Training an image captioning model with visual attention. An example of combining 2 modalities into a single model.

Training an RNN encoder-decoder to translate Spanish to English. This is a simple demonstration of sequence-to-sequence model.

Training a simple RNN text generator to demonstrate the concept of text generation.

Below are my notes from the course  "Generative AI with Large Language Models" offered by  deeplearning.ai

In this post I am going to document the process of building the TensorFlow Lite android library and C library (libtensorflowlite_c) on Ubunt...

Running TensorFlow Lite on Windows using the XNNPACK delegate

Developing a custom Aruco marker detector is a great practice of some basic image processing... We will also see how to use it for camera po...

Handling git error "dst refspec xyz matches more than one"...