pytorch-seq2seq
This is a framework for sequence-to-sequence (seq2seq) models implemented in PyTorch. The framework has modularized and extensible components for seq2seq models, training and inference, checkpoints, etc. This is an alpha release. We appreciate any kind of feedback or contribution.
What's New in 0.1.6
- Compatible with PyTorch 0.4
- Added support for pre-trained word embedding
Roadmap
Seq2seq is a fast evolving field with new techniques and architectures being published frequently. The goal of this library is facilitating the development of such techniques and applications. While constantly improving the quality of code and documentation, we will focus on the following items:
- Evaluation with benchmarks such as WMT machine translation, COCO image captioning, conversational models, etc;
- Provide more flexible model options, improving the usability of the library;
- Adding latest architectures such as the CNN based model proposed by Convolutional Sequence to Sequence Learning and the transformer model proposed by Attention Is All You Need;
- Support features in the new versions of PyTorch.
Installation
This package requires Python 2.7 or 3.6. We recommend creating a new virtual environment for this project (using virtualenv or conda).
Prerequisites
- Numpy:
pip install numpy(Refer here for problem installing Numpy). - PyTorch: Refer to PyTorch website to install the version w.r.t. your environment.
Install from source
Currently we only support installation from source code using setuptools. Checkout the source code and run the following commands:
pip install -r requirements.txt
python setup.py install
If you already had a version of PyTorch installed on your system, please verify that the active torch package is at least version 0.1.11.
Get Started
Prepare toy dataset
# Run script to generate the reverse toy dataset
# The generated data is stored in data/toy_reverse by default
scripts/toy.sh
Train and play
TRAIN_PATH=data/toy_reverse/train/data.txt
DEV_PATH=data/toy_reverse/dev/data.txt
# Start training
python examples/sample.py --train_path $TRAIN_PATH --dev_path $DEV_PATH
It will take about 3 minutes to train on CPU and less than 1 minute with a Tesla K80. Once training is complete, you will be prompted to enter a new sequence to translate and the model will print out its prediction (use ctrl-C to terminate). Try the example below!
Input: 1 3 5 7 9
Expected output: 9 7 5 3 1 EOS
Checkpoints
Checkpoints are organized by experiments and timestamps as shown in the following file structure
experiment_dir
+-- input_vocab
+-- output_vocab
+-- checkpoints
| +-- YYYY_mm_dd_HH_MM_SS
| +-- decoder
| +-- encoder
| +-- model_checkpoint
The sample script by default saves checkpoints in the experiment folder of the root directory. Look at the usages of the sample code for more options, including resuming and loading from checkpoints.
Benchmarks
- WMT Machine Translation (Coming soon)
Troubleshoots and Contributing
If you have any questions, bug reports, and feature requests, please open an issue on Github. For live discussions, please go to our Gitter lobby.
We appreciate any kind of feedback or contribution. Feel free to proceed with small issues like bug fixes, documentation improvement. For major contributions and new features, please discuss with the collaborators in corresponding issues.
Development Cycle
We are using 4-week release cycles, where during each cycle changes will be pushed to the develop branch and finally merge to the master branch at the end of each cycle.
Development Environment
We setup the development environment using Vagrant. Run vagrant up with our 'Vagrantfile' to get started.
The following tools are needed and installed in the development environment by default:
- Git
- Python
- Python packages: nose, mock, coverage, flake8
Test
The quality and the maintainability of the project is ensured by comprehensive tests. We encourage writing unit tests and integration tests when contributing new codes.
Locally please run nosetests in the package root directory to run unit tests. We use TravisCI to require that a pull request has to pass all unit tests to be eligible to merge. See travis configuration for more information.
Code Style
We follow PEP8 for code style. Especially the style of docstrings is important to generate documentation.
- Local: Run the following commands in the package root directory
# Python syntax errors or undefined names
flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics
# Style checks
flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
- Github: We use Codacy to check styles on pull requests and branches.
5.1k Jan 09, 2023
2.3k Jan 08, 2023
209 Dec 30, 2022
117 Jan 07, 2023
39 Nov 15, 2022
873 Dec 15, 2022
1k Jan 08, 2023
273 Dec 17, 2022
150 Dec 23, 2022
1.9k Jan 06, 2023
8 Nov 30, 2022
77.3k Jan 03, 2023
1.6k Dec 29, 2022
6 Dec 17, 2022
45 Sep 06, 2022
1.8k Dec 31, 2022
9 Jan 11, 2022
1.5k Nov 14, 2022
12.3k Jan 02, 2023