<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[Aren8的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/Aren8</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; Aren8]]></copyright><item><title><![CDATA[MindSpore之Faster_rcnn]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/120932635</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/120932635</guid><author>Aren8</author><pubDate>Sun, 24 Oct 2021 13:32:06 +0800</pubDate><description><![CDATA[前一阵子参加了华为的多目标检测比赛 link，尝试通过 faster_rcnn 算法定位和分类病理图像中的癌细胞。MindSpore 是华为的 AI 框架，支持华为自研的Ascend芯片。MindSpore目前不支持macOS，不过组织方提供了华为云作为训练平台。以下将分享使用mindspore及华为云的经验。
Notebook


首先可以从mindspore官方的 gitee 上下载faster_rcnn模型, 注意原先的model_zoo已经被移至model 仓库，同时还可以这里 link 下载在im]]></description><category></category></item><item><title><![CDATA[Django简易]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115804349</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115804349</guid><author>Aren8</author><pubDate>Sun, 18 Apr 2021 00:11:32 +0800</pubDate><description><![CDATA[重要命令：
1. django-admin startproject mysite
2. cd .\mysite
3. code . #开启vscode
4. python manage.py startapp myapp
5. #in mysite.setting:
	INSTALLED_APPS = [
	    'myapp',
	]
6. python manage.py migrate
7. python manage.py runserver

详细教程：
Django 框架快速入门
视频讲解：]]></description><category></category></item><item><title><![CDATA[Pytorch使用]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115671862</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115671862</guid><author>Aren8</author><pubDate>Tue, 13 Apr 2021 19:30:30 +0800</pubDate><description><![CDATA[训练

#generic
class LayerLinearRegression(nn.Module):
    def __init__(self):
        super().__init__()
        # Instead of our custom parameters, we use a Linear layer with single input and single output
        self.linear = nn.Linear(1, 1)
           .]]></description><category></category></item><item><title><![CDATA[数据预处理：pandas的使用和cv2初步]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115543568</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115543568</guid><author>Aren8</author><pubDate>Fri, 09 Apr 2021 11:40:41 +0800</pubDate><description><![CDATA[#读取文件夹里的所有文件名
filenames = os.listdir("../input/train/train")
#创建对应的分类
categories = []
for filename in filenames:
    category = filename.split('.')[0]
    if category == 'dog':
        categories.append(1)
    else:
        categories.append(0)
#创建datafram]]></description><category></category></item><item><title><![CDATA[tensorflow ImageDataGenerator的使用]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115467346</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115467346</guid><author>Aren8</author><pubDate>Fri, 09 Apr 2021 10:49:34 +0800</pubDate><description><![CDATA[docs
link

]]></description><category></category></item><item><title><![CDATA[django静态文件的引入方法]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115448850</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115448850</guid><author>Aren8</author><pubDate>Thu, 08 Apr 2021 20:40:51 +0800</pubDate><description><![CDATA[Link1

]]></description><category></category></item><item><title><![CDATA[笔记_Prognosis_week4]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/108049381</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/108049381</guid><author>Aren8</author><pubDate>Thu, 08 Apr 2021 20:28:32 +0800</pubDate><description><![CDATA[一. Survival(S) and hazard function(λ）


the definition



the formula and curve of the survial to hazard function



the formula and curve of the hazard to survial function



Cumulative Hazard
a) the formula and definition

求和代表离散时间，积分代表连续时间
b) the curve ]]></description><category></category></item><item><title><![CDATA[tensorflow (gpu)安装报错]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115448859</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115448859</guid><author>Aren8</author><pubDate>Thu, 08 Apr 2021 20:09:05 +0800</pubDate><description><![CDATA[各种报错的解决

]]></description><category></category></item><item><title><![CDATA[交叉验证：cross validation]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/115479877</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/115479877</guid><author>Aren8</author><pubDate>Wed, 07 Apr 2021 11:01:55 +0800</pubDate><description><![CDATA[cross validation的目的：进行调参
注意: cross validation的目的不是训练神经网络
如何做(以最简单的为例)
|1. 划分trainning set,test set, test set 不要动(仅用于最后评估参数)
|2. 设置grid:选择多组参数，接下来对每组参数重复以下步骤
|&gt;&gt;&gt;&gt;2.1. 把trainning set分成5份， 重复5次以下步骤
|&gt;&gt;&gt;&gt;&gt;&gt;&gt;2.1.1. 拿出一份作为valid.]]></description><category></category></item><item><title><![CDATA[OS module的简单使用， numpy保存文件， (zip,map,lambda)的使用]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/113880001</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/113880001</guid><author>Aren8</author><pubDate>Fri, 05 Mar 2021 23:01:19 +0800</pubDate><description><![CDATA[获取的都是当前脚本所在的dir2目录 link
os.path.dirname(os.path.realpath(__file__)) 


]]></description><category></category></item><item><title><![CDATA[tqdm和pickle的使用，datetime和time的使用，SimpleNamespace和glob的使用]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/113847326</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/113847326</guid><author>Aren8</author><pubDate>Thu, 18 Feb 2021 15:45:19 +0800</pubDate><description><![CDATA[参考：使用python常用的一些技巧
1.如何使用.运算符访问字典
types.SimpleNamespace()
&gt;&gt; from types import SimpleNamespace
&gt;&gt;&gt; d = {'a': 1, 'b':2}
&gt;&gt;&gt; sn = SimpleNamespace(**d)  # 这里的**不可以少,表示命名关键字参数
&gt;&gt;&gt; sn    #namespace(a=1, b=2)
&gt;&gt;&gt; sn.a  #]]></description><category></category></item><item><title><![CDATA[pytorch的安装报错]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/113846602</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/113846602</guid><author>Aren8</author><pubDate>Thu, 18 Feb 2021 14:52:16 +0800</pubDate><description><![CDATA[官网查到是这两条指令
pip install torch torchvision torchaudio
conda install pytorch torchvision torchaudio -c pytorch
失败过程

官网下载太慢  失败
使用镜像 镜像源没有torchaudio 失败
尝试其他方法继续报错

注意：
“-c pytorch”指定了从pytorch官网下载，如果要使用镜像源，需要删掉-c pytorch
解决：

使用镜像
conda install pytorch torchvi]]></description><category></category></item><item><title><![CDATA[conda的基本使用]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/113846008</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/113846008</guid><author>Aren8</author><pubDate>Thu, 18 Feb 2021 14:43:08 +0800</pubDate><description><![CDATA[conda与虚拟环境

创建新的环境 创建名为 test 的环境，使用的 python 版本为 python3：
conda create -n test python=3
conda create --name myclone --clone myenv 克隆环境
conda activate test (填写你的env_name) 进入创建的虚拟环境
conda deactivate 退出创建的虚拟环境
conda常用命令
//查看已有的 conda 环境，包括环境的名字和其对应的目录。
conda e]]></description><category></category></item><item><title><![CDATA[argparse模块]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/113844787</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/113844787</guid><author>Aren8</author><pubDate>Thu, 18 Feb 2021 14:04:19 +0800</pubDate><description><![CDATA[基础
demo.py文件
import argparse

parser = argparse.ArgumentParser(description='命令行中传入一个姓名')
#type是要传入的参数的数据类型  help是该参数的提示信息
parser.add_argument('name', type=str, help='姓名')
args = parser.parse_args()
#获得传入的参数
print(args)
#print

命令行:
python demo.py -h  #提示信息]]></description><category></category></item><item><title><![CDATA[Apply GANs week3]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/109355710</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/109355710</guid><author>Aren8</author><pubDate>Thu, 29 Oct 2020 11:29:49 +0800</pubDate><description><![CDATA[Unpaired Image-to-Image Translation
Why is unpaired image-to-image translation different than paired image-to-image translation?
There is no longer a clear target output.

Correct! WIth unpaired image-to-image translation, you can just have a pile of image]]></description><category></category></item><item><title><![CDATA[Apply GANs week2]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/109355519</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/109355519</guid><author>Aren8</author><pubDate>Thu, 29 Oct 2020 11:28:24 +0800</pubDate><description><![CDATA[Image-to-Image Translation
What is paired translation?
When you have corresponding input-output images that you can gather training data for.

Correct! Paired translation means that you have input-output pairs that map exactly onto each other (1-to-1).

Pa]]></description><category></category></item><item><title><![CDATA[Build Basic GANs week4]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/109274770</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/109274770</guid><author>Aren8</author><pubDate>Sun, 25 Oct 2020 16:02:41 +0800</pubDate><description><![CDATA[How does the generator learn what class to generate?
The discriminator is checking if an image looks real or fake based on (conditioned on) a certain class.

Correct! The discriminator also receives the class label and will classify the images based on if ]]></description><category></category></item><item><title><![CDATA[Build Basic GANs week3]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/109273859</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/109273859</guid><author>Aren8</author><pubDate>Sun, 25 Oct 2020 15:20:46 +0800</pubDate><description><![CDATA[Mode Collapse
Why can mode collapse occur?
The generator gets stuck in a local minimum.

Correct! Mode collapse occurs when the generator gets stuck generating one mode. The discriminator will eventually learn to
differentiate the generator’s fakes when th]]></description><category></category></item><item><title><![CDATA[Coursera Deep learning 复习]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/108260271</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/108260271</guid><author>Aren8</author><pubDate>Thu, 27 Aug 2020 14:43:07 +0800</pubDate><description><![CDATA[CNN
Sequence Model:

Week 1:

Assignment 1: RNN和LSTM模型的 foward propagation （tensorflow）
Assignment 2: Clip, Sample和完整LSTM 模型（tensorflow）
Assignment 2: Single LSTM step和预测模型 (Keras)


Week 2:

Assignment 1: 相似度和中性化
Assignment 2: 简单的情感分类模型和使用LSTM layer的情感分类.]]></description><category></category></item><item><title><![CDATA[笔记_Prognosis_week3]]></title><link>https://blog.youkuaiyun.com/Aren8/article/details/107939392</link><guid>https://blog.youkuaiyun.com/Aren8/article/details/107939392</guid><author>Aren8</author><pubDate>Tue, 11 Aug 2020 17:29:02 +0800</pubDate><description><![CDATA[Survival Estimate function on the whole population
一. Survival Model feature
a) Decreasing survive possibility as time goes on. b) Start at 1 and end at 0.
二. Censoring (实验终止)

Right censoring: the timed the event is only known to exceed a
certain value(18]]></description><category></category></item></channel></rss>