看了下官方手册和网上的一些解释，但还是没太弄明白，于是自己下来在草稿纸上画了一下，然后用程序验证，总算把这两个函数搞懂了些。

Pytorch Math operations

Pointwise Ops

基本运算

• torch.add()
  • torch.add(input, other, out=None)--执行加法，out=input+other
  • torch.add(input, other, alpha=1, out=None)--out=input + alpha x other
• torch.abs(input, out=None)--求绝对值，返回Tensor
• torch.div(input, other, out=None)--除法运算，这里的other可以是一个标量或者是一个张量

• torch.fmod(input, other, out=None)--input中的每个数据对other取余，余数和input中的被除数符号相同

• torch.mul(input, other, out=None)--相乘，

  \(out_i = input_i \times other\)或者\(out_i = input_i \times other_i\)

• torch.neg(input, out=None)--对每个元素乘以-1

• torch.remainder(input, other, out=None)--input中的每个数据对other取余，余数和除数的符号相同

突然心血来潮想搭建一个自己的博客，此前我有在博客园写一些博客的习惯，但看到那些简洁漂亮的个人博客，我也有些心痒想自己搭建一个。今天刚好在B站看到UP主CodeSheep发的一个个人博客搭建指南的视频，于是跟着视频自己也做了一个，虽然视频只有20分钟，但却花了我整整一个下午才勉强算是把博客搭建起来了，我在此记录一下这个过程，以及在中途遇到问题后在网上找到的相应的解决方法，希望对之后想搭建个人博客的小伙伴有所帮助。（以下内容仅针对windows操作系统）

0.LaSO: Label-Set Operations networks for multi-lable few-shot learning

1. Summary

This paper focus on the multi-label few-shot learning, where has no prior work of this task. They proposed Label-Set Operations networks, which can generate new multi-label samples in the feature space, this method can be seen as data augmentation techinques.

0. Matching Network for One Shot Learning

1. Summary

This paper is a metric-based method for few-shot learning task. It uses attention mechanism and considers to embed the whole support set into feature space not just a single sample in the support set. Given a query image, the predict output is the weighted sum of the samples in the support set.

Welcome to Hexo! This is your very first post. Check documentation for more info. If you get any problems when using Hexo, you can find the answer in troubleshooting or you can ask me on GitHub.

Quick Start

Create a new post

1

$ hexo new "My New Post"

More info: Writing

Run server

1

$ hexo server

More info: Server

Generate static files

1

$ hexo generate

More info: Generating

Deploy to remote sites

1

$ hexo deploy

More info: Deployment