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 […]
Tag Cloud
active contour Algorithm alpha beta pruning Armadillo Bilateral Filter Blur C++ camShift Cluster CNN Computer Vision Convolutional Neural Networks Deep Learning deep network Dynamic Programming Gradient Descent image blending Image Processing image pyramid LeetCode Machine Learning Matlab meanShift MNIST neural networks NLP Octave OpenCV Panorama PCA Poisson blending Pooling pyramid blending RANSAC Recurrent Neural Networks RNNs seam carving SIFT snake Softmax Sparse Autoencoder track UFLDL Unsupervised Learning ZCAPages
Categories
Archives