Have you ever wondered how Instagram masks are fitting so perfectly on your face? Would you like to know how you can try to implement something similar by yourself? This post will help you with that! ...
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 ...
How to Convert a Model from PyTorch to TensorRT and Speed Up Inference
The life of a machine learning engineer consists of long stretches of frustration and a few moments of joy! First, struggle to get your model to produce good results on your training data. You ...
Graph Convolutional Networks: Model Relations In Data
In an earlier post, we covered the problem of Multi Label Image Classification (MLIC) for Image Tagging. Recall that MLIC is an image classification task but unlike multi-class image ...
Experiment Logging with TensorBoard and wandb
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 ...
Federated Learning using PyTorch and PySyft
This is a a gentle introduction to federated learning --- a technique that makes machine learning more secure by training on decentralized data. We will also cover a real-life example of federated ...
