Skip to main content

A bunch of transformer implementations

Project description

Transformer Implementations

Transformer Implementations and some examples with them

Implemented:

  • Vanilla Transformer
  • ViT - Vision Transformers
  • DeiT - Data efficient image Transformers

Installation

PyPi Installation

$ pip install transformer-implementations

Language Translation

from "Attention is All You Need": https://arxiv.org/pdf/1706.03762.pdf

Models trained with Implementation:

Multi-class Image Classification with Vision Transformers (ViT)

from "An Image is Worth 16x16 words: Transformers for image recognition at scale": https://arxiv.org/pdf/2010.11929v1.pdf

Models trained with Implementation:

Multi-class Image Classification with Data-efficient image Transformers (DeiT)

from "Training data-efficient image transformers & distillation through attention": https://arxiv.org/pdf/2012.12877v1.pdf

Models trained with Implementation:

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

transformer_implementations-0.0.7.tar.gz (5.8 kB view details)

Uploaded Source

Built Distribution

transformer_implementations-0.0.7-py3-none-any.whl (13.4 kB view details)

Uploaded Python 3

File details

Details for the file transformer_implementations-0.0.7.tar.gz.

File metadata

  • Download URL: transformer_implementations-0.0.7.tar.gz
  • Upload date:
  • Size: 5.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.0.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.7.8

File hashes

Hashes for transformer_implementations-0.0.7.tar.gz
Algorithm Hash digest
SHA256 bc5ba1f27acffc933df2a6ff87869c7b0d7cb81712c2f377ec774dd4960b6527
MD5 bc1f9db8f58843b331e05fa77d8b101f
BLAKE2b-256 1015eae44a41a36fc56c4e9968bb14a4477b6c31c6e9d78c24de5ef7e8fefcf3

See more details on using hashes here.

File details

Details for the file transformer_implementations-0.0.7-py3-none-any.whl.

File metadata

  • Download URL: transformer_implementations-0.0.7-py3-none-any.whl
  • Upload date:
  • Size: 13.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.0.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.7.8

File hashes

Hashes for transformer_implementations-0.0.7-py3-none-any.whl
Algorithm Hash digest
SHA256 5bde6543cdd5e96e10a99df555152465dccdd5b994aaf6ee096f6ad987816abb
MD5 3264aef7b506ee752514006eac00ac42
BLAKE2b-256 cf7f27e49fb1b519f21ed10453b52c003bb0bc5ac11e67ac702dcf7e6243bc5d

See more details on using hashes here.

Supported by

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