ML-Model-CI

(★ 198)

MLModelCI is a complete MLOps platform for managing, converting, profiling, and deploying MLaaS (Machine Learning-as-a-Service), bridging the gap between current ML training and serving systems.

File Explorer

Download Latest Version (.zip)

- - run_test.yml
- ISSUE_TEMPLATE.md
- PULL_REQUEST_TEMPLATE.md
- .keep
- cpu.Dockerfile
- cuda10.2.Dockerfile
- docker-compose-cpu-modelhub.yml
- docker-compose-cuda10.2-modelhub.yml
- Dockerfile
- frontend.Dockerfile
- - iconv1.svg
  - model-service-block-diagram.png
  - modelci.png
- - convert.md
  - housekeeper.md
  - profile.md
  - register.md
  - retrieve-and-deploy.md
- - image_classification_model_deployment.ipynb
  - object_detection_model_deployment.ipynb
  - profile_example.ipynb
- resnet50.yml
- resnet50_explicit_path.yml
- resnet50_torchscript.yml
- retinanet.yml
- sample_k8s_deployment.conf
- sample_mrcnn.py
- - favicon.png
  - index.html
- - main.png
  - nonav.png
  - nonav_wide.png
  - visualizer.png
  - wide.png
- - app.ts
  - config.ts
  - global.scss
  - routes.ts
- .editorconfig
- .eslintignore
- .eslintrc.js
- .gitignore
- .prettierignore
- .prettierrc.js
- .stylelintignore
- .stylelintrc.js
- build.json
- package-lock.json
- package.json
- README.md
- tsconfig.json
- .keep
- - __init__.py
  - handler.py
  - main.py
  - readme.md
- - __init__.py
  - _fixup.py
  - modelhub.py
  - modelps.py
  - service.py
- - __init__.py
  - controller.py
  - executor.py
  - readme.md
- - __init__.py
  - readme.md
- - __init__.py
  - mongo_client.py
- - __init__.py
  - init_data.py
  - manager.py
  - model_loader.py
  - profile_.py
  - profiler.py
  - README.md
  - registrar.py
  - utils.py
- - __init__.py
  - README.md
- - __init__.py
  - gpu_node_exporter.py
  - readme.md
- - __init__.py
  - exceptions.py
  - model_dao.py
  - mongo_db.py
  - README.md
  - service.py
  - service_.py
- - __init__.py
  - trtis_objects.py
  - type_conversion.py
- - __init__.py
  - docker_api_utils.py
  - docker_container_manager.py
  - exceptions.py
  - logger.py
  - misc.py
- __init__.py
- config.py
- env-backend.env
- env-frontend.env
- env-mongodb.env
- init-mongo.sh
- ui.py
- README.md
- start_node_exporter.sh
- stop_node_exporter.sh
- generate_env.py
- init_db.js
- install.conda_env.sh
- install.sh
- install.trtis_client.sh
- install.verify.sh
- uninstall.sh
- pytest.ini
- README.md
- test_keras_conversion.py
- test_lightgbm_conversion.py
- test_model_api.py
- test_model_service.py
- test_modelhub_cli.py
- test_onnx_conversion.py
- test_pytorch_conversion.py
- test_sklearn_conversion.py
- test_xgboost_conversion.py
.codacy.yml
.dockerignore
.flake8
.fossa.yml
.gitattributes
.gitignore
.travis.yml
benchmark.md
CHANGELOG.md
CONTRIBUTING.md
environment.yml
LICENSE
pure_requires.yml
pyproject.toml
README.md
README_zh_CN.md
requirements.txt
setup.cfg
setup.py

# Installation Guide

1. Get the code

git clone https://github.com/cap-ntu/ML-Model-CI

Downloads the entire project code from GitHub to your computer.

cd ML-Model-CI

Moves into the project folder you just downloaded.

2. Docker

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Docker Desktop Needed to build and run containers. Install it and keep it running in the background.

Once you have installed, make sure the docker daemon is running, then you can start MLModelCI service on a leader server by:

Type this command into your terminal and run it.

![](https://img.shields.io/docker/pulls/mlmodelci/mlmodelci.svg)

Type this command into your terminal and run it.

![](https://img.shields.io/docker/v/mlmodelci/mlmodelci/cpu)![](https://img.shields.io/docker/image-size/mlmodelci/mlmodelci/cpu)

Type this command into your terminal and run it.

Start basic services by Docker Compose:

Runs the command against the services defined in the compose file.

![](https://img.shields.io/docker/v/mlmodelci/mlmodelci/cuda10.2-cudnn8)![](https://img.shields.io/docker/image-size/mlmodelci/mlmodelci/cuda10.2-cudnn8)

Type this command into your terminal and run it.

✅ Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.

Pulled directly from this repo's README.

3. Node.js

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Node.js Node.js must be installed to use npm. The LTS version is recommended.

cd frontend

This project's files live in a subfolder, so move into it first.

npm install

Downloads and installs the libraries listed in package.json.

npm start

Starts the development/run server.

✅ After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.

4. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

If you have installed MLModelCI via pip, you should start the frontend service manually.

Type this command into your terminal and run it.

- [Publish an image classification model](./example/notebook/image_classification_model_deployment.ipynb)  [![nbviewer](https://raw.githubusercontent.com/jupyter/design/master/logos/Badges/nbviewer_badge.svg)](https://nbviewer.jupyter.org/github/cap-ntu/ML-Model-CI/blob/master/example/notebook/image_classification_model_deployment.ipynb)

Type this command into your terminal and run it.

- [Publish an object detection model](./example/notebook/object_detection_model_deployment.ipynb)  [![nbviewer](https://raw.githubusercontent.com/jupyter/design/master/logos/Badges/nbviewer_badge.svg)](https://nbviewer.jupyter.org/github/cap-ntu/ML-Model-CI/blob/master/example/notebook/object_detection_model_deployment.ipynb)

Type this command into your terminal and run it.

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.

ML-Model-CI

File Explorer

# Installation Guide

2. Docker

3. Node.js

4. Python

Today's picks

Was this content helpful?

Recent Feedback

ML-Model-CI

File Explorer

# Installation Guide

2. Docker

3. Node.js

4. Python

Today's picks

Was this content helpful?

Recent Feedback

Download README