OPTICAL FLOW We are always interested in finding the movement of objects from videos, optical flow is one of the most famous methods to do this. Optical flow has lots of uses, such as tracking object, camera correction, mosaics and so on. All optical flow methods are based on the following assumptions: Color constancy (brightness […]
This post is about a new cluster algorithm published by Alex Rodriguez and Alessandro Laio in the latest Science magazine. The method is short and efficient, I implemented it using about only 100 lines of cpp code. BASIC METHOD There are two leading criteria in this method: Local Density and Minimum Distance with higher density. Rho above is the […]
I chose “Dropped out auto-encoder” as my final project topic in the last semester deep learning course, it was simply dropping out units in regular sparse auto-encoder, and furthermore, in stacked sparse auto-encoder, both in visible layer and hidden layer. It does not work well on auto-encoders, except can be used in fine-tune process of stacked sparse […]
The CIFAR-10 dataset can be found HERE. It is a very popular multi-channel image dataset for classifier training, as a simplify version of CIFAR-100, it is easier to use for newbies. Here’s a C++ version code for reading this dataset from .bin files into OpenCV matrices.
Since the last CNN post, I was working on a new version of CNN, which support multi-layers Conv and Pooling process, I’d like to share some experience here. VECTOR VS HASH TABLE You can see in the last post, I used vector of Mat in convolution steps, it works well when we only have one […]
WHAT IS CNN A Convolutional Neural Network (CNN) is comprised of one or more convolutional layers, pooling layers and then followed by one or more fully connected layers as in a standard neural network. The architecture of a CNN is designed to take advantage of the 2D structure of an input image (or other 2D input […]
This is the early version of my CNN, at that time, I incorrectly thought that I can just use some randomly chosen Gabor filters to do the convolution, so I wrote this. Actually, the test result is not bad for simple datasets such as MNIST, I think it’s just a fake CNN, but a nice […]
During this spring break, I worked on building a simple deep network, which has two parts, sparse autoencoder and softmax regression. The method is exactly the same as the “Building Deep Networks for Classification” part in UFLDL tutorial. For better understanding it, I re-implemented it using C++ and OpenCV. GENERAL OUTLINE Read dataset (including training data […]
Posted in Algorithm, Machine Learning, OpenCV
Tagged C++, Deep Learning, fine-tune, Machine Learning, MNIST, OpenCV, Softmax, Sparse Autoencoder, UFLDL
I’m learning Prof. Andrew Ng’s Unsupervised Feature Learning and Deep Learning tutorial, This is the 8th exercise, which is a simple ConvNet with Pooling process. I’ll not go through the detail of the material. More details about this exercise can be found HERE. I’ll try to implement it using C++ and OpenCV if I have time next week.