Google Cloud offers an excellent Jupyter Notebook managed service called Vertex AI Workbench which is relatively pricy. For some cases, I suggest using an old trick that can get you up to a 91% discount: hosting Jupyter Notebooks on Compute Engine Spot Instances using standard templates. This easy solution yields almost the same experience as … Continue reading 💸 Almost-Free Jupyter Notebooks on Google Cloud!
Overfitting causes serious headaches when training ML/DL models. But in this article, you'll see how just a few lines of code can generate data augmentations and boost your model's performance on the validation set. Additionally, you'll learn how to properly measure the effect of data augmentation using MLflow's experiment tracking. To accomplish the above, we'll … Continue reading Can a couple TensorFlow lines reduce overfitting?