Published inGeek CulturePython best practices even data scientists should knowHow to make your code as clean and readable as possibleMay 27, 2022May 27, 2022
Published inDecathlon DigitalHow can engineering interns contribute to a data science team?Why data science teams should hire interns and what they should work onMay 18, 2022May 18, 2022
Published inTowards Data ScienceWhat is the best input pipeline to train image classification models with tf.keras?A comparison between keras’ ImageDataGenerator, tensorflow’s image_dataset_from_directory and various tf.data.Dataset pipelines.Feb 3, 2021Feb 3, 2021
Published inThe StartupHow Simple Is It to Build an End-to-End Item-Based Recommender System?Collect data, train a model and deploy it using popular data science librariesJan 21, 20211Jan 21, 20211
Published inTowards AIHow To Win Your NHL Pool Without Even TryingHow I used machine learning to predict the number of points that a hockey player will score this yearJan 13, 2021Jan 13, 2021
Published inDecathlon DigitalIntroducing DecaVision to train image classifiers with Google’s free TPUsTrain your own computer vision models in a fraction of the time with Decathlon’s python packageDec 11, 2020Dec 11, 2020
Published inDecathlon DigitalBuilding a web app to capture sports trends on InstagramHow Décathlon capitalizes on social listeningSep 8, 2020Sep 8, 2020
Published inTowards Data SciencePython utility functions for computer visionHow to save some time managing your images when working on image classification.Apr 20, 2020Apr 20, 2020
Published inTowards Data ScienceFrom theoretical physicist to data scientistHow I became a data scientist with a PhD in theoretical physicsJan 15, 2020Jan 15, 2020
Published inTowards Data ScienceMaking an image dataset from Youtube videosHow to improve your deep learning dataset with realistic images.Oct 1, 2019Oct 1, 2019