Machine Learning

PyTorch a is deep learning framework based on Python, we can use the module and function in PyTorch to simple implement the model architecture we want.

When we use RNN network (such as LSTM and GRU), we can use Embedding layer provided from PyTorch, and receive many different length sequence sentence input.

Problem

Today, when I was trying to use nn.Embedding() to splice and calculate sentence vectors by myself, I got an error like this on the DataLoader I prepared in advance:

When we using PyTorch to build the model for deep learning tasks, sometimes we need to define more and more model layer.

It is so irritating. No one wants to keep pasting similar code over and over again.

What Is AutoEncoder ?

AutoEncoder is often referred to as AE for short. It is a neural network for unsupervised learning, in other words, it does not require labaled data.