Photos created using a Python implementation of
A Neural Algorithm of Artistic Style
Gatys et al.

After working for over 25 years as a successful full stack web developer, I am delving deeply into Machine Learning/Deep Learning to combine my web development experience with my educational background in statistics and data analysis. My LinkedIn profile contains a complete list of both job experience and education specifics.

I like to consider myself a Renaissance man and my hobbies reflect that. I am a luthier, a maker of stringed instruments, a juggler, specializing in the diabolo and I was a member of a renaissance group, The Spanish Sword Touring Group, where I acted, participated in theatrical sword fighting demonstrations, played the recorder and sang. Other interests include Embedded Devices (Raspberry Pi, Jetson Nano, Arduino, and Coral Dev Board) and 3D printing.


Data Science



This is a clone of Classic-Piano-Composer, https://github.com/Skuldur/Classical-Piano-Composer and instead of piano music, I used bluegrass mandolin songs from Mandolin Cafe TablEdit Library (converted to midi), https://www.mandolincafe.com/cgi-bin/tabledit/search?name=Bluegrass for training.


  • Converted TablEdit files of bluegrass songs into midi files.
  • Trained model on a Linux computer running Ubuntu 18.04 with 32GB RAM and a GeForce GTX 1070 Ti graphics card. Took approximately 10 hours to train the model.
  • The model generates 2 minutes of random music in about 30 seconds.

This project trains a neural network to generate midi single instrument music files.

Pickin' #1:

Pickin' #2:

Allows uploading of an image for OCR using Tesseract and deployed using Docker on balenaCloud. This project uses Flask, a light weight web server framework, which should be used for development purposes only. OpenCV is used to reduce noise in the image for better processing by pytesseract. Originally deployed in a Docker container on AWS - this version is revised to be deployed to BalenaCloud to a Jetson Nano device.

Github Repo: https://github.com/ricktorzynski/balena-ocr-tesseract-docker

Allows upload of an image for OCR using Tesseract and deployed using Tkinter. This uses Tkinter, a Python GUI framework based on Tcl/Tkl. OpenCV is used to reduce noise in the image for better processing by pytesseract. This app will also OCR multiple pages and add the OCR text to a text area.

Github Repo: https://github.com/ricktorzynski/ocr-tesseract-opencv-tkinter

Bluegrass Gospel Jam Network

Guardian Self Defense

Florida Blue Medicare

Axanar Donation Site

Ares Digital 3.0

Handbag Express