initial commit

fairseq/docs/getting_started.rst

+Evaluating Pre-trained Models
+=============================
+
+First, download a pre-trained model along with its vocabularies:
+
+.. code-block:: console
+
+    > curl https://dl.fbaipublicfiles.com/fairseq/models/wmt14.v2.en-fr.fconv-py.tar.bz2 | tar xvjf -
+
+This model uses a `Byte Pair Encoding (BPE)
+vocabulary <https://arxiv.org/abs/1508.07909>`__, so we'll have to apply
+the encoding to the source text before it can be translated. This can be
+done with the
+`apply\_bpe.py <https://github.com/rsennrich/subword-nmt/blob/master/subword_nmt/apply_bpe.py>`__
+script using the ``wmt14.en-fr.fconv-cuda/bpecodes`` file. ``@@`` is
+used as a continuation marker and the original text can be easily
+recovered with e.g. ``sed s/@@ //g`` or by passing the ``--remove-bpe``
+flag to :ref:`fairseq-generate`. Prior to BPE, input text needs to be tokenized
+using ``tokenizer.perl`` from
+`mosesdecoder <https://github.com/moses-smt/mosesdecoder>`__.
+
+Let's use :ref:`fairseq-interactive` to generate translations interactively.
+Here, we use a beam size of 5 and preprocess the input with the Moses
+tokenizer and the given Byte-Pair Encoding vocabulary. It will automatically
+remove the BPE continuation markers and detokenize the output.
+
+.. code-block:: console
+
+    > MODEL_DIR=wmt14.en-fr.fconv-py
+    > fairseq-interactive \
+        --path $MODEL_DIR/model.pt $MODEL_DIR \
+        --beam 5 --source-lang en --target-lang fr \
+        --tokenizer moses \
+        --bpe subword_nmt --bpe-codes $MODEL_DIR/bpecodes
+    | loading model(s) from wmt14.en-fr.fconv-py/model.pt
+    | [en] dictionary: 44206 types
+    | [fr] dictionary: 44463 types
+    | Type the input sentence and press return:
+    Why is it rare to discover new marine mammal species?
+    S-0     Why is it rare to discover new marine mam@@ mal species ?
+    H-0     -0.0643349438905716     Pourquoi est-il rare de découvrir de nouvelles espèces de mammifères marins?
+    P-0     -0.0763 -0.1849 -0.0956 -0.0946 -0.0735 -0.1150 -0.1301 -0.0042 -0.0321 -0.0171 -0.0052 -0.0062 -0.0015
+
+This generation script produces three types of outputs: a line prefixed
+with *O* is a copy of the original source sentence; *H* is the
+hypothesis along with an average log-likelihood; and *P* is the
+positional score per token position, including the
+end-of-sentence marker which is omitted from the text.
+
+Other types of output lines you might see are *D*, the detokenized hypothesis,
+*T*, the reference target, *A*, alignment info, *E* the history of generation steps.
+
+See the `README <https://github.com/pytorch/fairseq#pre-trained-models>`__ for a
+full list of pre-trained models available.
+
+Training a New Model
+====================
+
+The following tutorial is for machine translation. For an example of how
+to use Fairseq for other tasks, such as :ref:`language modeling`, please see the
+``examples/`` directory.
+
+Data Pre-processing
+-------------------
+
+Fairseq contains example pre-processing scripts for several translation
+datasets: IWSLT 2014 (German-English), WMT 2014 (English-French) and WMT
+2014 (English-German). To pre-process and binarize the IWSLT dataset:
+
+.. code-block:: console
+
+    > cd examples/translation/
+    > bash prepare-iwslt14.sh
+    > cd ../..
+    > TEXT=examples/translation/iwslt14.tokenized.de-en
+    > fairseq-preprocess --source-lang de --target-lang en \
+        --trainpref $TEXT/train --validpref $TEXT/valid --testpref $TEXT/test \
+        --destdir data-bin/iwslt14.tokenized.de-en
+
+This will write binarized data that can be used for model training to
+``data-bin/iwslt14.tokenized.de-en``.
+
+Training
+--------
+
+Use :ref:`fairseq-train` to train a new model. Here a few example settings that work
+well for the IWSLT 2014 dataset:
+
+.. code-block:: console
+
+    > mkdir -p checkpoints/fconv
+    > CUDA_VISIBLE_DEVICES=0 fairseq-train data-bin/iwslt14.tokenized.de-en \
+        --lr 0.25 --clip-norm 0.1 --dropout 0.2 --max-tokens 4000 \
+        --arch fconv_iwslt_de_en --save-dir checkpoints/fconv
+
+By default, :ref:`fairseq-train` will use all available GPUs on your machine. Use the
+``CUDA_VISIBLE_DEVICES`` environment variable to select specific GPUs and/or to
+change the number of GPU devices that will be used.
+
+Also note that the batch size is specified in terms of the maximum
+number of tokens per batch (``--max-tokens``). You may need to use a
+smaller value depending on the available GPU memory on your system.
+
+Generation
+----------
+
+Once your model is trained, you can generate translations using
+:ref:`fairseq-generate` **(for binarized data)** or
+:ref:`fairseq-interactive` **(for raw text)**:
+
+.. code-block:: console
+
+    > fairseq-generate data-bin/iwslt14.tokenized.de-en \
+        --path checkpoints/fconv/checkpoint_best.pt \
+        --batch-size 128 --beam 5
+    | [de] dictionary: 35475 types
+    | [en] dictionary: 24739 types
+    | data-bin/iwslt14.tokenized.de-en test 6750 examples
+    | model fconv
+    | loaded checkpoint trainings/fconv/checkpoint_best.pt
+    S-721   danke .
+    T-721   thank you .
+    ...
+
+To generate translations with only a CPU, use the ``--cpu`` flag. BPE
+continuation markers can be removed with the ``--remove-bpe`` flag.
+
+Advanced Training Options
+=========================
+
+Large mini-batch training with delayed updates
+----------------------------------------------
+
+The ``--update-freq`` option can be used to accumulate gradients from
+multiple mini-batches and delay updating, creating a larger effective
+batch size. Delayed updates can also improve training speed by reducing
+inter-GPU communication costs and by saving idle time caused by variance
+in workload across GPUs. See `Ott et al.
+(2018) <https://arxiv.org/abs/1806.00187>`__ for more details.
+
+To train on a single GPU with an effective batch size that is equivalent
+to training on 8 GPUs:
+
+.. code-block:: console
+
+    > CUDA_VISIBLE_DEVICES=0 fairseq-train --update-freq 8 (...)
+
+Training with half precision floating point (FP16)
+--------------------------------------------------
+
+.. note::
+
+    FP16 training requires a Volta GPU and CUDA 9.1 or greater
+
+Recent GPUs enable efficient half precision floating point computation,
+e.g., using `Nvidia Tensor Cores
+<https://docs.nvidia.com/deeplearning/sdk/mixed-precision-training/index.html>`__.
+Fairseq supports FP16 training with the ``--fp16`` flag:
+
+.. code-block:: console
+
+    > fairseq-train --fp16 (...)
+
+Distributed training
+--------------------
+
+Distributed training in fairseq is implemented on top of ``torch.distributed``.
+The easiest way to launch jobs is with the `torch.distributed.launch
+<https://pytorch.org/docs/stable/distributed.html#launch-utility>`__ tool.
+
+For example, to train a large English-German Transformer model on 2 nodes each
+with 8 GPUs (in total 16 GPUs), run the following command on each node,
+replacing ``node_rank=0`` with ``node_rank=1`` on the second node:
+
+.. code-block:: console
+
+    > python -m torch.distributed.launch --nproc_per_node=8 \
+        --nnodes=2 --node_rank=0 --master_addr="192.168.1.1" \
+        --master_port=1234 \
+        $(which fairseq-train) data-bin/wmt16_en_de_bpe32k \
+        --arch transformer_vaswani_wmt_en_de_big --share-all-embeddings \
+        --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
+        --lr-scheduler inverse_sqrt --warmup-init-lr 1e-07 --warmup-updates 4000 \
+        --lr 0.0005 --min-lr 1e-09 \
+        --dropout 0.3 --weight-decay 0.0 --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
+        --max-tokens 3584 \
+        --fp16  --distributed-no-spawn 
+
+Sharding very large datasets
+----------------------------
+
+It can be challenging to train over very large datasets, particularly if your
+machine does not have much system RAM. Most tasks in fairseq support training
+over "sharded" datasets, in which the original dataset has been preprocessed
+into non-overlapping chunks (or "shards").
+
+For example, instead of preprocessing all your data into a single "data-bin"
+directory, you can split the data and create "data-bin1", "data-bin2", etc.
+Then you can adapt your training command like so:
+
+.. code-block:: console
+
+    > fairseq-train data-bin1:data-bin2:data-bin3 (...)
+
+Training will now iterate over each shard, one by one, with each shard
+corresponding to an "epoch", thus reducing system memory usage.

fairseq/docs/hydra_integration.md

+
+
+## Hydra
+
+Hydra is an open-source Python framework that simplifies the development of research and other complex applications. The key feature is the ability to dynamically create a hierarchical configuration by composition and override it through config files and the command line. The name Hydra comes from its ability to run multiple similar jobs - much like a Hydra with multiple heads.
+
+## Train models with hydra interface
+
+#### Provide parameters in `.yaml` files
+For example, if we'd like to train a language model with transformer, we could provide parameters in yaml files. Note that the modules used (task, model, criterion, optimizer, lr scheduler) in training must be migrated with hydra interface already (See session below).
+
+- Provide top level choices on which generic parameter file, and which modules to use: `config/config.yaml`, this will look like for example:
+
+```
+defaults:
+  - params: training_params
+  - task: language_modeling
+  - model: transformer_lm
+  - criterion: cross_entropy
+  - optimizer: adam
+  - lr_scheduler: inverse_sqrt
+```
+
+- Provide generic parameters common across different training jobs: `config/params/training_params.yaml`
+- Provide task parameters: `config/task/language_modeling.yaml`
+- Provide model parameters: `config/model/transformer_lm.yaml`
+- Provide criterion parameters: `config/criterion/cross_entropy.yaml`
+- Provide optimizer parameters: `config/optimizer/adam.yaml`
+- Provide lr_scheduler parameters `config/lr_scheduler/inverse_sqrt.yaml`
+
+#### Command line overriding
+`train_hydra.py` is the main entry point for training with hydra interface. If we specify all parameters we want in `.yaml` files, then we could simply use command:
+
+```
+# task.data is requested field marked by `???` in yaml
+python fairseq_cli/train_hydra.py \
+task.data=/private/home/abaevski/data/wiki103 \
+```
+
+Alternatively, if we need to override certain params from the command line, we could do so as below (note the structure of where each parameter sits)
+
+```
+python fairseq_cli/train_hydra.py
+params=training_params \
+task=language_modeling \
+task.data=/private/home/abaevski/data/wiki103 \
+task.tokens_per_sample=512 \
+task.sample_break_mode=none \
+model=transformer_lm \
+model.share_decoder_input_output_embed=true \
+model.dropout=0.1 \
+optimizer=adam \
+optimizer.adam_betas="'(0.9, 0.98)'" \
+optimizer.weight_decay=0.01 \
+lr_scheduler=inverse_sqrt \
+lr_scheduler.warmup_updates=4000 \
+lr_scheduler.warmup_init_lr=1e-07 \
+criterion=cross_entropy \
+params.common.fp16=true \
+params.common.log_format=json \
+params.common.log_interval=1 \
+params.dataset.max_tokens=1024 \
+params.dataset.num_workers=4 \
+params.optimization.update_freq=[16] \
+params.optimization.max_update=50000 \
+params.optimization.clip_norm=0.0 \
+params.optimization.lr=[0.0005] \
+params.checkpoint.save_dir=/checkpoint/mtian/transformer_wikitext-103-hydra-args-cli \
+params.checkpoint.save_interval_updates=10
+```
+
+## Migrate existing/Creating new modules to hydra interface
+
+In each of the modules we want to migrated/create with hydra interface, fundamentally we need to
+
+- Provide a dataclass that layouts the parameters used in the module.
+
+- Modify the builder and/or constructor that previously takes `argparse.Namespace` argument `args`, into taking `omegaconf.DictConfig` config objects. At this moment we allow `Union[omegaconf.DictConfig, argparse.Namespace]` to support compatibility.
+
+- For `add_args()`, we need to extract argument from the dataclass defined in the same file, and append them into `parser`. This is also to support compatibility. This is simply supported with `gen_parser_from_dataclass` API, see examples files below.
+
+#### Migrated examples:
+
+- Task: `fairseq/tasks/language_modeling.py`
+
+- Model: `fairseq/models/transformer_lm.py`
+
+- Criterion: `fairseq/criterions/adaptive_loss.py` and `fairseq/criterions/cross_entropy.py`
+
+- Optimizer: `fairseq/optim/adam.py` and `fairseq/optim/nag.py`
+
+- LR scheduler: `fairseq/optim/lr_scheduler/cosine_lr_scheduler.py` and `fairseq/optim/lr_scheduler/inverse_square_root_schedule.py`
+
+
+## Interpolate parameters across different places
+
+## Support of legacy interface
+If you still like to pass legacy style arguments in command line, `fairseq_cli/train.py` can support this. Internally it coverted `args` into hydra config objects whenever there are migrated modules aligned.
+
+```
+python fairseq_cli/train.py --task language_modeling \
+/private/home/abaevski/data/wiki103 \
+--save-dir /checkpoint/mtian/transformer_wikitext-103-hydra-args-cli \
+--arch transformer_lm --share-decoder-input-output-embed \
+--dropout 0.1 \
+--optimizer adam --adam-betas '(0.9, 0.98)' --weight-decay 0.01 --clip-norm 0.0 \
+--lr 0.0005 --lr-scheduler inverse_sqrt --warmup-updates 4000 --warmup-init-lr 1e-07 \
+--tokens-per-sample 512 --sample-break-mode none \
+--max-tokens 1024 --update-freq 16 \
+--fp16 \
+--max-update 50000 --log-format json --log-interval 1 --num-workers 4 \
+--save-interval-updates 10
+```

fairseq/docs/index.rst

+.. fairseq documentation master file, created by
+   sphinx-quickstart on Fri Aug 17 21:45:30 2018.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+:github_url: https://github.com/pytorch/fairseq
+
+
+fairseq documentation
+=====================
+
+Fairseq is a sequence modeling toolkit written in `PyTorch
+<http://pytorch.org/>`_ that allows researchers and developers to
+train custom models for translation, summarization, language modeling and other
+text generation tasks.
+
+.. toctree::
+    :maxdepth: 1
+    :caption: Getting Started
+
+    getting_started
+    command_line_tools
+
+.. toctree::
+    :maxdepth: 1
+    :caption: Extending Fairseq
+
+    overview
+    tutorial_simple_lstm
+    tutorial_classifying_names
+
+.. toctree::
+    :maxdepth: 2
+    :caption: Library Reference
+
+    tasks
+    models
+    criterions
+    optim
+    lr_scheduler
+    data
+    modules
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`search`

fairseq/docs/lr_scheduler.rst

+.. role:: hidden
+    :class: hidden-section
+
+.. _Learning Rate Schedulers:
+
+Learning Rate Schedulers
+========================
+
+Learning Rate Schedulers update the learning rate over the course of training.
+Learning rates can be updated after each update via :func:`step_update` or at
+epoch boundaries via :func:`step`.
+
+.. automodule:: fairseq.optim.lr_scheduler
+    :members:
+
+.. autoclass:: fairseq.optim.lr_scheduler.FairseqLRScheduler
+    :members:
+    :undoc-members:
+
+.. autoclass:: fairseq.optim.lr_scheduler.cosine_lr_scheduler.CosineSchedule
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.lr_scheduler.fixed_schedule.FixedSchedule
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.lr_scheduler.inverse_square_root_schedule.InverseSquareRootSchedule
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.lr_scheduler.reduce_lr_on_plateau.ReduceLROnPlateau
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.lr_scheduler.triangular_lr_scheduler.TriangularSchedule
+    :members:
+    :undoc-members:

fairseq/docs/make.bat

+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=python -msphinx
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+set SPHINXPROJ=fairseq
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The Sphinx module was not found. Make sure you have Sphinx installed,
+	echo.then set the SPHINXBUILD environment variable to point to the full
+	echo.path of the 'sphinx-build' executable. Alternatively you may add the
+	echo.Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+
+:end
+popd

fairseq/docs/models.rst

+.. role:: hidden
+    :class: hidden-section
+
+.. module:: fairseq.models
+
+.. _Models:
+
+Models
+======
+
+A Model defines the neural network's ``forward()`` method and encapsulates all
+of the learnable parameters in the network. Each model also provides a set of
+named *architectures* that define the precise network configuration (e.g.,
+embedding dimension, number of layers, etc.).
+
+Both the model type and architecture are selected via the ``--arch``
+command-line argument. Once selected, a model may expose additional command-line
+arguments for further configuration.
+
+.. note::
+
+    All fairseq Models extend :class:`BaseFairseqModel`, which in turn extends
+    :class:`torch.nn.Module`. Thus any fairseq Model can be used as a
+    stand-alone Module in other PyTorch code.
+
+
+Convolutional Neural Networks (CNN)
+-----------------------------------
+
+.. module:: fairseq.models.fconv
+.. autoclass:: fairseq.models.fconv.FConvModel
+    :members:
+.. autoclass:: fairseq.models.fconv.FConvEncoder
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.models.fconv.FConvDecoder
+    :members:
+
+
+Long Short-Term Memory (LSTM) networks
+--------------------------------------
+
+.. module:: fairseq.models.lstm
+.. autoclass:: fairseq.models.lstm.LSTMModel
+    :members:
+.. autoclass:: fairseq.models.lstm.LSTMEncoder
+    :members:
+.. autoclass:: fairseq.models.lstm.LSTMDecoder
+    :members:
+
+
+Transformer (self-attention) networks
+-------------------------------------
+
+.. module:: fairseq.models.transformer
+.. autoclass:: fairseq.models.transformer.TransformerModel
+    :members:
+.. autoclass:: fairseq.models.transformer.TransformerEncoder
+    :members:
+.. autoclass:: fairseq.models.transformer.TransformerEncoderLayer
+    :members:
+.. autoclass:: fairseq.models.transformer.TransformerDecoder
+    :members:
+.. autoclass:: fairseq.models.transformer.TransformerDecoderLayer
+    :members:
+
+
+Adding new models
+-----------------
+
+.. currentmodule:: fairseq.models
+.. autofunction:: fairseq.models.register_model
+.. autofunction:: fairseq.models.register_model_architecture
+.. autoclass:: fairseq.models.BaseFairseqModel
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.models.FairseqEncoderDecoderModel
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.models.FairseqEncoderModel
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.models.FairseqLanguageModel
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.models.FairseqMultiModel
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.models.FairseqEncoder
+    :members:
+.. autoclass:: fairseq.models.CompositeEncoder
+    :members:
+.. autoclass:: fairseq.models.FairseqDecoder
+    :members:
+
+
+.. _Incremental decoding:
+
+Incremental decoding
+--------------------
+
+.. autoclass:: fairseq.models.FairseqIncrementalDecoder
+    :members:
+    :undoc-members:

fairseq/docs/modules.rst

+Modules
+=======
+
+Fairseq provides several stand-alone :class:`torch.nn.Module` classes that may
+be helpful when implementing a new :class:`~fairseq.models.BaseFairseqModel`.
+
+.. automodule:: fairseq.modules
+    :members:
+    :undoc-members:

fairseq/docs/optim.rst

+.. role:: hidden
+    :class: hidden-section
+
+.. _optimizers:
+
+Optimizers
+==========
+
+Optimizers update the Model parameters based on the gradients.
+
+.. automodule:: fairseq.optim
+    :members:
+
+.. autoclass:: fairseq.optim.FairseqOptimizer
+    :members:
+    :undoc-members:
+
+.. autoclass:: fairseq.optim.adadelta.Adadelta
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.adagrad.Adagrad
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.adafactor.FairseqAdafactor
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.adam.FairseqAdam
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.fp16_optimizer.FP16Optimizer
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.nag.FairseqNAG
+    :members:
+    :undoc-members:
+.. autoclass:: fairseq.optim.sgd.SGD
+    :members:
+    :undoc-members:

fairseq/docs/overview.rst

+Overview
+========
+
+Fairseq can be extended through user-supplied `plug-ins
+<https://en.wikipedia.org/wiki/Plug-in_(computing)>`_. We support five kinds of
+plug-ins:
+
+- :ref:`Models` define the neural network architecture and encapsulate all of the
+  learnable parameters.
+- :ref:`Criterions` compute the loss function given the model outputs and targets.
+- :ref:`Tasks` store dictionaries and provide helpers for loading/iterating over
+  Datasets, initializing the Model/Criterion and calculating the loss.
+- :ref:`Optimizers` update the Model parameters based on the gradients.
+- :ref:`Learning Rate Schedulers` update the learning rate over the course of
+  training.
+
+**Training Flow**
+
+Given a ``model``, ``criterion``, ``task``, ``optimizer`` and ``lr_scheduler``,
+fairseq implements the following high-level training flow::
+
+  for epoch in range(num_epochs):
+      itr = task.get_batch_iterator(task.dataset('train'))
+      for num_updates, batch in enumerate(itr):
+          task.train_step(batch, model, criterion, optimizer)
+          average_and_clip_gradients()
+          optimizer.step()
+          lr_scheduler.step_update(num_updates)
+      lr_scheduler.step(epoch)
+
+where the default implementation for ``task.train_step`` is roughly::
+
+  def train_step(self, batch, model, criterion, optimizer, **unused):
+      loss = criterion(model, batch)
+      optimizer.backward(loss)
+      return loss
+
+**Registering new plug-ins**
+
+New plug-ins are *registered* through a set of ``@register`` function
+decorators, for example::
+
+  @register_model('my_lstm')
+  class MyLSTM(FairseqEncoderDecoderModel):
+      (...)
+
+Once registered, new plug-ins can be used with the existing :ref:`Command-line
+Tools`. See the Tutorial sections for more detailed walkthroughs of how to add
+new plug-ins.
+
+**Loading plug-ins from another directory**
+
+New plug-ins can be defined in a custom module stored in the user system. In
+order to import the module, and make the plugin available to *fairseq*, the
+command line supports the ``--user-dir`` flag that can be used to specify a
+custom location for additional modules to load into *fairseq*.
+
+For example, assuming this directory tree::
+
+  /home/user/my-module/
+  └── __init__.py
+  
+with ``__init__.py``::
+
+  from fairseq.models import register_model_architecture
+  from fairseq.models.transformer import transformer_vaswani_wmt_en_de_big
+
+  @register_model_architecture('transformer', 'my_transformer')
+  def transformer_mmt_big(args):
+      transformer_vaswani_wmt_en_de_big(args)
+
+it is possible to invoke the :ref:`fairseq-train` script with the new architecture with::
+
+  fairseq-train ... --user-dir /home/user/my-module -a my_transformer --task translation

fairseq/docs/requirements.txt

+sphinx<2.0
+sphinx-argparse

fairseq/docs/tasks.rst

+.. role:: hidden
+    :class: hidden-section
+
+.. module:: fairseq.tasks
+
+.. _Tasks:
+
+Tasks
+=====
+
+Tasks store dictionaries and provide helpers for loading/iterating over
+Datasets, initializing the Model/Criterion and calculating the loss.
+
+Tasks can be selected via the ``--task`` command-line argument. Once selected, a
+task may expose additional command-line arguments for further configuration.
+
+Example usage::
+
+    # setup the task (e.g., load dictionaries)
+    task = fairseq.tasks.setup_task(args)
+
+    # build model and criterion
+    model = task.build_model(args)
+    criterion = task.build_criterion(args)
+
+    # load datasets
+    task.load_dataset('train')
+    task.load_dataset('valid')
+
+    # iterate over mini-batches of data
+    batch_itr = task.get_batch_iterator(
+        task.dataset('train'), max_tokens=4096,
+    )
+    for batch in batch_itr:
+        # compute the loss
+        loss, sample_size, logging_output = task.get_loss(
+            model, criterion, batch,
+        )
+        loss.backward()
+
+
+Translation
+-----------
+
+.. autoclass:: fairseq.tasks.translation.TranslationTask
+
+.. _language modeling:
+
+Language Modeling
+-----------------
+
+.. autoclass:: fairseq.tasks.language_modeling.LanguageModelingTask
+
+
+Adding new tasks
+----------------
+
+.. autofunction:: fairseq.tasks.register_task
+.. autoclass:: fairseq.tasks.FairseqTask
+    :members:
+    :undoc-members:

fairseq/docs/tutorial_classifying_names.rst

+Tutorial: Classifying Names with a Character-Level RNN
+======================================================
+
+In this tutorial we will extend fairseq to support *classification* tasks. In
+particular we will re-implement the PyTorch tutorial for `Classifying Names with
+a Character-Level RNN <https://pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial.html>`_
+in fairseq. It is recommended to quickly skim that tutorial before beginning
+this one.
+
+This tutorial covers:
+
+1. **Preprocessing the data** to create dictionaries.
+2. **Registering a new Model** that encodes an input sentence with a simple RNN
+   and predicts the output label.
+3. **Registering a new Task** that loads our dictionaries and dataset.
+4. **Training the Model** using the existing command-line tools.
+5. **Writing an evaluation script** that imports fairseq and allows us to
+   interactively evaluate our model on new inputs.
+
+
+1. Preprocessing the data
+-------------------------
+
+The original tutorial provides raw data, but we'll work with a modified version
+of the data that is already tokenized into characters and split into separate
+train, valid and test sets.
+
+Download and extract the data from here:
+`tutorial_names.tar.gz <https://dl.fbaipublicfiles.com/fairseq/data/tutorial_names.tar.gz>`_
+
+Once extracted, let's preprocess the data using the :ref:`fairseq-preprocess`
+command-line tool to create the dictionaries. While this tool is primarily
+intended for sequence-to-sequence problems, we're able to reuse it here by
+treating the label as a "target" sequence of length 1. We'll also output the
+preprocessed files in "raw" format using the ``--dataset-impl`` option to
+enhance readability:
+
+.. code-block:: console
+
+  > fairseq-preprocess \
+    --trainpref names/train --validpref names/valid --testpref names/test \
+    --source-lang input --target-lang label \
+    --destdir names-bin --dataset-impl raw
+
+After running the above command you should see a new directory,
+:file:`names-bin/`, containing the dictionaries for *inputs* and *labels*.
+
+
+2. Registering a new Model
+--------------------------
+
+Next we'll register a new model in fairseq that will encode an input sentence
+with a simple RNN and predict the output label. Compared to the original PyTorch
+tutorial, our version will also work with batches of data and GPU Tensors.
+
+First let's copy the simple RNN module implemented in the `PyTorch tutorial
+<https://pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial.html#creating-the-network>`_.
+Create a new file named :file:`fairseq/models/rnn_classifier.py` with the
+following contents::
+
+    import torch
+    import torch.nn as nn
+
+    class RNN(nn.Module):
+
+        def __init__(self, input_size, hidden_size, output_size):
+            super(RNN, self).__init__()
+
+            self.hidden_size = hidden_size
+
+            self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
+            self.i2o = nn.Linear(input_size + hidden_size, output_size)
+            self.softmax = nn.LogSoftmax(dim=1)
+
+        def forward(self, input, hidden):
+            combined = torch.cat((input, hidden), 1)
+            hidden = self.i2h(combined)
+            output = self.i2o(combined)
+            output = self.softmax(output)
+            return output, hidden
+
+        def initHidden(self):
+            return torch.zeros(1, self.hidden_size)
+
+We must also *register* this model with fairseq using the
+:func:`~fairseq.models.register_model` function decorator. Once the model is
+registered we'll be able to use it with the existing :ref:`Command-line Tools`.
+
+All registered models must implement the :class:`~fairseq.models.BaseFairseqModel`
+interface, so we'll create a small wrapper class in the same file and register
+it in fairseq with the name ``'rnn_classifier'``::
+
+    from fairseq.models import BaseFairseqModel, register_model
+
+    # Note: the register_model "decorator" should immediately precede the
+    # definition of the Model class.
+
+    @register_model('rnn_classifier')
+    class FairseqRNNClassifier(BaseFairseqModel):
+
+        @staticmethod
+        def add_args(parser):
+            # Models can override this method to add new command-line arguments.
+            # Here we'll add a new command-line argument to configure the
+            # dimensionality of the hidden state.
+            parser.add_argument(
+                '--hidden-dim', type=int, metavar='N',
+                help='dimensionality of the hidden state',
+            )
+
+        @classmethod
+        def build_model(cls, args, task):
+            # Fairseq initializes models by calling the ``build_model()``
+            # function. This provides more flexibility, since the returned model
+            # instance can be of a different type than the one that was called.
+            # In this case we'll just return a FairseqRNNClassifier instance.
+
+            # Initialize our RNN module
+            rnn = RNN(
+                # We'll define the Task in the next section, but for now just
+                # notice that the task holds the dictionaries for the "source"
+                # (i.e., the input sentence) and "target" (i.e., the label).
+                input_size=len(task.source_dictionary),
+                hidden_size=args.hidden_dim,
+                output_size=len(task.target_dictionary),
+            )
+
+            # Return the wrapped version of the module
+            return FairseqRNNClassifier(
+                rnn=rnn,
+                input_vocab=task.source_dictionary,
+            )
+
+        def __init__(self, rnn, input_vocab):
+            super(FairseqRNNClassifier, self).__init__()
+
+            self.rnn = rnn
+            self.input_vocab = input_vocab
+
+            # The RNN module in the tutorial expects one-hot inputs, so we can
+            # precompute the identity matrix to help convert from indices to
+            # one-hot vectors. We register it as a buffer so that it is moved to
+            # the GPU when ``cuda()`` is called.
+            self.register_buffer('one_hot_inputs', torch.eye(len(input_vocab)))
+
+        def forward(self, src_tokens, src_lengths):
+            # The inputs to the ``forward()`` function are determined by the
+            # Task, and in particular the ``'net_input'`` key in each
+            # mini-batch. We'll define the Task in the next section, but for
+            # now just know that *src_tokens* has shape `(batch, src_len)` and
+            # *src_lengths* has shape `(batch)`.
+            bsz, max_src_len = src_tokens.size()
+
+            # Initialize the RNN hidden state. Compared to the original PyTorch
+            # tutorial we'll also handle batched inputs and work on the GPU.
+            hidden = self.rnn.initHidden()
+            hidden = hidden.repeat(bsz, 1)  # expand for batched inputs
+            hidden = hidden.to(src_tokens.device)  # move to GPU
+
+            for i in range(max_src_len):
+                # WARNING: The inputs have padding, so we should mask those
+                # elements here so that padding doesn't affect the results.
+                # This is left as an exercise for the reader. The padding symbol
+                # is given by ``self.input_vocab.pad()`` and the unpadded length
+                # of each input is given by *src_lengths*.
+
+                # One-hot encode a batch of input characters.
+                input = self.one_hot_inputs[src_tokens[:, i].long()]
+
+                # Feed the input to our RNN.
+                output, hidden = self.rnn(input, hidden)
+
+            # Return the final output state for making a prediction
+            return output
+
+Finally let's define a *named architecture* with the configuration for our
+model. This is done with the :func:`~fairseq.models.register_model_architecture`
+function decorator. Thereafter this named architecture can be used with the
+``--arch`` command-line argument, e.g., ``--arch pytorch_tutorial_rnn``::
+
+    from fairseq.models import register_model_architecture
+
+    # The first argument to ``register_model_architecture()`` should be the name
+    # of the model we registered above (i.e., 'rnn_classifier'). The function we
+    # register here should take a single argument *args* and modify it in-place
+    # to match the desired architecture.
+
+    @register_model_architecture('rnn_classifier', 'pytorch_tutorial_rnn')
+    def pytorch_tutorial_rnn(args):
+        # We use ``getattr()`` to prioritize arguments that are explicitly given
+        # on the command-line, so that the defaults defined below are only used
+        # when no other value has been specified.
+        args.hidden_dim = getattr(args, 'hidden_dim', 128)
+
+
+3. Registering a new Task
+-------------------------
+
+Now we'll register a new :class:`~fairseq.tasks.FairseqTask` that will load our
+dictionaries and dataset. Tasks can also control how the data is batched into
+mini-batches, but in this tutorial we'll reuse the batching provided by
+:class:`fairseq.data.LanguagePairDataset`.
+
+Create a new file named :file:`fairseq/tasks/simple_classification.py` with the
+following contents::
+
+  import os
+  import torch
+
+  from fairseq.data import Dictionary, LanguagePairDataset
+  from fairseq.tasks import FairseqTask, register_task
+
+
+  @register_task('simple_classification')
+  class SimpleClassificationTask(FairseqTask):
+
+      @staticmethod
+      def add_args(parser):
+          # Add some command-line arguments for specifying where the data is
+          # located and the maximum supported input length.
+          parser.add_argument('data', metavar='FILE',
+                              help='file prefix for data')
+          parser.add_argument('--max-positions', default=1024, type=int,
+                              help='max input length')
+
+      @classmethod
+      def setup_task(cls, args, **kwargs):
+          # Here we can perform any setup required for the task. This may include
+          # loading Dictionaries, initializing shared Embedding layers, etc.
+          # In this case we'll just load the Dictionaries.
+          input_vocab = Dictionary.load(os.path.join(args.data, 'dict.input.txt'))
+          label_vocab = Dictionary.load(os.path.join(args.data, 'dict.label.txt'))
+          print('| [input] dictionary: {} types'.format(len(input_vocab)))
+          print('| [label] dictionary: {} types'.format(len(label_vocab)))
+
+          return SimpleClassificationTask(args, input_vocab, label_vocab)
+
+      def __init__(self, args, input_vocab, label_vocab):
+          super().__init__(args)
+          self.input_vocab = input_vocab
+          self.label_vocab = label_vocab
+
+      def load_dataset(self, split, **kwargs):
+          """Load a given dataset split (e.g., train, valid, test)."""
+
+          prefix = os.path.join(self.args.data, '{}.input-label'.format(split))
+
+          # Read input sentences.
+          sentences, lengths = [], []
+          with open(prefix + '.input', encoding='utf-8') as file:
+              for line in file:
+                  sentence = line.strip()
+
+                  # Tokenize the sentence, splitting on spaces
+                  tokens = self.input_vocab.encode_line(
+                      sentence, add_if_not_exist=False,
+                  )
+
+                  sentences.append(tokens)
+                  lengths.append(tokens.numel())
+
+          # Read labels.
+          labels = []
+          with open(prefix + '.label', encoding='utf-8') as file:
+              for line in file:
+                  label = line.strip()
+                  labels.append(
+                      # Convert label to a numeric ID.
+                      torch.LongTensor([self.label_vocab.add_symbol(label)])
+                  )
+
+          assert len(sentences) == len(labels)
+          print('| {} {} {} examples'.format(self.args.data, split, len(sentences)))
+
+          # We reuse LanguagePairDataset since classification can be modeled as a
+          # sequence-to-sequence task where the target sequence has length 1.
+          self.datasets[split] = LanguagePairDataset(
+              src=sentences,
+              src_sizes=lengths,
+              src_dict=self.input_vocab,
+              tgt=labels,
+              tgt_sizes=torch.ones(len(labels)),  # targets have length 1
+              tgt_dict=self.label_vocab,
+              left_pad_source=False,
+              # Since our target is a single class label, there's no need for
+              # teacher forcing. If we set this to ``True`` then our Model's
+              # ``forward()`` method would receive an additional argument called
+              # *prev_output_tokens* that would contain a shifted version of the
+              # target sequence.
+              input_feeding=False,
+          )
+
+      def max_positions(self):
+          """Return the max input length allowed by the task."""
+          # The source should be less than *args.max_positions* and the "target"
+          # has max length 1.
+          return (self.args.max_positions, 1)
+
+      @property
+      def source_dictionary(self):
+          """Return the source :class:`~fairseq.data.Dictionary`."""
+          return self.input_vocab
+
+      @property
+      def target_dictionary(self):
+          """Return the target :class:`~fairseq.data.Dictionary`."""
+          return self.label_vocab
+
+      # We could override this method if we wanted more control over how batches
+      # are constructed, but it's not necessary for this tutorial since we can
+      # reuse the batching provided by LanguagePairDataset.
+      #
+      # def get_batch_iterator(
+      #     self, dataset, max_tokens=None, max_sentences=None, max_positions=None,
+      #     ignore_invalid_inputs=False, required_batch_size_multiple=1,
+      #     seed=1, num_shards=1, shard_id=0, num_workers=0, epoch=1,
+      #     data_buffer_size=0, disable_iterator_cache=False,
+      # ):
+      #     (...)
+
+
+4. Training the Model
+---------------------
+
+Now we're ready to train the model. We can use the existing :ref:`fairseq-train`
+command-line tool for this, making sure to specify our new Task (``--task
+simple_classification``) and Model architecture (``--arch
+pytorch_tutorial_rnn``):
+
+.. note::
+
+  You can also configure the dimensionality of the hidden state by passing the
+  ``--hidden-dim`` argument to :ref:`fairseq-train`.
+
+.. code-block:: console
+
+  > fairseq-train names-bin \
+    --task simple_classification \
+    --arch pytorch_tutorial_rnn \
+    --optimizer adam --lr 0.001 --lr-shrink 0.5 \
+    --max-tokens 1000
+  (...)
+  | epoch 027 | loss 1.200 | ppl 2.30 | wps 15728 | ups 119.4 | wpb 116 | bsz 116 | num_updates 3726 | lr 1.5625e-05 | gnorm 1.290 | clip 0% | oom 0 | wall 32 | train_wall 21
+  | epoch 027 | valid on 'valid' subset | valid_loss 1.41304 | valid_ppl 2.66 | num_updates 3726 | best 1.41208
+  | done training in 31.6 seconds
+
+The model files should appear in the :file:`checkpoints/` directory.
+
+
+5. Writing an evaluation script
+-------------------------------
+
+Finally we can write a short script to evaluate our model on new inputs. Create
+a new file named :file:`eval_classifier.py` with the following contents::
+
+  from fairseq import checkpoint_utils, data, options, tasks
+
+  # Parse command-line arguments for generation
+  parser = options.get_generation_parser(default_task='simple_classification')
+  args = options.parse_args_and_arch(parser)
+
+  # Setup task
+  task = tasks.setup_task(args)
+
+  # Load model
+  print('| loading model from {}'.format(args.path))
+  models, _model_args = checkpoint_utils.load_model_ensemble([args.path], task=task)
+  model = models[0]
+
+  while True:
+      sentence = input('\nInput: ')
+
+      # Tokenize into characters
+      chars = ' '.join(list(sentence.strip()))
+      tokens = task.source_dictionary.encode_line(
+          chars, add_if_not_exist=False,
+      )
+
+      # Build mini-batch to feed to the model
+      batch = data.language_pair_dataset.collate(
+          samples=[{'id': -1, 'source': tokens}],  # bsz = 1
+          pad_idx=task.source_dictionary.pad(),
+          eos_idx=task.source_dictionary.eos(),
+          left_pad_source=False,
+          input_feeding=False,
+      )
+
+      # Feed batch to the model and get predictions
+      preds = model(**batch['net_input'])
+
+      # Print top 3 predictions and their log-probabilities
+      top_scores, top_labels = preds[0].topk(k=3)
+      for score, label_idx in zip(top_scores, top_labels):
+          label_name = task.target_dictionary.string([label_idx])
+          print('({:.2f})\t{}'.format(score, label_name))
+
+Now we can evaluate our model interactively. Note that we have included the
+original data path (:file:`names-bin/`) so that the dictionaries can be loaded:
+
+.. code-block:: console
+
+  > python eval_classifier.py names-bin --path checkpoints/checkpoint_best.pt
+  | [input] dictionary: 64 types
+  | [label] dictionary: 24 types
+  | loading model from checkpoints/checkpoint_best.pt
+
+  Input: Satoshi
+  (-0.61) Japanese
+  (-1.20) Arabic
+  (-2.86) Italian
+
+  Input: Sinbad
+  (-0.30) Arabic
+  (-1.76) English
+  (-4.08) Russian

fairseq/docs/tutorial_simple_lstm.rst

+Tutorial: Simple LSTM
+=====================
+
+In this tutorial we will extend fairseq by adding a new
+:class:`~fairseq.models.FairseqEncoderDecoderModel` that encodes a source
+sentence with an LSTM and then passes the final hidden state to a second LSTM
+that decodes the target sentence (without attention).
+
+This tutorial covers:
+
+1. **Writing an Encoder and Decoder** to encode/decode the source/target
+   sentence, respectively.
+2. **Registering a new Model** so that it can be used with the existing
+   :ref:`Command-line tools`.
+3. **Training the Model** using the existing command-line tools.
+4. **Making generation faster** by modifying the Decoder to use
+   :ref:`Incremental decoding`.
+
+
+1. Building an Encoder and Decoder
+----------------------------------
+
+In this section we'll define a simple LSTM Encoder and Decoder. All Encoders
+should implement the :class:`~fairseq.models.FairseqEncoder` interface and
+Decoders should implement the :class:`~fairseq.models.FairseqDecoder` interface.
+These interfaces themselves extend :class:`torch.nn.Module`, so FairseqEncoders
+and FairseqDecoders can be written and used in the same ways as ordinary PyTorch
+Modules.
+
+
+Encoder
+~~~~~~~
+
+Our Encoder will embed the tokens in the source sentence, feed them to a
+:class:`torch.nn.LSTM` and return the final hidden state. To create our encoder
+save the following in a new file named :file:`fairseq/models/simple_lstm.py`::
+
+  import torch.nn as nn
+  from fairseq import utils
+  from fairseq.models import FairseqEncoder
+
+  class SimpleLSTMEncoder(FairseqEncoder):
+
+      def __init__(
+          self, args, dictionary, embed_dim=128, hidden_dim=128, dropout=0.1,
+      ):
+          super().__init__(dictionary)
+          self.args = args
+
+          # Our encoder will embed the inputs before feeding them to the LSTM.
+          self.embed_tokens = nn.Embedding(
+              num_embeddings=len(dictionary),
+              embedding_dim=embed_dim,
+              padding_idx=dictionary.pad(),
+          )
+          self.dropout = nn.Dropout(p=dropout)
+
+          # We'll use a single-layer, unidirectional LSTM for simplicity.
+          self.lstm = nn.LSTM(
+              input_size=embed_dim,
+              hidden_size=hidden_dim,
+              num_layers=1,
+              bidirectional=False,
+              batch_first=True,
+          )
+
+      def forward(self, src_tokens, src_lengths):
+          # The inputs to the ``forward()`` function are determined by the
+          # Task, and in particular the ``'net_input'`` key in each
+          # mini-batch. We discuss Tasks in the next tutorial, but for now just
+          # know that *src_tokens* has shape `(batch, src_len)` and *src_lengths*
+          # has shape `(batch)`.
+
+          # Note that the source is typically padded on the left. This can be
+          # configured by adding the `--left-pad-source "False"` command-line
+          # argument, but here we'll make the Encoder handle either kind of
+          # padding by converting everything to be right-padded.
+          if self.args.left_pad_source:
+              # Convert left-padding to right-padding.
+              src_tokens = utils.convert_padding_direction(
+                  src_tokens,
+                  padding_idx=self.dictionary.pad(),
+                  left_to_right=True
+              )
+
+          # Embed the source.
+          x = self.embed_tokens(src_tokens)
+
+          # Apply dropout.
+          x = self.dropout(x)
+
+          # Pack the sequence into a PackedSequence object to feed to the LSTM.
+          x = nn.utils.rnn.pack_padded_sequence(x, src_lengths, batch_first=True)
+
+          # Get the output from the LSTM.
+          _outputs, (final_hidden, _final_cell) = self.lstm(x)
+
+          # Return the Encoder's output. This can be any object and will be
+          # passed directly to the Decoder.
+          return {
+              # this will have shape `(bsz, hidden_dim)`
+              'final_hidden': final_hidden.squeeze(0),
+          }
+
+      # Encoders are required to implement this method so that we can rearrange
+      # the order of the batch elements during inference (e.g., beam search).
+      def reorder_encoder_out(self, encoder_out, new_order):
+          """
+          Reorder encoder output according to `new_order`.
+
+          Args:
+              encoder_out: output from the ``forward()`` method
+              new_order (LongTensor): desired order
+
+          Returns:
+              `encoder_out` rearranged according to `new_order`
+          """
+          final_hidden = encoder_out['final_hidden']
+          return {
+              'final_hidden': final_hidden.index_select(0, new_order),
+          }
+
+
+Decoder
+~~~~~~~
+
+Our Decoder will predict the next word, conditioned on the Encoder's final
+hidden state and an embedded representation of the previous target word -- which
+is sometimes called *teacher forcing*. More specifically, we'll use a
+:class:`torch.nn.LSTM` to produce a sequence of hidden states that we'll project
+to the size of the output vocabulary to predict each target word.
+
+::
+
+  import torch
+  from fairseq.models import FairseqDecoder
+
+  class SimpleLSTMDecoder(FairseqDecoder):
+
+      def __init__(
+          self, dictionary, encoder_hidden_dim=128, embed_dim=128, hidden_dim=128,
+          dropout=0.1,
+      ):
+          super().__init__(dictionary)
+
+          # Our decoder will embed the inputs before feeding them to the LSTM.
+          self.embed_tokens = nn.Embedding(
+              num_embeddings=len(dictionary),
+              embedding_dim=embed_dim,
+              padding_idx=dictionary.pad(),
+          )
+          self.dropout = nn.Dropout(p=dropout)
+
+          # We'll use a single-layer, unidirectional LSTM for simplicity.
+          self.lstm = nn.LSTM(
+              # For the first layer we'll concatenate the Encoder's final hidden
+              # state with the embedded target tokens.
+              input_size=encoder_hidden_dim + embed_dim,
+              hidden_size=hidden_dim,
+              num_layers=1,
+              bidirectional=False,
+          )
+
+          # Define the output projection.
+          self.output_projection = nn.Linear(hidden_dim, len(dictionary))
+
+      # During training Decoders are expected to take the entire target sequence
+      # (shifted right by one position) and produce logits over the vocabulary.
+      # The *prev_output_tokens* tensor begins with the end-of-sentence symbol,
+      # ``dictionary.eos()``, followed by the target sequence.
+      def forward(self, prev_output_tokens, encoder_out):
+          """
+          Args:
+              prev_output_tokens (LongTensor): previous decoder outputs of shape
+                  `(batch, tgt_len)`, for teacher forcing
+              encoder_out (Tensor, optional): output from the encoder, used for
+                  encoder-side attention
+
+          Returns:
+              tuple:
+                  - the last decoder layer's output of shape
+                    `(batch, tgt_len, vocab)`
+                  - the last decoder layer's attention weights of shape
+                    `(batch, tgt_len, src_len)`
+          """
+          bsz, tgt_len = prev_output_tokens.size()
+
+          # Extract the final hidden state from the Encoder.
+          final_encoder_hidden = encoder_out['final_hidden']
+
+          # Embed the target sequence, which has been shifted right by one
+          # position and now starts with the end-of-sentence symbol.
+          x = self.embed_tokens(prev_output_tokens)
+
+          # Apply dropout.
+          x = self.dropout(x)
+
+          # Concatenate the Encoder's final hidden state to *every* embedded
+          # target token.
+          x = torch.cat(
+              [x, final_encoder_hidden.unsqueeze(1).expand(bsz, tgt_len, -1)],
+              dim=2,
+          )
+
+          # Using PackedSequence objects in the Decoder is harder than in the
+          # Encoder, since the targets are not sorted in descending length order,
+          # which is a requirement of ``pack_padded_sequence()``. Instead we'll
+          # feed nn.LSTM directly.
+          initial_state = (
+              final_encoder_hidden.unsqueeze(0),  # hidden
+              torch.zeros_like(final_encoder_hidden).unsqueeze(0),  # cell
+          )
+          output, _ = self.lstm(
+              x.transpose(0, 1),  # convert to shape `(tgt_len, bsz, dim)`
+              initial_state,
+          )
+          x = output.transpose(0, 1)  # convert to shape `(bsz, tgt_len, hidden)`
+
+          # Project the outputs to the size of the vocabulary.
+          x = self.output_projection(x)
+
+          # Return the logits and ``None`` for the attention weights
+          return x, None
+
+
+2. Registering the Model
+------------------------
+
+Now that we've defined our Encoder and Decoder we must *register* our model with
+fairseq using the :func:`~fairseq.models.register_model` function decorator.
+Once the model is registered we'll be able to use it with the existing
+:ref:`Command-line Tools`.
+
+All registered models must implement the
+:class:`~fairseq.models.BaseFairseqModel` interface. For sequence-to-sequence
+models (i.e., any model with a single Encoder and Decoder), we can instead
+implement the :class:`~fairseq.models.FairseqEncoderDecoderModel` interface.
+
+Create a small wrapper class in the same file and register it in fairseq with
+the name ``'simple_lstm'``::
+
+  from fairseq.models import FairseqEncoderDecoderModel, register_model
+
+  # Note: the register_model "decorator" should immediately precede the
+  # definition of the Model class.
+
+  @register_model('simple_lstm')
+  class SimpleLSTMModel(FairseqEncoderDecoderModel):
+
+      @staticmethod
+      def add_args(parser):
+          # Models can override this method to add new command-line arguments.
+          # Here we'll add some new command-line arguments to configure dropout
+          # and the dimensionality of the embeddings and hidden states.
+          parser.add_argument(
+              '--encoder-embed-dim', type=int, metavar='N',
+              help='dimensionality of the encoder embeddings',
+          )
+          parser.add_argument(
+              '--encoder-hidden-dim', type=int, metavar='N',
+              help='dimensionality of the encoder hidden state',
+          )
+          parser.add_argument(
+              '--encoder-dropout', type=float, default=0.1,
+              help='encoder dropout probability',
+          )
+          parser.add_argument(
+              '--decoder-embed-dim', type=int, metavar='N',
+              help='dimensionality of the decoder embeddings',
+          )
+          parser.add_argument(
+              '--decoder-hidden-dim', type=int, metavar='N',
+              help='dimensionality of the decoder hidden state',
+          )
+          parser.add_argument(
+              '--decoder-dropout', type=float, default=0.1,
+              help='decoder dropout probability',
+          )
+
+      @classmethod
+      def build_model(cls, args, task):
+          # Fairseq initializes models by calling the ``build_model()``
+          # function. This provides more flexibility, since the returned model
+          # instance can be of a different type than the one that was called.
+          # In this case we'll just return a SimpleLSTMModel instance.
+
+          # Initialize our Encoder and Decoder.
+          encoder = SimpleLSTMEncoder(
+              args=args,
+              dictionary=task.source_dictionary,
+              embed_dim=args.encoder_embed_dim,
+              hidden_dim=args.encoder_hidden_dim,
+              dropout=args.encoder_dropout,
+          )
+          decoder = SimpleLSTMDecoder(
+              dictionary=task.target_dictionary,
+              encoder_hidden_dim=args.encoder_hidden_dim,
+              embed_dim=args.decoder_embed_dim,
+              hidden_dim=args.decoder_hidden_dim,
+              dropout=args.decoder_dropout,
+          )
+          model = SimpleLSTMModel(encoder, decoder)
+
+          # Print the model architecture.
+          print(model)
+
+          return model
+
+      # We could override the ``forward()`` if we wanted more control over how
+      # the encoder and decoder interact, but it's not necessary for this
+      # tutorial since we can inherit the default implementation provided by
+      # the FairseqEncoderDecoderModel base class, which looks like:
+      #
+      # def forward(self, src_tokens, src_lengths, prev_output_tokens):
+      #     encoder_out = self.encoder(src_tokens, src_lengths)
+      #     decoder_out = self.decoder(prev_output_tokens, encoder_out)
+      #     return decoder_out
+
+Finally let's define a *named architecture* with the configuration for our
+model. This is done with the :func:`~fairseq.models.register_model_architecture`
+function decorator. Thereafter this named architecture can be used with the
+``--arch`` command-line argument, e.g., ``--arch tutorial_simple_lstm``::
+
+  from fairseq.models import register_model_architecture
+
+  # The first argument to ``register_model_architecture()`` should be the name
+  # of the model we registered above (i.e., 'simple_lstm'). The function we
+  # register here should take a single argument *args* and modify it in-place
+  # to match the desired architecture.
+
+  @register_model_architecture('simple_lstm', 'tutorial_simple_lstm')
+  def tutorial_simple_lstm(args):
+      # We use ``getattr()`` to prioritize arguments that are explicitly given
+      # on the command-line, so that the defaults defined below are only used
+      # when no other value has been specified.
+      args.encoder_embed_dim = getattr(args, 'encoder_embed_dim', 256)
+      args.encoder_hidden_dim = getattr(args, 'encoder_hidden_dim', 256)
+      args.decoder_embed_dim = getattr(args, 'decoder_embed_dim', 256)
+      args.decoder_hidden_dim = getattr(args, 'decoder_hidden_dim', 256)
+
+
+3. Training the Model
+---------------------
+
+Now we're ready to train the model. We can use the existing :ref:`fairseq-train`
+command-line tool for this, making sure to specify our new Model architecture
+(``--arch tutorial_simple_lstm``).
+
+.. note::
+
+  Make sure you've already preprocessed the data from the IWSLT example in the
+  :file:`examples/translation/` directory.
+
+.. code-block:: console
+
+  > fairseq-train data-bin/iwslt14.tokenized.de-en \
+    --arch tutorial_simple_lstm \
+    --encoder-dropout 0.2 --decoder-dropout 0.2 \
+    --optimizer adam --lr 0.005 --lr-shrink 0.5 \
+    --max-tokens 12000
+  (...)
+  | epoch 052 | loss 4.027 | ppl 16.30 | wps 420805 | ups 39.7 | wpb 9841 | bsz 400 | num_updates 20852 | lr 1.95313e-05 | gnorm 0.218 | clip 0% | oom 0 | wall 529 | train_wall 396
+  | epoch 052 | valid on 'valid' subset | valid_loss 4.74989 | valid_ppl 26.91 | num_updates 20852 | best 4.74954
+
+The model files should appear in the :file:`checkpoints/` directory. While this
+model architecture is not very good, we can use the :ref:`fairseq-generate` script to
+generate translations and compute our BLEU score over the test set:
+
+.. code-block:: console
+
+  > fairseq-generate data-bin/iwslt14.tokenized.de-en \
+    --path checkpoints/checkpoint_best.pt \
+    --beam 5 \
+    --remove-bpe
+  (...)
+  | Translated 6750 sentences (153132 tokens) in 17.3s (389.12 sentences/s, 8827.68 tokens/s)
+  | Generate test with beam=5: BLEU4 = 8.18, 38.8/12.1/4.7/2.0 (BP=1.000, ratio=1.066, syslen=139865, reflen=131146)
+
+
+4. Making generation faster
+---------------------------
+
+While autoregressive generation from sequence-to-sequence models is inherently
+slow, our implementation above is especially slow because it recomputes the
+entire sequence of Decoder hidden states for every output token (i.e., it is
+``O(n^2)``). We can make this significantly faster by instead caching the
+previous hidden states.
+
+In fairseq this is called :ref:`Incremental decoding`. Incremental decoding is a
+special mode at inference time where the Model only receives a single timestep
+of input corresponding to the immediately previous output token (for teacher
+forcing) and must produce the next output incrementally. Thus the model must
+cache any long-term state that is needed about the sequence, e.g., hidden
+states, convolutional states, etc.
+
+To implement incremental decoding we will modify our model to implement the
+:class:`~fairseq.models.FairseqIncrementalDecoder` interface. Compared to the
+standard :class:`~fairseq.models.FairseqDecoder` interface, the incremental
+decoder interface allows ``forward()`` methods to take an extra keyword argument
+(*incremental_state*) that can be used to cache state across time-steps.
+
+Let's replace our ``SimpleLSTMDecoder`` with an incremental one::
+
+  import torch
+  from fairseq.models import FairseqIncrementalDecoder
+
+  class SimpleLSTMDecoder(FairseqIncrementalDecoder):
+
+      def __init__(
+          self, dictionary, encoder_hidden_dim=128, embed_dim=128, hidden_dim=128,
+          dropout=0.1,
+      ):
+          # This remains the same as before.
+          super().__init__(dictionary)
+          self.embed_tokens = nn.Embedding(
+              num_embeddings=len(dictionary),
+              embedding_dim=embed_dim,
+              padding_idx=dictionary.pad(),
+          )
+          self.dropout = nn.Dropout(p=dropout)
+          self.lstm = nn.LSTM(
+              input_size=encoder_hidden_dim + embed_dim,
+              hidden_size=hidden_dim,
+              num_layers=1,
+              bidirectional=False,
+          )
+          self.output_projection = nn.Linear(hidden_dim, len(dictionary))
+
+      # We now take an additional kwarg (*incremental_state*) for caching the
+      # previous hidden and cell states.
+      def forward(self, prev_output_tokens, encoder_out, incremental_state=None):
+          if incremental_state is not None:
+              # If the *incremental_state* argument is not ``None`` then we are
+              # in incremental inference mode. While *prev_output_tokens* will
+              # still contain the entire decoded prefix, we will only use the
+              # last step and assume that the rest of the state is cached.
+              prev_output_tokens = prev_output_tokens[:, -1:]
+
+          # This remains the same as before.
+          bsz, tgt_len = prev_output_tokens.size()
+          final_encoder_hidden = encoder_out['final_hidden']
+          x = self.embed_tokens(prev_output_tokens)
+          x = self.dropout(x)
+          x = torch.cat(
+              [x, final_encoder_hidden.unsqueeze(1).expand(bsz, tgt_len, -1)],
+              dim=2,
+          )
+
+          # We will now check the cache and load the cached previous hidden and
+          # cell states, if they exist, otherwise we will initialize them to
+          # zeros (as before). We will use the ``utils.get_incremental_state()``
+          # and ``utils.set_incremental_state()`` helpers.
+          initial_state = utils.get_incremental_state(
+              self, incremental_state, 'prev_state',
+          )
+          if initial_state is None:
+              # first time initialization, same as the original version
+              initial_state = (
+                  final_encoder_hidden.unsqueeze(0),  # hidden
+                  torch.zeros_like(final_encoder_hidden).unsqueeze(0),  # cell
+              )
+
+          # Run one step of our LSTM.
+          output, latest_state = self.lstm(x.transpose(0, 1), initial_state)
+
+          # Update the cache with the latest hidden and cell states.
+          utils.set_incremental_state(
+              self, incremental_state, 'prev_state', latest_state,
+          )
+
+          # This remains the same as before
+          x = output.transpose(0, 1)
+          x = self.output_projection(x)
+          return x, None
+
+      # The ``FairseqIncrementalDecoder`` interface also requires implementing a
+      # ``reorder_incremental_state()`` method, which is used during beam search
+      # to select and reorder the incremental state.
+      def reorder_incremental_state(self, incremental_state, new_order):
+          # Load the cached state.
+          prev_state = utils.get_incremental_state(
+              self, incremental_state, 'prev_state',
+          )
+
+          # Reorder batches according to *new_order*.
+          reordered_state = (
+              prev_state[0].index_select(1, new_order),  # hidden
+              prev_state[1].index_select(1, new_order),  # cell
+          )
+
+          # Update the cached state.
+          utils.set_incremental_state(
+              self, incremental_state, 'prev_state', reordered_state,
+          )
+
+Finally, we can rerun generation and observe the speedup:
+
+.. code-block:: console
+
+  # Before
+
+  > fairseq-generate data-bin/iwslt14.tokenized.de-en \
+    --path checkpoints/checkpoint_best.pt \
+    --beam 5 \
+    --remove-bpe
+  (...)
+  | Translated 6750 sentences (153132 tokens) in 17.3s (389.12 sentences/s, 8827.68 tokens/s)
+  | Generate test with beam=5: BLEU4 = 8.18, 38.8/12.1/4.7/2.0 (BP=1.000, ratio=1.066, syslen=139865, reflen=131146)
+
+  # After
+
+  > fairseq-generate data-bin/iwslt14.tokenized.de-en \
+    --path checkpoints/checkpoint_best.pt \
+    --beam 5 \
+    --remove-bpe
+  (...)
+  | Translated 6750 sentences (153132 tokens) in 5.5s (1225.54 sentences/s, 27802.94 tokens/s)
+  | Generate test with beam=5: BLEU4 = 8.18, 38.8/12.1/4.7/2.0 (BP=1.000, ratio=1.066, syslen=139865, reflen=131146)

fairseq/examples/.gitignore

+!*/*.sh
+!*/*.md

fairseq/examples/__init__.py

+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+
+__version__ = "0.10.2"
+
+import examples.noisychannel  # noqa

fairseq/examples/backtranslation/README.md

+# Understanding Back-Translation at Scale (Edunov et al., 2018)
+
+This page includes pre-trained models from the paper [Understanding Back-Translation at Scale (Edunov et al., 2018)](https://arxiv.org/abs/1808.09381).
+
+## Pre-trained models
+
+Model | Description | Dataset | Download
+---|---|---|---
+`transformer.wmt18.en-de` | Transformer <br> ([Edunov et al., 2018](https://arxiv.org/abs/1808.09381)) <br> WMT'18 winner | [WMT'18 English-German](http://www.statmt.org/wmt18/translation-task.html) | [download (.tar.gz)](https://dl.fbaipublicfiles.com/fairseq/models/wmt18.en-de.ensemble.tar.gz) <br> See NOTE in the archive
+
+## Example usage (torch.hub)
+
+We require a few additional Python dependencies for preprocessing:
+```bash
+pip install subword_nmt sacremoses
+```
+
+Then to generate translations from the full model ensemble:
+```python
+import torch
+
+# List available models
+torch.hub.list('pytorch/fairseq')  # [..., 'transformer.wmt18.en-de', ... ]
+
+# Load the WMT'18 En-De ensemble
+en2de_ensemble = torch.hub.load(
+    'pytorch/fairseq', 'transformer.wmt18.en-de',
+    checkpoint_file='wmt18.model1.pt:wmt18.model2.pt:wmt18.model3.pt:wmt18.model4.pt:wmt18.model5.pt',
+    tokenizer='moses', bpe='subword_nmt')
+
+# The ensemble contains 5 models
+len(en2de_ensemble.models)
+# 5
+
+# Translate
+en2de_ensemble.translate('Hello world!')
+# 'Hallo Welt!'
+```
+
+## Training your own model (WMT'18 English-German)
+
+The following instructions can be adapted to reproduce the models from the paper.
+
+
+#### Step 1. Prepare parallel data and optionally train a baseline (English-German) model
+
+First download and preprocess the data:
+```bash
+# Download and prepare the data
+cd examples/backtranslation/
+bash prepare-wmt18en2de.sh
+cd ../..
+
+# Binarize the data
+TEXT=examples/backtranslation/wmt18_en_de
+fairseq-preprocess \
+    --joined-dictionary \
+    --source-lang en --target-lang de \
+    --trainpref $TEXT/train --validpref $TEXT/valid --testpref $TEXT/test \
+    --destdir data-bin/wmt18_en_de --thresholdtgt 0 --thresholdsrc 0 \
+    --workers 20
+
+# Copy the BPE code into the data-bin directory for future use
+cp examples/backtranslation/wmt18_en_de/code data-bin/wmt18_en_de/code
+```
+
+(Optionally) Train a baseline model (English-German) using just the parallel data:
+```bash
+CHECKPOINT_DIR=checkpoints_en_de_parallel
+fairseq-train --fp16 \
+    data-bin/wmt18_en_de \
+    --source-lang en --target-lang de \
+    --arch transformer_wmt_en_de_big --share-all-embeddings \
+    --dropout 0.3 --weight-decay 0.0 \
+    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
+    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
+    --lr 0.001 --lr-scheduler inverse_sqrt --warmup-updates 4000 \
+    --max-tokens 3584 --update-freq 16 \
+    --max-update 30000 \
+    --save-dir $CHECKPOINT_DIR
+# Note: the above command assumes 8 GPUs. Adjust `--update-freq` if you have a
+# different number of GPUs.
+```
+
+Average the last 10 checkpoints:
+```bash
+python scripts/average_checkpoints.py \
+    --inputs $CHECKPOINT_DIR \
+    --num-epoch-checkpoints 10 \
+    --output $CHECKPOINT_DIR/checkpoint.avg10.pt
+```
+
+Evaluate BLEU:
+```bash
+# tokenized BLEU on newstest2017:
+bash examples/backtranslation/tokenized_bleu.sh \
+    wmt17 \
+    en-de \
+    data-bin/wmt18_en_de \
+    data-bin/wmt18_en_de/code \
+    $CHECKPOINT_DIR/checkpoint.avg10.pt
+# BLEU4 = 29.57, 60.9/35.4/22.9/15.5 (BP=1.000, ratio=1.014, syslen=63049, reflen=62152)
+# compare to 29.46 in Table 1, which is also for tokenized BLEU
+
+# generally it's better to report (detokenized) sacrebleu though:
+bash examples/backtranslation/sacrebleu.sh \
+    wmt17 \
+    en-de \
+    data-bin/wmt18_en_de \
+    data-bin/wmt18_en_de/code \
+    $CHECKPOINT_DIR/checkpoint.avg10.pt
+# BLEU+case.mixed+lang.en-de+numrefs.1+smooth.exp+test.wmt17+tok.13a+version.1.4.3 = 29.0 60.6/34.7/22.4/14.9 (BP = 1.000 ratio = 1.013 hyp_len = 62099 ref_len = 61287)
+```
+
+
+#### Step 2. Back-translate monolingual German data
+
+Train a reverse model (German-English) to do the back-translation:
+```bash
+CHECKPOINT_DIR=checkpoints_de_en_parallel
+fairseq-train --fp16 \
+    data-bin/wmt18_en_de \
+    --source-lang de --target-lang en \
+    --arch transformer_wmt_en_de_big --share-all-embeddings \
+    --dropout 0.3 --weight-decay 0.0 \
+    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
+    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
+    --lr 0.001 --lr-scheduler inverse_sqrt --warmup-updates 4000 \
+    --max-tokens 3584 --update-freq 16 \
+    --max-update 30000 \
+    --save-dir $CHECKPOINT_DIR
+# Note: the above command assumes 8 GPUs. Adjust `--update-freq` if you have a
+# different number of GPUs.
+```
+
+Let's evaluate the back-translation (BT) model to make sure it is well trained:
+```bash
+bash examples/backtranslation/sacrebleu.sh \
+    wmt17 \
+    de-en \
+    data-bin/wmt18_en_de \
+    data-bin/wmt18_en_de/code \
+    $CHECKPOINT_DIR/checkpoint_best.py
+# BLEU+case.mixed+lang.de-en+numrefs.1+smooth.exp+test.wmt17+tok.13a+version.1.4.3 = 34.9 66.9/41.8/28.5/19.9 (BP = 0.983 ratio = 0.984 hyp_len = 63342 ref_len = 64399)
+# compare to the best system from WMT'17 which scored 35.1: http://matrix.statmt.org/matrix/systems_list/1868
+```
+
+Next prepare the monolingual data:
+```bash
+# Download and prepare the monolingual data
+# By default the script samples 25M monolingual sentences, which after
+# deduplication should be just over 24M sentences. These are split into 25
+# shards, each with 1M sentences (except for the last shard).
+cd examples/backtranslation/
+bash prepare-de-monolingual.sh
+cd ../..
+
+# Binarize each shard of the monolingual data
+TEXT=examples/backtranslation/wmt18_de_mono
+for SHARD in $(seq -f "%02g" 0 24); do \
+    fairseq-preprocess \
+        --only-source \
+        --source-lang de --target-lang en \
+        --joined-dictionary \
+        --srcdict data-bin/wmt18_en_de/dict.de.txt \
+        --testpref $TEXT/bpe.monolingual.dedup.${SHARD} \
+        --destdir data-bin/wmt18_de_mono/shard${SHARD} \
+        --workers 20; \
+    cp data-bin/wmt18_en_de/dict.en.txt data-bin/wmt18_de_mono/shard${SHARD}/; \
+done
+```
+
+Now we're ready to perform back-translation over the monolingual data. The
+following command generates via sampling, but it's possible to use greedy
+decoding (`--beam 1`), beam search (`--beam 5`),
+top-k sampling (`--sampling --beam 1 --sampling-topk 10`), etc.:
+```bash
+mkdir backtranslation_output
+for SHARD in $(seq -f "%02g" 0 24); do \
+    fairseq-generate --fp16 \
+        data-bin/wmt18_de_mono/shard${SHARD} \
+        --path $CHECKPOINT_DIR/checkpoint_best.pt \
+        --skip-invalid-size-inputs-valid-test \
+        --max-tokens 4096 \
+        --sampling --beam 1 \
+    > backtranslation_output/sampling.shard${SHARD}.out; \
+done
+```
+
+After BT, use the `extract_bt_data.py` script to re-combine the shards, extract
+the back-translations and apply length ratio filters:
+```bash
+python examples/backtranslation/extract_bt_data.py \
+    --minlen 1 --maxlen 250 --ratio 1.5 \
+    --output backtranslation_output/bt_data --srclang en --tgtlang de \
+    backtranslation_output/sampling.shard*.out
+
+# Ensure lengths are the same:
+# wc -l backtranslation_output/bt_data.{en,de}
+#   21795614 backtranslation_output/bt_data.en
+#   21795614 backtranslation_output/bt_data.de
+#   43591228 total
+```
+
+Binarize the filtered BT data and combine it with the parallel data:
+```bash
+TEXT=backtranslation_output
+fairseq-preprocess \
+    --source-lang en --target-lang de \
+    --joined-dictionary \
+    --srcdict data-bin/wmt18_en_de/dict.en.txt \
+    --trainpref $TEXT/bt_data \
+    --destdir data-bin/wmt18_en_de_bt \
+    --workers 20
+
+# We want to train on the combined data, so we'll symlink the parallel + BT data
+# in the wmt18_en_de_para_plus_bt directory. We link the parallel data as "train"
+# and the BT data as "train1", so that fairseq will combine them automatically
+# and so that we can use the `--upsample-primary` option to upsample the
+# parallel data (if desired).
+PARA_DATA=$(readlink -f data-bin/wmt18_en_de)
+BT_DATA=$(readlink -f data-bin/wmt18_en_de_bt)
+COMB_DATA=data-bin/wmt18_en_de_para_plus_bt
+mkdir -p $COMB_DATA
+for LANG in en de; do \
+    ln -s ${PARA_DATA}/dict.$LANG.txt ${COMB_DATA}/dict.$LANG.txt; \
+    for EXT in bin idx; do \
+        ln -s ${PARA_DATA}/train.en-de.$LANG.$EXT ${COMB_DATA}/train.en-de.$LANG.$EXT; \
+        ln -s ${BT_DATA}/train.en-de.$LANG.$EXT ${COMB_DATA}/train1.en-de.$LANG.$EXT; \
+        ln -s ${PARA_DATA}/valid.en-de.$LANG.$EXT ${COMB_DATA}/valid.en-de.$LANG.$EXT; \
+        ln -s ${PARA_DATA}/test.en-de.$LANG.$EXT ${COMB_DATA}/test.en-de.$LANG.$EXT; \
+    done; \
+done
+```
+
+
+#### 3. Train an English-German model over the combined parallel + BT data
+
+Finally we can train a model over the parallel + BT data:
+```bash
+CHECKPOINT_DIR=checkpoints_en_de_parallel_plus_bt
+fairseq-train --fp16 \
+    data-bin/wmt18_en_de_para_plus_bt \
+    --upsample-primary 16 \
+    --source-lang en --target-lang de \
+    --arch transformer_wmt_en_de_big --share-all-embeddings \
+    --dropout 0.3 --weight-decay 0.0 \
+    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
+    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
+    --lr 0.0007 --lr-scheduler inverse_sqrt --warmup-updates 4000 \
+    --max-tokens 3584 --update-freq 16 \
+    --max-update 100000 \
+    --save-dir $CHECKPOINT_DIR
+# Note: the above command assumes 8 GPUs. Adjust `--update-freq` if you have a
+# different number of GPUs.
+```
+
+Average the last 10 checkpoints:
+```bash
+python scripts/average_checkpoints.py \
+    --inputs $CHECKPOINT_DIR \
+    --num-epoch-checkpoints 10 \
+    --output $CHECKPOINT_DIR/checkpoint.avg10.pt
+```
+
+Evaluate BLEU:
+```bash
+# tokenized BLEU on newstest2017:
+bash examples/backtranslation/tokenized_bleu.sh \
+    wmt17 \
+    en-de \
+    data-bin/wmt18_en_de \
+    data-bin/wmt18_en_de/code \
+    $CHECKPOINT_DIR/checkpoint.avg10.pt
+# BLEU4 = 32.35, 64.4/38.9/26.2/18.3 (BP=0.977, ratio=0.977, syslen=60729, reflen=62152)
+# compare to 32.35 in Table 1, which is also for tokenized BLEU
+
+# generally it's better to report (detokenized) sacrebleu:
+bash examples/backtranslation/sacrebleu.sh \
+    wmt17 \
+    en-de \
+    data-bin/wmt18_en_de \
+    data-bin/wmt18_en_de/code \
+    $CHECKPOINT_DIR/checkpoint.avg10.pt
+# BLEU+case.mixed+lang.en-de+numrefs.1+smooth.exp+test.wmt17+tok.13a+version.1.4.3 = 31.5 64.3/38.2/25.6/17.6 (BP = 0.971 ratio = 0.971 hyp_len = 59515 ref_len = 61287)
+```
+
+
+## Citation
+```bibtex
+@inproceedings{edunov2018backtranslation,
+  title = {Understanding Back-Translation at Scale},
+  author = {Edunov, Sergey and Ott, Myle and Auli, Michael and Grangier, David},
+  booktitle = {Conference of the Association for Computational Linguistics (ACL)},
+  year = 2018,
+}
+```

fairseq/examples/backtranslation/deduplicate_lines.py

+#!/usr/bin/python3
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+
+import argparse
+import fileinput
+import hashlib
+import sys
+from multiprocessing import Pool
+
+
+def get_hashes_and_lines(raw_line):
+    hash = hashlib.md5(raw_line).hexdigest()
+    return hash, raw_line
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--workers", type=int, default=10)
+    parser.add_argument("files", nargs="*", help="input files")
+    args = parser.parse_args()
+
+    seen = set()
+    with fileinput.input(args.files, mode="rb") as h:
+        pool = Pool(args.workers)
+        results = pool.imap_unordered(get_hashes_and_lines, h, 1000)
+        for i, (hash, raw_line) in enumerate(results):
+            if hash not in seen:
+                seen.add(hash)
+                sys.stdout.buffer.write(raw_line)
+            if i % 1000000 == 0:
+                print(i, file=sys.stderr, end="", flush=True)
+            elif i % 100000 == 0:
+                print(".", file=sys.stderr, end="", flush=True)
+    print(file=sys.stderr, flush=True)
+
+
+if __name__ == "__main__":
+    main()

fairseq/examples/backtranslation/extract_bt_data.py

+#!/usr/bin/env python
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+
+import argparse
+import fileinput
+
+from tqdm import tqdm
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description=(
+            "Extract back-translations from the stdout of fairseq-generate. "
+            "If there are multiply hypotheses for a source, we only keep the first one. "
+        )
+    )
+    parser.add_argument("--output", required=True, help="output prefix")
+    parser.add_argument(
+        "--srclang", required=True, help="source language (extracted from H-* lines)"
+    )
+    parser.add_argument(
+        "--tgtlang", required=True, help="target language (extracted from S-* lines)"
+    )
+    parser.add_argument("--minlen", type=int, help="min length filter")
+    parser.add_argument("--maxlen", type=int, help="max length filter")
+    parser.add_argument("--ratio", type=float, help="ratio filter")
+    parser.add_argument("files", nargs="*", help="input files")
+    args = parser.parse_args()
+
+    def validate(src, tgt):
+        srclen = len(src.split(" ")) if src != "" else 0
+        tgtlen = len(tgt.split(" ")) if tgt != "" else 0
+        if (
+            (args.minlen is not None and (srclen < args.minlen or tgtlen < args.minlen))
+            or (
+                args.maxlen is not None
+                and (srclen > args.maxlen or tgtlen > args.maxlen)
+            )
+            or (
+                args.ratio is not None
+                and (max(srclen, tgtlen) / float(min(srclen, tgtlen)) > args.ratio)
+            )
+        ):
+            return False
+        return True
+
+    def safe_index(toks, index, default):
+        try:
+            return toks[index]
+        except IndexError:
+            return default
+
+    with open(args.output + "." + args.srclang, "w") as src_h, open(
+        args.output + "." + args.tgtlang, "w"
+    ) as tgt_h:
+        for line in tqdm(fileinput.input(args.files)):
+            if line.startswith("S-"):
+                tgt = safe_index(line.rstrip().split("\t"), 1, "")
+            elif line.startswith("H-"):
+                if tgt is not None:
+                    src = safe_index(line.rstrip().split("\t"), 2, "")
+                    if validate(src, tgt):
+                        print(src, file=src_h)
+                        print(tgt, file=tgt_h)
+                    tgt = None
+
+
+if __name__ == "__main__":
+    main()

fairseq/examples/backtranslation/prepare-de-monolingual.sh

+#!/bin/bash
+
+SCRIPTS=mosesdecoder/scripts
+TOKENIZER=$SCRIPTS/tokenizer/tokenizer.perl
+NORM_PUNC=$SCRIPTS/tokenizer/normalize-punctuation.perl
+REM_NON_PRINT_CHAR=$SCRIPTS/tokenizer/remove-non-printing-char.perl
+BPEROOT=subword-nmt/subword_nmt
+
+
+BPE_CODE=wmt18_en_de/code
+SUBSAMPLE_SIZE=25000000
+LANG=de
+
+
+OUTDIR=wmt18_${LANG}_mono
+orig=orig
+tmp=$OUTDIR/tmp
+mkdir -p $OUTDIR $tmp
+
+
+URLS=(
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2007.de.shuffled.gz"
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2008.de.shuffled.gz"
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2009.de.shuffled.gz"
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2010.de.shuffled.gz"
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2011.de.shuffled.gz"
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2012.de.shuffled.gz"
+    "http://www.statmt.org/wmt14/training-monolingual-news-crawl/news.2013.de.shuffled.gz"
+    "http://www.statmt.org/wmt15/training-monolingual-news-crawl-v2/news.2014.de.shuffled.v2.gz"
+    "http://data.statmt.org/wmt16/translation-task/news.2015.de.shuffled.gz"
+    "http://data.statmt.org/wmt17/translation-task/news.2016.de.shuffled.gz"
+    "http://data.statmt.org/wmt18/translation-task/news.2017.de.shuffled.deduped.gz"
+)
+FILES=(
+    "news.2007.de.shuffled.gz"
+    "news.2008.de.shuffled.gz"
+    "news.2009.de.shuffled.gz"
+    "news.2010.de.shuffled.gz"
+    "news.2011.de.shuffled.gz"
+    "news.2012.de.shuffled.gz"
+    "news.2013.de.shuffled.gz"
+    "news.2014.de.shuffled.v2.gz"
+    "news.2015.de.shuffled.gz"
+    "news.2016.de.shuffled.gz"
+    "news.2017.de.shuffled.deduped.gz"
+)
+
+
+cd $orig
+for ((i=0;i<${#URLS[@]};++i)); do
+    file=${FILES[i]}
+    if [ -f $file ]; then
+        echo "$file already exists, skipping download"
+    else
+        url=${URLS[i]}
+        wget "$url"
+    fi
+done
+cd ..
+
+
+if [ -f $tmp/monolingual.${SUBSAMPLE_SIZE}.${LANG} ]; then
+    echo "found monolingual sample, skipping shuffle/sample/tokenize"
+else
+    gzip -c -d -k $(for FILE in "${FILES[@]}"; do echo $orig/$FILE; done) \
+    | shuf -n $SUBSAMPLE_SIZE \
+    | perl $NORM_PUNC $LANG \
+    | perl $REM_NON_PRINT_CHAR \
+    | perl $TOKENIZER -threads 8 -a -l $LANG \
+    > $tmp/monolingual.${SUBSAMPLE_SIZE}.${LANG}
+fi
+
+
+if [ -f $tmp/bpe.monolingual.${SUBSAMPLE_SIZE}.${LANG} ]; then
+    echo "found BPE monolingual sample, skipping BPE step"
+else
+    python $BPEROOT/apply_bpe.py -c $BPE_CODE \
+        < $tmp/monolingual.${SUBSAMPLE_SIZE}.${LANG} \
+        > $tmp/bpe.monolingual.${SUBSAMPLE_SIZE}.${LANG}
+fi
+
+
+if [ -f $tmp/bpe.monolingual.dedup.${SUBSAMPLE_SIZE}.${LANG} ]; then
+    echo "found deduplicated monolingual sample, skipping deduplication step"
+else
+    python deduplicate_lines.py $tmp/bpe.monolingual.${SUBSAMPLE_SIZE}.${LANG} \
+    > $tmp/bpe.monolingual.dedup.${SUBSAMPLE_SIZE}.${LANG}
+fi
+
+
+if [ -f $OUTDIR/bpe.monolingual.dedup.00.de ]; then
+    echo "found sharded data, skipping sharding step"
+else
+    split --lines 1000000 --numeric-suffixes \
+        --additional-suffix .${LANG} \
+        $tmp/bpe.monolingual.dedup.${SUBSAMPLE_SIZE}.${LANG} \
+        $OUTDIR/bpe.monolingual.dedup.
+fi