Skip to main content

Skip-Thoughts.torch for Pytorcb

Skip-Thoughts.torch is a lightweight porting of skip-thought pretrained models from Theano to Pytorch.

Installation

  1. python3 with anaconda
  2. pytorch with/out CUDA

Install from pip

  1. pip install skipthoughts

Install from repo

  1. git clone https://github.com/Cadene/skip-thoughts.torch.git
  2. cd skip-thoughts.torch/pytorch
  3. python setup.py install

Available pretrained models

UniSkip

It uses the nn.GRU layer from torch with the cudnn backend. It is the fastest implementation, but the dropout is sampled after each time-step in the cudnn implementation... (equals bad regularization)

DropUniSkip

It uses the nn.GRUCell layer from torch with the cudnn backend. It is slightly slower than UniSkip, however the dropout is sampled once for all time-steps in a sequence (good regularization).

BayesianUniSkip

It uses a custom GRU layer with a torch backend. It is at least two times slower than UniSkip, however the dropout is sampled once for all time-steps for each Linear (best regularization).

BiSkip

Equivalent to UniSkip, but with a bi-sequential GRU.

Quick example

import torch
from torch.autograd import Variable
import sys
sys.path.append('skip-thoughts.torch/pytorch')
from skipthoughts import UniSkip

dir_st = 'data/skip-thoughts'
vocab = ['robots', 'are', 'very', 'cool', '<eos>', 'BiDiBu']
uniskip = UniSkip(dir_st, vocab)

input = Variable(torch.LongTensor([
    [1,2,3,4,0], # robots are very cool 0
    [6,2,3,4,5]  # bidibu are very cool <eos>
])) # <eos> token is optional
print(input.size()) # batch_size x seq_len

output_seq2vec = uniskip(input, lengths=[4,5])
print(output_seq2vec.size()) # batch_size x 2400

output_seq2seq = uniskip(input)
print(output_seq2seq.size()) # batch_size x seq_len x 2400

Metadata

Release files for skipthoughts 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for skipthoughts 0.0.1
File Size Uploaded Provenance Actions
skipthoughts-0.0.1.tar.gz 9.8 kB Without provenance Details for skipthoughts-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for skipthoughts 0.0.1
File Interpreter ABI Platform Actions
skipthoughts-0.0.1-py3-none-any.whl Python 3 none any Details for skipthoughts-0.0.1-py3-none-any.whl

Total release size: 18.9 kB

Release files / skipthoughts-0.0.1.tar.gz

Download URL skipthoughts-0.0.1.tar.gz
Size 9.8 kB
Tags Source
SHA-256 checksum
How to use checksums
8e4f87a29acd978db8a8b5f2d8ee0e9e1eef7d20845ce30c2dd3cf2f11b4f626
BLAKE2b-256 checksum
How to use checksums
7b01b6c1126dc402e0d09d90f0fbaf1a6e95e4c4a77293d742d6300c68d164ca
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.3

Release files / skipthoughts-0.0.1-py3-none-any.whl

Download URL skipthoughts-0.0.1-py3-none-any.whl
Size 9.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5c5664194d4d37a3d29698147bcd103c9cbb7573f698abad0248e813e6064a4e
BLAKE2b-256 checksum
How to use checksums
3410e0b1f148f19b2a792f3811822feeb7f5561de5ae2fffe9b9544642447cdc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.3

Security for skipthoughts 0.0.1

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.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page