ResNet9: train to 94% CIFAR10 accuracy in 100 seconds with a single Turing GPU
DAWNBench recently updated its leaderboard. Among the impressive entries from top-class research institutes and AI Startups, perhaps the biggest leap was ...
Published on by Chuan Li
DAWNBench recently updated its leaderboard. Among the impressive entries from top-class research institutes and AI Startups, perhaps the biggest leap was ...
Published on by Chuan Li
Object Detection using Single Shot MultiBox Detector The problem The task of object detection is to identify "what" objects are inside of an image and "where" ...
Published on by Chuan Li
SegNet. Image source: https://mi.eng.cam.ac.uk/projects/segnet/ The problem Image segmentation is the problem of assigning each pixel in an image a class ...
Published on by Chuan Li
Hyper-parameter search: Grid v.s. Random. Image source: [Bergstra and Bengio 2012] In order to improve the performance of a neural network, it is often ...
Published on by Chuan Li
Images from Stanford Dogs Dataset: http://vision.stanford.edu/aditya86/ImageNetDogs/ Our last tutorial described how to do basic image classification with ...
Published on by Chuan Li
T-SNE embedding of CIFAR10. Image source: http://cs231n.github.io/classification/ Welcome to our Beginner's Demo! We will walk you through the steps of ...