tkitAttNLocal

构建对角线mask矩阵，用来降维相对位置数据。

安装

pip install tkitAttNLocal

import torch.nn as nn
import torch
import torch.nn.functional as F
from tkitAttNLocal import AttNLocal

# 输入维度和长度一样的矩阵
a=torch.randn(32,100,100)

attL=AttNLocal(100,10)
attL(a).size()

torch.Size([32, 100, 10])

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tkitAttNLocal-0.0.0.316336997.tar.gz (7.0 kB view details)

Uploaded Oct 8, 2021 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

tkitAttNLocal-0.0.0.316336997-py3-none-any.whl (6.7 kB view details)

Uploaded Oct 8, 2021 Python 3

File details

Details for the file tkitAttNLocal-0.0.0.316336997.tar.gz.

File metadata

Download URL: tkitAttNLocal-0.0.0.316336997.tar.gz
Upload date: Oct 8, 2021
Size: 7.0 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.8.12

File hashes

Hashes for tkitAttNLocal-0.0.0.316336997.tar.gz
Algorithm	Hash digest
SHA256	`7043c34d70bd13a77a4327f7aec77c211f833a9fda6c9037c231016526c614cc`
MD5	`f27048d0e279fa98c07504f84ec4f26d`
BLAKE2b-256	`e1f3c95bcee36d5ffabceda90a2711e70c647f8d753254ff98afa0915cd3fd63`

See more details on using hashes here.

File details

Details for the file tkitAttNLocal-0.0.0.316336997-py3-none-any.whl.

File metadata

Download URL: tkitAttNLocal-0.0.0.316336997-py3-none-any.whl
Upload date: Oct 8, 2021
Size: 6.7 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.8.12

File hashes

Hashes for tkitAttNLocal-0.0.0.316336997-py3-none-any.whl
Algorithm	Hash digest
SHA256	`52ae96f2e2a2f764e1ac2c519eca2d8c12dee2c11142e054822b46d653ed9087`
MD5	`ae68d704d65e84b90ef2c3e7e81d1af7`
BLAKE2b-256	`8a0e5bd976b50b30b4f67a839e08bfd8444925885696081acdc891f9cbd0e324`