[Bug Fix] trainer.update(1) should be used after loss.mean() is called

.coveragerc

@@ -2,8 +2,7 @@
 [run]
 omit =
     tests/*
-    conda/*
-    scripts/tests/*
+    scripts/*
 concurrency =
     multiprocessing
     thread

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 100
+max-complexity = 18
+exclude = tests,__init__.py

.github/workflows/unittests-gpu.yml

@@ -0,0 +1,60 @@
+name: continuous build - gpu
+
+on: [push, pull_request_target]
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  unittest-gpu:
+    runs-on: ubuntu-latest
+    strategy: 
+      fail-fast: false
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Install Linux dependencies
+        run: sudo apt-get install libopenblas-dev
+
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+          architecture: x64
+
+      - name: Install Other Dependencies
+        run: |
+          python -m pip install --user --quiet --upgrade pip
+          python -m pip install --user --quiet -e .[extras]
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v1
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: us-east-1
+
+      - name: Extract branch name
+        shell: bash
+        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
+        id: extract_branch
+
+      - name: Test project on AWS Batch(For push)
+        if: startsWith(steps.extract_branch.outputs.branch, 'PR-') != true
+        run: |
+          python ./tools/batch/submit-job.py --region us-east-1 --job-type g4dn.4x --source-ref ${{ github.ref }} --work-dir tools/batch --remote https://github.com/dmlc/gluon-nlp --command "/batch_states/test.sh" --wait | tee > script.log
+
+      - name: Test project on AWS Batch(For pull request)
+        if: startsWith(steps.extract_branch.outputs.branch, 'PR-') == true
+        run: |
+          python ./tools/batch/submit-job.py --region us-east-1 --job-type g4dn.4x --source-ref ${{ github.event.pull_request.head.ref }} --work-dir tools/batch --remote https://github.com/${{ github.event.pull_request.head.repo.full_name }} --command "/batch_states/test.sh" --wait | tee > script.log
+
+      - name: Upload log file for AWS Batch test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: GPU_Test_Results
+          path: script.log
+
+

.github/workflows/unittests.yml

@@ -0,0 +1,47 @@
+name: continuous build
+
+on: [push, pull_request]
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  unittest:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        # TODO Add windows test by using "windows-latest"
+        os: [macos-latest, ubuntu-latest]
+        python-version: [ '3.6', '3.7', '3.8']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      # Install OS specific dependencies
+      - name: Install Linux dependencies
+        if: matrix.os == 'ubuntu-latest'
+        # TODO https://github.com/apache/incubator-mxnet/issues/18293
+        run: sudo apt-get install libopenblas-dev
+
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+      - name: Install Other Dependencies
+        run: |
+          python -m pip install --user --upgrade pip
+          python -m pip install --user setuptools pytest pytest-cov contextvars
+          python -m pip install --upgrade cython
+          python -m pip install --pre --user "mxnet>=2.0.0b20200802" -f https://dist.mxnet.io/python
+          python -m pip install --user -e .[extras]
+      - name: Test project
+        run: |
+          python -m pytest --cov=./ --cov-report=xml --device="cpu" --durations=50 tests/
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1.0.10
+        with:
+          env_vars: OS,PYTHON    
+

.pytype.cfg

@@ -5,4 +5,4 @@ inputs =
     src/gluonnlp
 
 # Python version (major.minor) of the target code.
-python_version = 3.5
+python_version = 3.6

CODEOWNERS

@@ -1,9 +1,9 @@
-# Watchers and contributors to Apache MXNet repo directories/packages/files
+# Watchers and contributors to DMLC GluonNLP repo directories/packages/files
 # Please see documentation of use of CODEOWNERS file at
 # https://help.github.com/articles/about-codeowners/ and
 # https://github.com/blog/2392-introducing-code-owners
 #
-# Anybody can add themselves or a team as additional watcher or contributor 
+# Anybody can add themselves or a team as additional watcher or contributor
 # to get notified about changes in a specific package.
 # See https://help.github.com/articles/about-teams how to setup teams.
 

README.md

@@ -0,0 +1,111 @@
+<h3 align="center">
+GluonNLP: Your Choice of Deep Learning for NLP
+</h3>
+
+<p align="center">
+    <a href="https://github.com/dmlc/gluon-nlp/actions"><img src="https://github.com/dmlc/gluon-nlp/workflows/continuous%20build/badge.svg"></a>
+    <a href="https://codecov.io/gh/dmlc/gluon-nlp"><img src="https://codecov.io/gh/dmlc/gluon-nlp/branch/master/graph/badge.svg"></a>
+    <a href="https://github.com/dmlc/gluonnlp/actions"><img src="https://img.shields.io/badge/python-3.6%2C3.8-blue.svg"></a>
+    <a href="https://pypi.org/project/gluonnlp/#history"><img src="https://img.shields.io/pypi/v/gluonnlp.svg"></a>
+</p>
+
+GluonNLP is a toolkit that enables easy text preprocessing, datasets
+loading and neural models building to help you speed up your Natural
+Language Processing (NLP) research.
+
+# Features
+
+For NLP Practitioners
+- Easy-to-use Data Pipeline
+- Automatically Train Models via AutoNLP (TODO)
+
+For Researchers
+- Pretrained Model Zoo
+- Programming with numpy-like API
+
+For Engineers
+- Fast Deployment
+    - [TVM](https://tvm.apache.org/) (TODO)
+- AWS Integration
+
+
+# Installation
+First of all, install the latest MXNet. You may use the following commands:
+
+```bash
+# Install the version with CUDA 10.0
+python3 -m pip install -U --pre "mxnet-cu100>=2.0.0b20200802" -f https://dist.mxnet.io/python
+
+# Install the version with CUDA 10.1
+python3 -m pip install -U --pre "mxnet-cu101>=2.0.0b20200802" -f https://dist.mxnet.io/python
+
+# Install the version with CUDA 10.2
+python3 -m pip install -U --pre "mxnet-cu102>=2.0.0b20200802" -f https://dist.mxnet.io/python
+
+# Install the cpu-only version
+python3 -m pip install -U --pre "mxnet>=2.0.0b20200802" -f https://dist.mxnet.io/python
+```
+
+
+To install GluonNLP, use
+
+```bash
+python3 -m pip install -U -e .
+
+# Also, you may install all the extra requirements via
+python3 -m pip install -U -e ."[extras]"
+```
+
+If you find that you do not have the permission, you can also install to the user folder:
+
+```bash
+python3 -m pip install -U -e . --user
+```
+
+For Windows users, we recommend to use the [Windows Subsystem for Linux](https://docs.microsoft.com/en-us/windows/wsl/about).
+
+
+# Access the Command-line Toolkits
+
+To facilitate the researcher and the engineers, we provide command-line-toolkits for
+downloading and preprocessing the NLP datasets. For more details, you may refer to
+ [GluonNLP Datasets](./scripts/datasets) and [GluonNLP Preprocessing Tools](./scripts/preprocess).
+
+```bash
+# CLI for downloading / preparing the dataset
+nlp_data help
+
+# CLI for accessing some common data preprocessing scripts
+nlp_preprocess help
+
+# Also, you can use `python -m` to access the toolkits
+python3 -m gluonnlp.cli.data help
+python3 -m gluonnlp.cli.preprocess help
+
+```
+
+### Frequently Asked Questions
+- **Question**: I cannot you access the command line toolkits. By running `nlp_data`, it reports `nlp_data: command not found`.
+
+  This is sometimes because that you have installed glunonnlp to the user folder and 
+  the executables are installed to `~/.local/bin`. You can try to change the `PATH` variable to 
+  also include '~/.local/bin'.
+
+  ```
+  export PATH=${PATH}:~/.local/bin
+  ```
+
+
+# Run Unittests
+You may go to [tests](tests) to see all how to run the unittests.
+
+
+# Use Docker
+You can use Docker to launch a JupyterLab development environment with GluonNLP installed.
+
+```
+docker pull gluonai/gluon-nlp:gpu-latest
+docker run --gpus all --rm -it -p 8888:8888 -p 8787:8787 -p 8786:8786 --shm-size=4g gluonai/gluon-nlp:gpu-latest
+``` 
+
+For more details, you can refer to the guidance in [tools/docker](tools/docker).