PinnedAngel IgaretainTowards Data ScienceThe Million-Dollar Question: When to Stop Training your Deep Learning ModelOn early stopping, or how to avoid overfitting or underfitting by knowing how long to train your neural network for·5 min read·Jun 22, 2021--1--1
PinnedAngel IgaretainTowards Data ScienceDealing with Imbalanced Data in TensorFlow: Class WeightsClass imbalance is a common challenge when training Machine Learning models. Here is a possible solution by generating class weights and…4 min read·Jun 8, 2021--2--2
Angel IgaretainKlarna EngineeringStop Misusing ROC Curve and GINI: Navigate Imbalanced Datasets with ConfidenceDiscover how the Precision-Recall curve can provide a more robust metric for binary classification in data science and machine learning.9 min read·Nov 9, 2023----
Angel IgaretainTowards Data ScienceTaking the TensorBoard Embedding Projector to the Next LevelTensorBoard Projector allows to graphically represent low-dimensional embeddings. Here I show you how, instead of displaying a point, you…·4 min read·Jul 28, 2021--3--3
Angel IgaretainTowards Data ScienceStratified Sampling: You May Have Been Splitting Your Dataset All WrongRandomly generating splits of the data set is not always the optimal solution, as the proportions in the target variable can be extremely…3 min read·Jul 21, 2021--1--1
Angel IgaretainTowards Data ScienceRemoving Duplicate or Similar Images in PythonWhen training a machine learning model that uses images as input, it is relevant to check for similar or duplicated pictures in the…3 min read·Jul 14, 2021--2--2
Angel IgaretainTowards Data ScienceHow to Split a Tensorflow Dataset into Train, Validation, and Test sets·4 min read·Jun 2, 2021----
Angel IgaretainTowards Data ScienceA better comparison of TensorBoard experimentsAn existing TensorBoard limitation is that it only considers the last epoch when ranking experiments. Here is how to better evaluate…4 min read·May 12, 2021----