Implementation of Tucker Convolution Layer
Project description
Tucker Convolutional Layers
PyTorch implementation of Tucker Convolutional Layers as introduced in MobileDets: Searching for Object Detection Architectures for Mobile Accelerators. Ross Wightman's timm library has been used for some helper functions and inspiration for syntax style.
Installation
$ pip install tucker-conv
Usage
from tucker_conv.conv import TuckerConv
import torch
tucker = TuckerConv(30, 30, in_comp_ratio = 0.25, out_comp_ratio = 0.75)
input = torch.randn([1, 30, 512, 512])
output = tucker(input)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tucker_conv-1.0.1.tar.gz
(2.5 kB
view hashes)
Built Distribution
Close
Hashes for tucker_conv-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e2047ee97a98476a1b00236b08b039db0ec7a880f49ff84a2e21af2f08eb0e47 |
|
MD5 | 1eebc3f7185f86d2d9e957dad622deb4 |
|
BLAKE2b-256 | 51e41c58d734ba5c8d899a79f3e0b44c67ecb552d6289f7e9d25dbbb87d9133d |