AI with Catherine Ordun

Sign in Subscribe

data processing

PyTorch Pair-Wise Transforms and Data

PyTorch Pair-Wise Transforms and Data

Consider that you have a pair of images you want to train. In my case, it's a GAN, where I'm improving upon older work from 2020 in the facial-visible-to-thermal GAN [https://github.com/nudro/favtgan]. My paired image consists of a visible and thermal face, simultaneously

Basic cropping with PIL and PyTorch

Basic cropping with PIL and PyTorch

I'm embarrassed to say that even at this point in my life, I still have to look up this formatting to crop an image. Once and for all, I'll post it here so that I don't forget it and also in case you'

Pandas and PIL

Pandas and PIL

This was a quick and handy little script that I think some of you might need from time to time, especially if you're dealing with lots and lots of annotated, labeled images. In the AffectNet dataset, there's a 5.4 Gb file that for me on

Organizing files in train/test directories

Organizing files in train/test directories

For a prototype model I'm writing that involves a multi-class problem with facial images, I've found the need to use some basic Python code to organize my image files and partition them into train and test directories. I thought it might be helpful to post this

Exploring Different Data Preprocessing Methods for LSTMs

Exploring Different Data Preprocessing Methods for LSTMs

I tend to focus a lot on how the data is wired, snipped, and prepared for models. I think the preprocessing steps of data lay the foundations by which all models are built and provides me a highly valuable exercise to understand the nooks and crannies of my dataset, especially