Sabyasachi SahooinTowards Data ScienceResidual blocks — Building blocks of ResNetUnderstanding a residual block is quite easy. In traditional neural networks, each layer feeds into the next layer. In a network with…Nov 27, 20186Nov 27, 20186
Sabyasachi SahooinTowards Data ScienceSeparable convolutions — trading little accuracy for huge computational gainsTypically in convolutions, we use a 2D or a 3D kernel filter where we hope that each filter extracts some kind of a feature by convoluting…Nov 19, 20181Nov 19, 20181
Sabyasachi SahooinTowards Data ScienceGrouped Convolutions — convolutions in parallelUsually, convolution filters are applied on an image layer by layer to get the final output feature maps. We increase the no of kernels…Nov 18, 20181Nov 18, 20181
Sabyasachi SahooinTowards Data ScienceDeciding optimal filter size for CNNsSo, by now you know how to use convolutional neural networks (CNNs) on your datasets and you start wondering: Apart from tuning various…Aug 19, 20183Aug 19, 20183