-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
108 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,106 @@ | ||
--- | ||
catalog: | ||
- zhoukan | ||
created_time: '2024-05-05 08:00:00' | ||
type: Post | ||
slug: zhoukan4 | ||
title: 好玩周刊 (第三期) 2024.5.5 | ||
status: 已发布 | ||
urlname: 55ccba7c-a6ea-41c4-8b54-22fd39361a88 | ||
date: '2024-05-04 23:23:00' | ||
updated: '2024-05-05 11:15:00' | ||
--- | ||
|
||
# 好玩周刊 (第三期) 首届AI方**程式大赛** 2024.5.5 | ||
|
||
|
||
这里记录好玩的任何事物,每周发布。 | ||
|
||
|
||
也许没有人会看,也供自己闲暇时候回顾。 | ||
|
||
|
||
## 封面图 | ||
|
||
|
||
 | ||
|
||
|
||
> 首届AI方程式大赛 A2RL | ||
|
||
## 首届AI方程式大赛 A2RL | ||
|
||
|
||
这个月,F1中国大奖赛,周冠宇迎来主场首秀。F1这项赛事在中国换发了一个新的生机。 | ||
|
||
|
||
对于F1我的印象还停留在小时候看极速汽车频道里的画面,对于F1的赛制和了解非常浅薄。 | ||
|
||
|
||
不过最近这个A2RL的自动驾驶F1让我引起了我的很大兴趣。由算法驱动的F1是怎么样的呢,这个实现起来一定是一个非常酷的事情。F1+算法是科技前沿的联合了。看了机器之心对于这个赛事的报道,还是非常有趣的。 | ||
|
||
|
||
[https://finance.sina.cn/tech/2024-04-29/detail-inatnptz3058864.d.html?fromtech=1&from=wap](https://finance.sina.cn/tech/2024-04-29/detail-inatnptz3058864.d.html?fromtech=1&from=wap) | ||
|
||
|
||
我想也许AI还可以结合更多有趣的东西,AI方程式仅仅展现了AI+的一环。很多东西加上AI也许会更加有趣。可以说AI+目前感觉还能结合更多东西,也是当前的蓝海。 | ||
|
||
|
||
## 好玩网站: | ||
|
||
|
||
**1.深入浅出PyTorch** | ||
|
||
|
||
[https://datawhalechina.github.io/thorough-pytorch/index.html](https://datawhalechina.github.io/thorough-pytorch/index.html) | ||
|
||
|
||
一个从谷歌搜索到的pytorch全面教程,算是能够精通pytorch,不过还需要辅以深度学习相关概念。 | ||
|
||
|
||
以后可以多学习一下。 | ||
|
||
|
||
**2.魔塔社区** | ||
|
||
|
||
[https://www.modelscope.cn/home](https://www.modelscope.cn/home) | ||
|
||
|
||
相当于huggingface的中文模型社区,即使随便逛一逛也能有点收获。 | ||
|
||
|
||
huggingface中国用不了,这个可以作为一点替代品。 | ||
|
||
|
||
**3.保姆级教程,用PyTorch和BERT进行文本分类** | ||
|
||
|
||
[https://zhuanlan.zhihu.com/p/524487313](https://zhuanlan.zhihu.com/p/524487313) | ||
|
||
|
||
详细的描述了怎么使用bert预训练模型进行数据集训练,写的非常详细基础,在这个教程上我尝试写了一个头条的新闻数据集进行训练。得到了以下好成绩。一个通用的预训练模型可以帮助很好的进行一些具体实验。 | ||
|
||
|
||
Epochs: 2 | ||
| Train Loss: 0.172 | ||
| Train Accuracy: 0.904 | ||
| Val Loss: 0.194 | ||
| Val Accuracy: 0.890 | ||
|
||
|
||
有点郁闷的是,用学校训练了5小时左右,缺找不到保存的预训练权重。 | ||
|
||
|
||
## 好玩的事: | ||
|
||
|
||
**1.无限/多次回购的速食食品?** | ||
|
||
|
||
[https://sspai.com/bullet/1713257129/](https://sspai.com/bullet/1713257129/) | ||
|
||
|
||
在少数派看到了这么一个讨论,本身我也喜欢速食食品。主要是速食食品方便,容易保存,且可以品尝不同风味的食品,有的也相对干净。这个讨论看到了不少可以尝试的产品。 | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
2024-05-05 03:14:27 begin | ||
2024-05-05 03:16:16 begin |