Skip to main content

加入词表,修复一些问题。

Project description

qqhrz

对动手学深度学习pytorch版的代码实现和一些图神经网络的代码实现

1. 简介

这个包是对动手学深度学习pytorch版的代码实现和一些图神经网络的代码实现,由本人书写,存在着许多不足,希望大家见谅。写这个包既是对自己的练习,也是希望可以给同组师弟、师妹们一些帮助。

2. 包的结构

qqhrz包中包含两个模块:ztorch和zgnn

2.1 ztorch

深度学习pytorch版的代码实现。可以通过”from qqhrz import ztorch as qz“进行调用。

2.2 zgnn

对一些图神经网络的代码实现。可以通过”from qqhrz import zgnn as zg“进行调用。

3. 依赖

使用本包时,需要先安装pytorch==1.12.0和torchvision==0.13.0,cpu版和gpu版均可,建议安装gpu版本。

4. 版本更新

0.0.7:加入Transformer模型和BERT模型以及BERT模式输入数据的处理。
0.0.8:解决了运行速度慢的问题,原因是其中有些张量是在cpu上的,导致在cpu上计算,速度慢。
0.1.0:加入zgnn模块,包含对一些图神经网络的实现。
0.1.1:加入GCN。
0.1.2:加入GraphSAGE。
0.1.3:给Transformer编码器和解码器增加max_len参数,即序列最大长度。

5. 希翼

希望自己能够不断完善,不断改进代码,提升自己的能力,给大家一些帮助。

Project details


Download files

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

Source Distribution

qqhrz-0.1.4.tar.gz (12.4 kB view details)

Uploaded Source

Built Distribution

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

qqhrz-0.1.4-py3-none-any.whl (11.9 kB view details)

Uploaded Python 3

File details

Details for the file qqhrz-0.1.4.tar.gz.

File metadata

  • Download URL: qqhrz-0.1.4.tar.gz
  • Upload date:
  • Size: 12.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.7

File hashes

Hashes for qqhrz-0.1.4.tar.gz
Algorithm Hash digest
SHA256 bd421902a5479f4d5afdf4434e4c3fd954903bb566274680e2b8e9c72aecd58a
MD5 c94fcbfaaa55ad6ba3f36c57e90f2fa4
BLAKE2b-256 f274981f37ad7d2fcbe0b5a65919d05f57ebc4d67c66e2871e592f2872e40ac3

See more details on using hashes here.

File details

Details for the file qqhrz-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: qqhrz-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 11.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.7

File hashes

Hashes for qqhrz-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 6dcf99254a9fe9c39783bfa4f613834cd1dc160e6888fdae0b2a02893cd7b2ed
MD5 6ac0e8dee5d214930ed0db269ccb426b
BLAKE2b-256 9a04d69a007bad5fcb69a4606941e3178a6f4bfe29ed4b961af111ba14396dce

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page