For review

.deepsource.toml

@@ -0,0 +1,7 @@
+  version = 1
+
+  [[analyzers]]
+  name = "python"
+  enabled = true
+  max_line_length = 120
+  runtime_version = "3.x.x"

.github/workflows/greetings.yml

@@ -0,0 +1,13 @@
+name: Greetings
+
+on: [pull_request, issues]
+
+jobs:
+  greeting:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/first-interaction@v1
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        issue-message: 'Message that will be displayed on users'' first issue'
+        pr-message: 'Message that will be displayed on users'' first pr'

.gitignore

@@ -0,0 +1,220 @@
+
+# Created by https://www.gitignore.io/api/vim,macos,python,windows,virtualenv
+# Edit at https://www.gitignore.io/?templates=vim,macos,python,windows,virtualenv
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+*~
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+### VirtualEnv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.gitignore.io/api/vim,macos,python,windows,virtualenv
+
+datasets/
+.idea/

README.md

@@ -1,2 +1,110 @@
-# transformer-tensorflow2.0
-transformer in tensorflow 2.0
+# Transformer-tensorflow2.0
+
+[attention is all you need](https://arxiv.org/pdf/1706.03762.pdf) (transformer) in tensorflow 2.0
+
+[paper review(pdf)](https://github.com/strutive07/transformer-tensorflow2.0/blob/master/Attention%20is%20all%20you%20need.pdf)
+
+[colab guide](https://colab.research.google.com/github/strutive07/transformer-tensorflow2.0/blob/master/transformer_implement_tf2_0.ipynb)
+
+[Download pre-trained model(checkpoint)](https://drive.google.com/file/d/1jsY7WMI9EU5ifhcxV_sMpK8znPA1mvkf/view?usp=sharing)
+
+[Download pre-trained bpe data](https://drive.google.com/drive/folders/1YUABrVUz3oGKgGfMJNWQl0WCP_nVjhiS?usp=sharing)
+
+[![DeepSource](https://static.deepsource.io/deepsource-badge-light-mini.svg)](https://deepsource.io/gh/strutive07/transformer-tensorflow2.0/?ref=repository-badge)
+
+## How to train
+
+1. Install enviornments
+
+    bash ubuntu16_04_cuda10_cudnn7_tensorflow2.0_install.sh
+
+2. Training
+
+- Single GPU training
+    1. Change hyper parameter in train.py
+    2. Run training script
+
+    ```bash
+    python train.py
+    ```
+
+
+
+- Multi GPU training
+    1. Change hyper parameter in distributed_train.py
+    2. Run training script
+
+    ```bash
+    python distributed_train.py
+    ```
+
+3. Test
+- if you did not train bpe, train bpe model or download pre-trained bpe model. LINK: [Download pre-trained bpe data](https://drive.google.com/drive/folders/1YUABrVUz3oGKgGfMJNWQl0WCP_nVjhiS?usp=sharing). You should save it in *top dataset directory*.
+example: ./dataset/train.en.segmented.vocab and so on.
+
+
+## How to add dataset
+
+Add data config to `data_loader.py`
+
+```python
+CONFIG = {
+        'wmt14/en-de': {
+            'source_lang': 'en',
+            'target_lang': 'de',
+            'base_url': 'https://nlp.stanford.edu/projects/nmt/data/wmt14.en-de/',
+            'train_files': ['train.en', 'train.de'],
+            'vocab_files': ['vocab.50K.en', 'vocab.50K.de'],
+            'dictionary_files': ['dict.en-de'],
+            'test_files': [
+                'newstest2012.en', 'newstest2012.de',
+                'newstest2013.en', 'newstest2013.de',
+                'newstest2014.en', 'newstest2014.de',
+                'newstest2015.en', 'newstest2015.de',
+            ]
+        }
+    }
+```
+
+If you want to add custom dataset, add data config like below and add `custom_dataset` parameter to DataLoader.load
+
+```python
+CONFIG = {
+        'wmt14/en-de': {
+            'source_lang': 'en',
+            'target_lang': 'de',
+            'train_files': ['train.en', 'train.de'],
+            'vocab_files': ['vocab.50K.en', 'vocab.50K.de'],
+            'dictionary_files': ['dict.en-de'],
+            'test_files': [
+                'newstest2012.en', 'newstest2012.de',
+                'newstest2013.en', 'newstest2013.de',
+                'newstest2014.en', 'newstest2014.de',
+                'newstest2015.en', 'newstest2015.de',
+            ]
+        }
+    }
+
+data_loader = DataLoader(
+    dataset_name='wmt14/en-de',
+    data_dir='./datasets',
+    batch_size=GLOBAL_BATCH_SIZE,
+    bpe_vocab_size=BPE_VOCAB_SIZE,
+    seq_max_len_source=SEQ_MAX_LEN_SOURCE,
+    seq_max_len_target=SEQ_MAX_LEN_TARGET,
+    data_limit=DATA_LIMIT,
+    train_ratio=TRAIN_RATIO
+)
+
+dataset, val_dataset = data_loader.load(custom_dataset=True)
+```
+
+
+
+## BLEU Score
+
+| Test Dataset | BLEU Score |
+| ------------ | ---------- |
+| newstest2013 | 23.3       |
+| newstest2014 | 22.85      |
+| newstest2015 | 25.33      |