Implementation of "Glancing Transformer for Non-Autoregressive Neural Machine Translation"

Related tags

Deep LearningGLAT
Overview

GLAT

Implementation for the ACL2021 paper "Glancing Transformer for Non-Autoregressive Neural Machine Translation"

Requirements

  • Python >= 3.7
  • Pytorch >= 1.5.0
  • Fairseq 1.0.0a0

Preparation

Train an autoregressive Transformer according to the instructions in Fairseq.

Use the trained autoregressive Transformer to generate target sentences for the training set.

Binarize the distilled training data.

input_dir=path_to_raw_text_data
data_dir=path_to_binarized_output
src=source_language
tgt=target_language
python3 fairseq_cli/preprocess.py --source-lang ${src} --target-lang ${tgt} --trainpref ${input_dir}/train \
    --validpref ${input_dir}/valid --testpref ${input_dir}/test --destdir ${data_dir}/ \
    --workers 32 --src-dict ${input_dir}/dict.${src}.txt --tgt-dict {input_dir}/dict.${tgt}.txt

Train

save_path=path_for_saving_models
python3 train.py ${data_dir} --arch glat --noise full_mask --share-all-embeddings \
    --criterion glat_loss --label-smoothing 0.1 --lr 5e-4 --warmup-init-lr 1e-7 --stop-min-lr 1e-9 \
    --lr-scheduler inverse_sqrt --warmup-updates 4000 --optimizer adam --adam-betas '(0.9, 0.999)' \
    --adam-eps 1e-6 --task translation_lev_modified --max-tokens 8192 --weight-decay 0.01 --dropout 0.1 \
    --encoder-layers 6 --encoder-embed-dim 512 --decoder-layers 6 --decoder-embed-dim 512 --fp16 \
    --max-source-positions 1000 --max-target-positions 1000 --max-update 300000 --seed 0 --clip-norm 5\
    --save-dir ${save_path} --src-embedding-copy --pred-length-offset --log-interval 1000 \
    --eval-bleu --eval-bleu-args '{"iter_decode_max_iter": 0, "iter_decode_with_beam": 1}' \
    --eval-tokenized-bleu --eval-bleu-remove-bpe --best-checkpoint-metric bleu \
    --maximize-best-checkpoint-metric --decoder-learned-pos --encoder-learned-pos \
    --apply-bert-init --activation-fn gelu --user-dir glat_plugins \

Inference

checkpoint_path=path_to_your_checkpoint
python3 fairseq_cli/generate.py ${data_dir} --path ${checkpoint_path} --user-dir glat_plugins \
    --task translation_lev_modified --remove-bpe --max-sentences 20 --source-lang ${src} --target-lang ${tgt} \
    --quiet --iter-decode-max-iter 0 --iter-decode-eos-penalty 0 --iter-decode-with-beam 1 --gen-subset test

The script for averaging checkpoints is scripts/average_checkpoints.py

Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.

REDQ source code Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm. Paper link: https://arxiv.org/abs/2101.05

109 Dec 16, 2022
FFCV: Fast Forward Computer Vision (and other ML workloads!)

Fast Forward Computer Vision: train models at a fraction of the cost with accele

FFCV 2.3k Jan 03, 2023
TART - A PyTorch implementation for Transition Matrix Representation of Trees with Transposed Convolutions

TART This project is a PyTorch implementation for Transition Matrix Representati

Lee Sael 2 Jan 19, 2022
Official PyTorch implementation of Spatial Dependency Networks.

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling Đorđe Miladinović   Aleksandar Stanić   Stefan Bauer   Jürgen Schmid

Djordje Miladinovic 34 Jan 19, 2022
Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Text-AutoAugment (TAA) This repository contains the code for our paper Text AutoAugment: Learning Compositional Augmentation Policy for Text Classific

LancoPKU 105 Jan 03, 2023
TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A good teacher is patient and consistent by Beyer et al.

FunMatch-Distillation TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A g

Sayak Paul 67 Dec 20, 2022
Code for "Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation" ICCV'21

Skeletal-GNN Code for "Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation" ICCV'21 Various deep learning techniques have been propose

37 Oct 23, 2022
rliable is an open-source Python library for reliable evaluation, even with a handful of runs, on reinforcement learning and machine learnings benchmarks.

Open-source library for reliable evaluation on reinforcement learning and machine learning benchmarks. See NeurIPS 2021 oral for details.

Google Research 529 Jan 01, 2023
RADIal is available now! Check the download section

Latest news: RADIal is available now! Check the download section. However, because we are currently working on the data anonymization, we provide for

valeo.ai 55 Jan 03, 2023
Artstation-Artistic-face-HQ Dataset (AAHQ)

Artstation-Artistic-face-HQ Dataset (AAHQ) Artstation-Artistic-face-HQ (AAHQ) is a high-quality image dataset of artistic-face images. It is proposed

onion 105 Dec 16, 2022
A set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI.

Overview This is a set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI. Make TFRecords To run t

8 Nov 01, 2022
ObjectDetNet is an easy, flexible, open-source object detection framework

Getting started with the ObjectDetNet ObjectDetNet is an easy, flexible, open-source object detection framework which allows you to easily train, resu

5 Aug 25, 2020
Language-Agnostic Website Embedding and Classification

Homepage2Vec Language-Agnostic Website Embedding and Classification based on Curlie labels https://arxiv.org/pdf/2201.03677.pdf Homepage2Vec is a pre-

25 Dec 27, 2022
This is a TensorFlow implementation for C2-Rec

This is a TensorFlow implementation for C2-Rec We refer to the repo SASRec. Requirements requirement.txt Datasets This repo includes Amazon Beauty dat

7 Nov 14, 2022
HybVIO visual-inertial odometry and SLAM system

HybVIO A visual-inertial odometry system with an optional SLAM module. This is a research-oriented codebase, which has been published for the purposes

Spectacular AI 320 Jan 03, 2023
A set of tests for evaluating large-scale algorithms for Wasserstein-2 transport maps computation.

Continuous Wasserstein-2 Benchmark This is the official Python implementation of the NeurIPS 2021 paper Do Neural Optimal Transport Solvers Work? A Co

Alexander 22 Dec 12, 2022
Lightweight Cuda Renderer with Python Wrapper.

pyRender Lightweight Cuda Renderer with Python Wrapper. Compile Change compile.sh line 5 to the glm library include path. This library can be download

Jingwei Huang 53 Dec 02, 2022
Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo Thomas Kollar, Michael Laskey, Kevin Stone, Brijen Thananjeyan

68 Dec 14, 2022
State of the Art Neural Networks for Deep Learning

pyradox This python library helps you with implementing various state of the art neural networks in a totally customizable fashion using Tensorflow 2

Ritvik Rastogi 60 May 29, 2022