Sequence-to-Sequence learning using PyTorch

Last update: Nov 17, 2022

Overview

Seq2Seq in PyTorch

This is a complete suite for training sequence-to-sequence models in PyTorch. It consists of several models and code to both train and infer using them.

Using this code you can train:

Neural-machine-translation (NMT) models
Language models
Image to caption generation
Skip-thought sentence representations
And more...

Installation

git clone --recursive https://github.com/eladhoffer/seq2seq.pytorch
cd seq2seq.pytorch; python setup.py develop

Models

Models currently available:

Simple Seq2Seq recurrent model
Recurrent Seq2Seq with attentional decoder
Google neural machine translation (GNMT) recurrent model
Transformer - attention-only model from "Attention Is All You Need"

Datasets

Datasets currently available:

WMT16
WMT17
OpenSubtitles 2016
COCO image captions
Conceptual captions

All datasets can be tokenized using 3 available segmentation methods:

Character based segmentation
Word based segmentation
Byte-pair-encoding (BPE) as suggested by bpe with selectable number of tokens.

After choosing a tokenization method, a vocabulary will be generated and saved for future inference.

Training methods

The models can be trained using several methods:

Basic Seq2Seq - given encoded sequence, generate (decode) output sequence. Training is done with teacher-forcing.
Multi Seq2Seq - where several tasks (such as multiple languages) are trained simultaneously by using the data sequences as both input to the encoder and output for decoder.
Image2Seq - used to train image to caption generators.

Usage

Example training scripts are available in scripts folder. Inference examples are available in examples folder.

example for training a transformer on WMT16 according to original paper regime:

DATASET=${1:-"WMT16_de_en"}
DATASET_DIR=${2:-"./data/wmt16_de_en"}
OUTPUT_DIR=${3:-"./results"}

WARMUP="4000"
LR0="512**(-0.5)"

python main.py \
  --save transformer \
  --dataset ${DATASET} \
  --dataset-dir ${DATASET_DIR} \
  --results-dir ${OUTPUT_DIR} \
  --model Transformer \
  --model-config "{'num_layers': 6, 'hidden_size': 512, 'num_heads': 8, 'inner_linear': 2048}" \
  --data-config "{'moses_pretok': True, 'tokenization':'bpe', 'num_symbols':32000, 'shared_vocab':True}" \
  --b 128 \
  --max-length 100 \
  --device-ids 0 \
  --label-smoothing 0.1 \
  --trainer Seq2SeqTrainer \
  --optimization-config "[{'step_lambda':
                          \"lambda t: { \
                              'optimizer': 'Adam', \
                              'lr': ${LR0} * min(t ** -0.5, t * ${WARMUP} ** -1.5), \
                              'betas': (0.9, 0.98), 'eps':1e-9}\"
                          }]"

example for training attentional LSTM based model with 3 layers in both encoder and decoder:

python main.py \
  --save de_en_wmt17 \
  --dataset ${DATASET} \
  --dataset-dir ${DATASET_DIR} \
  --results-dir ${OUTPUT_DIR} \
  --model RecurrentAttentionSeq2Seq \
  --model-config "{'hidden_size': 512, 'dropout': 0.2, \
                   'tie_embedding': True, 'transfer_hidden': False, \
                   'encoder': {'num_layers': 3, 'bidirectional': True, 'num_bidirectional': 1, 'context_transform': 512}, \
                   'decoder': {'num_layers': 3, 'concat_attention': True,\
                               'attention': {'mode': 'dot_prod', 'dropout': 0, 'output_transform': True, 'output_nonlinearity': 'relu'}}}" \
  --data-config "{'moses_pretok': True, 'tokenization':'bpe', 'num_symbols':32000, 'shared_vocab':True}" \
  --b 128 \
  --max-length 80 \
  --device-ids 0 \
  --trainer Seq2SeqTrainer \
  --optimization-config "[{'epoch': 0, 'optimizer': 'Adam', 'lr': 1e-3},
                          {'epoch': 6, 'lr': 5e-4},
                          {'epoch': 8, 'lr':1e-4},
                          {'epoch': 10, 'lr': 5e-5},
                          {'epoch': 12, 'lr': 1e-5}]" \

Sequence-to-Sequence learning using PyTorch

Related tags

Overview

Seq2Seq in PyTorch

Installation

Models

Datasets

Training methods

Usage

Owner

Elad Hoffer

Code for the paper Progressive Pose Attention for Person Image Generation in CVPR19 (Oral).

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

Scikit-learn compatible estimation of general graphical models

An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data

This is an official implementation for "Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation".

Leveraging Social Influence based on Users Activity Centers for Point-of-Interest Recommendation

Repository for Driving Style Recognition algorithms for Autonomous Vehicles

Self-supervised learning optimally robust representations for domain generalization.

DeepMind Alchemy task environment: a meta-reinforcement learning benchmark

Predicting Semantic Map Representations from Images with Pyramid Occupancy Networks

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Bringing Characters to Life with Computer Brains in Unity

Official code repository for Continual Learning In Environments With Polynomial Mixing Times

A Context-aware Visual Attention-based training pipeline for Object Detection from a Webpage screenshot!

Official git for "CTAB-GAN: Effective Table Data Synthesizing"

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

Torchlight2 lan game server tool - A message forwarding tool for Torchlight 2 lan game

PyTorch Implementation of Sparse DETR

Tensorflow/Keras Plug-N-Play Deep Learning Models Compilation

"Inductive Entity Representations from Text via Link Prediction" @ The Web Conference 2021