practical-cnn
practical-cnn copied to clipboard
vedaldi
A VGG practical on convolutional neural networks
For example, in exercise 3, why you compute dzdx3 as follows: dzdx3 = ... - single(res.x3 < 1 & pos) / sum(pos(:)) + ... + single(res.x3 > 0 & neg)...
i want to know where can get the standard answer about those task？
In the BP formulation(1), the x(L) should be x(L-1), and other formulations have the same problem. The corresponding formulation in the matconvnet manual is right.
I want to train the vgg-vd-16 model from scratch, which parameter initialization method should I choose, gaussian or xavier or xavierimproved?
hi, in part 2 there is a calculation of dzdx_empirical , can somone help and explain the calculation? why is there a sum? and why is there a division by...
Propose to add some titles to the images to be more clear what is what. Propose to add some pauses, to that it would be possible to view the results...
Moved prime designator in normalisation equation to sum variable to agree with notation in G(k) after inline equation in G(k) after inline equation [style]. Made channel of input (k) agree...