through a very easy example & including code! 🤓 📓
Disclaimer: this is not an extensive tutorial on training Tesseract, just the setting up of the machine through a very simple training example!
Recently I wanted to know whether training Tesseract would improve the results 📈 in the scope of my problem or not.
Despite of all official recommendations I wanted to give it a try!
Important note: Before you invest time and effort on training Tesseract, it is highly recommended to read the ImproveQuality page.
In theory, two main reasons would lead to retraining Tesseract:
Everybody talks about AI. If you have no idea about the topic and the buzzwords around it, this is your place!
By the end of this post you’ll be able to:
I would like to share with you a few things I’ve learned from testing Pandas and Numpy when performing a very specific operation: the dot product.
Yes yes, of course this post comes along with its own Jupyter Notebook.
Everything started with Metaphor, a personal project I’m using to explore Word Embeddings. Totally at an early stage, but promising fun! What? You don’t know what word embeddings are? King-Man + Woman = ?
Well, if that doesn’t ring the bell don’t worry. This post isn’t about Word Embeddings at all 😅.
But hey, I’ll tell you about the origin anyway…