OpenCV library is widely used due to its extensive coverage of the computer vision tasks, and availability to involve it in various projects, including deep learning. Usually, OpenCV is used with C++ ...
PyTorch to Tensorflow Model Conversion
In this post, we will learn how to convert a PyTorch model to TensorFlow. If you are new to Deep Learning you may be overwhelmed by which framework to use. We personally think PyTorch is the first ...
Stanford MRNet Challenge: Classifying Knee MRIs
Stanford ML Group, led by Andrew Ng, works on important problems in areas such as healthcare and climate change, using AI. Last year they released a knee MRI dataset consisting of 1,370 knee MRI ...
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 ...
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 ...