PCA和AutoEncoder這兩個方法，大家因該都是耳熟能詳。兩者的差異在於PCA是使用線性變換的方式，透過乘上一個矩陣 ...

This section describes how to train a Variational Autoencoder (VAE) using perceptual loss, i.e. instead of a loss that depends on the pixel-wise difference between the training image and the ...

Generating high-quality images based on text descriptions is an appealing research topic, which has widespread applications in various fields. However, it is quite challenging since that images and ...