Thread by @thedataprof

Hi friends, here’s my new hand-drawn cartoon illustration ✏️
Quickly deploy #machinelearning models
👀🧵👇 See thread below

2/ Deployment of machine learning models is often overlooked especially in academia
- We spend countless hours compiling the dataset, processing the data, fine tuning the model and perhaps interpreting and making sense of the model
- Many times we stop at that
- Why not deploy?

3/ Perhaps model deployment is difficult?
- Django? Flask? API?
- We now have access to powerful libraries:
1. Dash (@plotlygraphs) plotly.com/dash/
2. @Gradio gradio.app
3. @streamlit streamlit.io
4. Shiny (@rstudio) shiny.rstudio.com

3/ I've written a step-by-step tutorial (published in @TDataScience) on How to Create and Deploy a Machine Learning App to Heroku
towardsdatascience.com/how-to-create-…

5/ I've provided a high-level overview on deploying machine learning models in this YouTube video

6/ I've also created playlist of videos on creating @streamlit web apps here

7/ Here's 2 videos on deploying @streamlit apps:
1. Deploy to Heroku
2. Deploy to Streamlit Sharing

8/ Made a video on building @Gradio web apps for machine learning and deep learning models

9/ Forgot to mention that the illustration in this thread focuses on low-code solutions for deploying machine learning models, which helps the data scientists to quickly implement a front-end to ML models without extensive knowledge of APIs or Django/Flask