keep doing, keep chilling
Daily log is to track the progress made by me on 100Days of ML coding challenge. At the 100th day to see myself what is difference between Day-1 and Day-100 and also differnce are betterment from previous days.
100 Days ML challenge and to learns ML end to end from zero to mastery levels. This challenge focus more on the production environment rather than the concepts and theory behind ML/DL models. I will be applying ML pipeline and the process of taking an ML model and applying into a real-world application.
- Learn how to deploy ML models into production.
- Learn about the ML Pipeline.
- Learn more about privacy & protection for ML applications.
- Learn the CI/CD for ML.
- Learn about CUDA and get hands on Experience.
- Learn more about Reinforcement Learning.
- Learn more about Generative Learning.
- Learn about AWS microservies.
- Develop a web application using Flask
- Code a Linear Regression Model
- Deploy the trained model as Rest Service
- Read the section about Streamlit-Deployment.
- Create a simple UI Using Streamlit
- Deploy the trained Model as REST service
- Build or Code LSTM model
- Train the LSTM Model
- Create UI using Streamlit
- Debugs the model
- Deploy the trained model as a REST service
- Read Chapter-4: ML Deployment using Docker
- Create a docker-file for Flask App
- Create Docker image
- Push our Docker image to DockerHub
- Read chapter 5: ML Deployment using Kubernetes
- Create GCP Project
- Enable and Utilize the Kubernetes Engine API or GCP
- Read topics under scripting from Websites [MadeWithML](https://madewithml.com/courses/mlops/packaging/)
- Apply learning by adding it to current projects