Category: > Programming

Normally, It would be used CNN or Dense for MNIST, but this time I used RNN. RNN training takes a lot of time. So you should use GPU. If you try to do around 50 epochs as shown below, it may...

This datasets has 50000 color images for training and 10000 color images.  Regarding class, It’s labeled as follows. Normally we can see many sample of MNIST and CIFAR10 on internet. But kinda seldom to see CIFAR100. So I try to do...

  I understand that no need to use keras for this wine recognition. Scikit-learn is better, easy and good result. This is just less than 200 dataset. Just I try to use keras for small dataset of categorical analysis.   .....

It is so trouble and annoying if currency price change high and down. When should we exchange? Everybody would like to know it..Ops. This is small talk. Let’s get down the business. I tried to creat a model to predict the movement...