Blood Face Detector in Python(Part 2) — Building a Web Application using Streamlit in Python.

In my previous post, I talked about how to train your Blood Face Classifier model using Transfer Learning by fine-tuning the Mobilenet V2 architecture and then Evaluating the results on unseen images and in the real-time video feed.

In today’s article, I am going to show you how to build a simple web application using Streamlit in Python.

Note: It is highly recommended for you to read and understand the part-1 of this blog post to understand what is happening in part-2.

For those of you who don’t know what is streamlit, it is an open-source library for Python users and is used to build beautiful and custom web-applications for your machine learning and data science projects.

Today, I am going to show you how to use streamlit with OpenCV to upload an image in a web browser and make predictions or run your camera to make predictions from your browser.

Take a look below to understand what we are going to build today:

Note: You can download the source code for the project on my Github page. You can find the code for today's article in the app.py file.

Now, coming back to the topic:

Step-1: Installing Streamlit using Pypi

Open your terminal and write:

pip install streamlit

Step-2: Importing the required libraries