Continuous Machine Learning (CML) is CI/CD for Machine Learning Projects

name: CML
on: [push]
jobs:
  train-and-report:
    runs-on: ubuntu-latest
    container: docker://ghcr.io/iterative/cml:0-dvc2-base1
    steps:
      - uses: actions/checkout@v3
      - run: |
          pip install -r requirements.txt
          python train.py  # generate plot.png
 
          # Create CML report
          cat metrics.txt >> report.md
          echo '![](./plot.png "Confusion Matrix")' >> report.md
          cml comment create report.md
        env:
          REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}

name: CML & DVC
on: [push]
jobs:
  train-and-report:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: actions/setup-python@v4
        with:
          python-version: '3.x'
      - uses: iterative/setup-cml@v1
      - uses: iterative/setup-dvc@v1
      - name: Train model
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
        run: |
          dvc pull data
          pip install -r requirements.txt
          dvc repro
      - name: Create CML report
        run: |
          # Compare metrics to main
          git fetch --depth=1 origin main:main 
          dvc metrics diff --show-md main >> report.md
          # Plot training loss function diff
          dvc plots diff \
            --target loss.csv --show-vega main > vega.json
          vl2png vega.json > plot.png
          echo '![](./plot.png "Training Loss")' >> report.md
          cml comment create report.md
        env:
          REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}

name: CML & TensorBoard
on: [push]
jobs:
  train-and-report:
    runs-on: ubuntu-latest
    container: docker://ghcr.io/iterative/cml:0-dvc2-base1
    steps:
      - uses: actions/checkout@v3
      - name: Train and Report
        env:
          REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          TB_CREDENTIALS: ${{ secrets.TB_CREDENTIALS }}
        run: |
          pip install -r requirements.txt
          cml tensorboard connect \
            --logdir=./logs \
            --name="Go to tensorboard" \
            --md >> report.md
          cml comment create report.md
          python train.py  # generate ./logs

name: CML
on: [push]
jobs:
  launch-runner:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: iterative/setup-cml@v1
      - name: Deploy runner on AWS EC2
        # Supports AWS, Azure, GCP, K8s
        env:
          REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
        run: |
          cml runner launch \
          --cloud=aws \
          --cloud-region=us-west \
          --cloud-type=m5.2xlarge \
          --labels=cml-runner
  train-and-report:
    runs-on: [self-hosted, cml-runner]
    needs: launch-runner
    timeout-minutes: 50400 # 35 days
    container: docker://iterativeai/cml:0-dvc2-base1
    steps:
      - uses: actions/checkout@v3
      - name: Train and Report
        run: |
          pip install -r requirements.txt
          python train.py  # generate plot.png
          echo "## Report from your EC2 Instance" >> report.md
          cat metrics.txt >> report.md
          echo '![](./plot.png "Confusion Matrix")' >> report.md
          cml comment create report.md
        env:
          REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}

name: CML
on: [push]
jobs:
  launch-runner:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: iterative/setup-cml@v1
      - name: Deploy runner on AWS EC2
        # Supports AWS, Azure, GCP, K8s
        env:
          REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
        run: |
          cml runner launch \
          --cloud=aws \
          --cloud-region=us-west \
          --cloud-type=p2.xlarge \
          --cloud-hdd-size=64 \
          --labels=cml-gpu
  train-and-report:
    runs-on: [self-hosted, cml-gpu]
    needs: launch-runner
    timeout-minutes: 50400 # 35 days
    container:
      image: docker://iterativeai/cml:0-dvc2-base1-gpu
      options: --gpus all
    steps:
      - uses: actions/checkout@v3
      - name: Train model
        run: |
          dvc pull data
          pip install -r requirements.txt
          dvc repro
      - name: Create CML report
        run: |
          git show origin/main:image.png > image-main.png
          cat <<EOF > report.md
          # Style transfer
          ## Workspace vs. Main
          ![](./image.png "Workspace") ![](./image-main.png "Main")
          ## Training metrics
          $(dvc params diff main --show-md)
          ## GPU info
          $(cat gpu_info.txt)
          EOF
          cml comment create report.md
        env:
          REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}