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 ...
Understanding Lens Distortion
In a previous post, we went over the geometry of image formation and learned how a point in 3D gets projected on to the image plane of a camera. The model we used was based on the pinhole camera ...
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 ...
Getting Started with OpenCV CUDA Module
If you have been working with OpenCV for some time, you should have noticed that in most scenarios OpenCV utilizes CPU, which doesn't always guarantee you the desired performance. To tackle this ...