semi-supervised-paper / semi-supervised-paper-implementation Goto Github PK

Hello,

I found your ZCA matrix and thanks for your upload.

I know how to calculate ZCA matrix, but for CIFAR10 or 100 the matrix is huge and my hardware cannot support this.

So I want to know, how you calculate the matrix? by brutal force(means you have some super hardware) or is there some tricks to estimate the ZCA matrix for the whole dataset?

really thanks if you can give me some hint

Hi,

Thanks for your implementation.

However, my hardware just cannot support me to calculate the ZCA matrix as the dataset is quite big. [50000, 3, 32, 32]

Thus can you also provide us the ZCA matrix?

really thanks