Deep Learning Made Easy

How to use a custom loss with hugging face

Recently I helped a colleague at work to fix an issue to setup a custom loss when using hugging face. We couldn’t find much information about it, so we had to figure it out ourselves. Here I want to share it so others can find it next time.

MLFlow for MLOps

Recently I have been looking for different alternatives for mlops at my job. We end up choosing mlflow and with this article I…

Sparsemax: from paper to code

Here we are with another paper implementation. Veeeery slowly, but I’m on my way to implement TabNet paper…

Ghost BatchNorm explained

From paper to code

GLU: Gated Linear Unit implementation

From paper to code

List of deep learning losses for regression

Mean absolute value

Deep learning losses for classification & probabilities

An unified view

Classification &…

DeepFactors for forecasting, architecture review

The difference between the mean and the median.