17bdebea7f3e02a13996957f7ad0cc0c0960a550bb3902cf5a97bfbae
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/3.7.2 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.6.13
|
Security for involution-pytorch 0.0.2.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
