When approaching a problem using Machine Learning or Deep Learning, researchers often face a necessity of model tuning because the chosen method usually depends on various hyperparameters and used ...
Image Matting with state-of-the-art Method “F, B, Alpha Matting”
The foreground is the part of a view or picture, that is nearest to you when you look at it (Oxford dictionary). We, humans, are usually good at distinguishing foreground objects on images from the ...
Bag of Tricks for Image Classification
Introduction Image classification is a key task in Computer Vision. In an image classification task, the input is an image, and the output is a class label (e.g. "cat", "dog", etc. ) that ...
TensorBoard with PyTorch Lightning
A picture is worth a thousand words! As computer vision and machine learning experts, we could not agree more. Human intuition is the most powerful way of making sense out of random chaos, ...
Getting Started with PyTorch Lightning
Imagine, one day you have an amazing idea for your machine learning project. You write down all the details on a piece of paper- the model architecture, the optimizer, the dataset. And now you just ...
Ensuring Training Reproducibility in PyTorch
Imagine you trained a deep learning model on some dataset. A few days later, you want to reproduce the same experiment, but if you were not careful, you may never be able to reproduce the same ...