streamlit computer vision(person-profiler) user interface

STREAMLIT(Part-1):BUILDING A SIMPLE STREAMLIT APPLICATION FOR COMPUTER VISION

Goal: build a simple streamlit application to detect complexion and gender of a person based on facial recognition. It will work by uploading a picture and also live detection with webcam. We will use the pretrained gender model and the trained complexion model.

LINK TO COMPUTER-VISION PART-1(Explains the complexion model training and AutoML): https://juniorboyboy2.medium.com/computer-vision-part-1-build-a-person-profiler-application-based-on-gender-and-complexion-using-738f1b631c82

LINK TO COMPUTER-VISION PART-2(explains pretrained models used for the gender model): https://juniorboyboy2.medium.com/computer-vision-part-2-build-a-person-profiler-application-based-on-gender-and-complexion-learn-c01014d8ccbe

OUTLINE:

1. What is Streamlit
2. Streamlit built-in or magic functions
3. Accessing the trained models via streamlit
4. launch streamlit app.

1.What is Streamlit

Streamlit is an open-source Python library that makes it easy to create and share beautiful, custom web apps for machine learning and data science. In just a few minutes you can build and deploy powerful data apps — so let’s get started!. To install ; run “pip install streamlit”.

2. Streamlit built-in or magic functions

Magic commands are a feature in Streamlit that allows you to write markdown and data to your app with very few keypresses.

for example

2.1 streamlit.write

2.2 streamlit.text(body)

2.3 st.markdown(‘Streamlit is **_really_ cool**.’)

2.4 streamlit.caption(‘This is a string that explains something above’)

2.5 st.title(‘This is a title’)

2.6 streamlit.subheader(“This is a title”)

2.7 st.table(df)

and many more. visit https://docs.streamlit.io/en/stable/api.html for more

3. Accessing the trained models via streamlit

import libraries

load trained models

streamlit User interface

To view complete and explanatory code: https://github.com/juniorboycoder/Person_profiler_source_code/blob/main/app.py

4. launch streamlit app.

Run streamlit app

Output

CONCLUSION

We built a simple streamlit application to detect complexion and gender of a person both by webcam and picture upload.

WRITER: OLUYEDE SEGUN . A(jr)

Resources used (References) and further reading:

API reference - Streamlit 0.86.0 documentation

Link to my github code:

Person_profiler_source_code/app.py at main · juniorboycoder/Person_profiler_source_code

linkedin profile: https://www.linkedin.com/in/oluyede-segun-adedeji-jr-a5550b167/

twitter profile: https://twitter.com/oluyedejun1

TAGS: #COMPUTERVISION #OPENCV #PYTHON #STREAMLIT #DEEPLEARNING