Py-博客學習50問

1.time.time()/clock()

https://www.cnblogs.com/bettermanlu/archive/2011/09/19/2181529.html

前者掛鍾時間，后者處理器CPU時間。

掛鍾時間也稱為經過時間或運行時間。 與CPU時間相比，掛鍾時間通常更長，因為執行測量程序的CPU也可能同時執行其他程序的指令。

2.reload(sys)

https://blog.csdn.net/qq_36711420/article/details/79382327

主要進行編碼格式的轉換

3.local variable 'xxx' referenced before assignment

http://blog.sina.com.cn/s/blog_4b9eab320100q2l5.html

4. 8大排序算法

微信文章鏈接

5.希爾排序

https://blog.csdn.net/weixin_37818081/article/details/79202115

6.歸並排序

https://blog.csdn.net/k_koris/article/details/80508543

7.python中的Swap函數

https://blog.csdn.net/hyqsong/article/details/47864753

8.CNN

https://nndl.github.io/
9.LeNet-5學習及簡單實現

https://www.charleychai.com/blogs/2018/ai/NN/lenet.html

https://blog.csdn.net/qq_15192373/article/details/78536107

10.MNIST數據集介紹

https://blog.csdn.net/simple_the_best/article/details/75267863

11.CNN中補齊same/valid兩種方式

https://blog.csdn.net/wuzqChom/article/details/74785643

https://blog.csdn.net/qq_30979017/article/details/79407720

import keras

def test_model(input):
    input=keras.layers.Input(input)
    x=keras.layers.Conv2D(32,(5,5),strides=(2,2),padding='same')(input)
    return keras.models.Model(input,x)
model=test_model((7,7,3))

12.conv1D和conv2D的區別

 https://blog.csdn.net/hahajinbu/article/details/79535172

//get

13.instance函數

https://www.runoob.com/python/python-func-isinstance.html

14.只有一個元素的元組加逗號

https://blog.csdn.net/carrey_0612/article/details/79932265

15.加載mnist數據集時出現警告

https://stackoverflow.com/questions/49901806/warning-please-use-alternatives-such-as-official-mnist-dataset-py-from-tensorfl 

16.ndarray的多維理解

https://zhuanlan.zhihu.com/p/39287693

17.讀取csv文件

https://www.cnblogs.com/cloud-ken/p/8432999.html

18.ValueError: sequence too large; cannot be greater than 32 

https://stackoverflow.com/questions/17688094/numpy-array-sequence-too-large

https://stackoverflow.com/questions/39325930/numpy-ndarray-with-more-that-32-dimensions

19.DataFrame的切片操作

https://blog.csdn.net/LY_ysys629/article/details/55224284

20.np_utils.to_categorical

https://keras.io/utils/

21.對數組矩陣補齊padding

https://blog.csdn.net/zenghaitao0128/article/details/78713663

22.tf識別mnist教程（如何打印圖片）

http://tunm.top/blog/32

23.Keras可視化訓練誤差和驗證誤差

https://machinelearningmastery.com/display-deep-learning-model-training-history-in-keras/

24.flatten展平的作用

https://blog.csdn.net/program_developer/article/details/80853425 

25.Keras實現LeNet-5/tf實現（好文）

https://medium.com/@mgazar/lenet-5-in-9-lines-of-code-using-keras-ac99294c8086

26.open和codecs.open區別

 

//在用open時write會將寫入文件內容同樣輸出到控制台，而后者沒有。

前者f.write返回寫入字節的個數。

27.one-hot與數組相互轉換

https://blog.csdn.net/ChaoFeiLi/article/details/89363117

28.遞歸和循環的比較

http://landcareweb.com/questions/791/di-gui-bi-xun-huan-geng-kuai-ma

29.函數式編程語言

http://www.ruanyifeng.com/blog/2012/04/functional_programming.html

30.Keras之ImageDataGenerator()

https://www.jianshu.com/p/d23b5994db64

31.numpy.expand_dims

https://blog.csdn.net/qq_16949707/article/details/53418912 

32.DN中的過擬合問題及解決辦法

https://www.jianshu.com/p/86051c14d434

 33.Keras.fit和fit_generator

https://blog.csdn.net/learning_tortosie/article/details/85243310

34.訓練模型如何選batch_size?

怎么選取訓練神經網絡時的Batch size? - YJango的回答 - 知乎 https://www.zhihu.com/question/61607442/answer/440401209

怎么選取訓練神經網絡時的Batch size? - 夕小瑤的回答 - 知乎 https://www.zhihu.com/question/61607442/answer/204525634

35.標准差的計算

https://www.cnblogs.com/webRobot/p/7722820.html

為何分母為n-1

https://blog.csdn.net/Hearthougan/article/details/77859173

36.playground教程

 https://www.jianshu.com/p/5f83defc7615

37.二分查找時間復雜度

https://blog.csdn.net/frances_han/article/details/6458067

38.py中的二維數組申請

https://www.cnblogs.com/btchenguang/archive/2012/01/30/2332479.html

39.牛頓法-優化算法

 https://blog.csdn.net/google19890102/article/details/41087931

40.最優化算法overview

http://ruder.io/optimizing-gradient-descent/

41.shel腳本編程入門

https://www.runoob.com/linux/linux-shell-include-file.html

 https://lg1024.com/post/shell_01.html

42._import_動態加載模塊

http://wsfdl.com/python/2013/11/02/Python%E6%A8%A1%E5%9D%97%E7%9A%84%E5%8A%A8%E6%80%81%E5%8A%A0%E8%BD%BD.html

43.打開pkl文件

https://blog.csdn.net/NewstarSouth/article/details/47092037

44.io.open和open

https://stackoverflow.com/questions/33891373/difference-between-io-open-vs-open-in-python

45. eval函數

https://www.runoob.com/python/python-func-eval.html

https://blog.csdn.net/zhanh1218/article/details/37562167

 46.tf的GPU和CPU的區別

https://blog.csdn.net/huangx06/article/details/78835360

https://stackoverflow.com/questions/52624703/difference-between-installation-libraries-of-tensorflow-gpu-vs-cpu

47.全角半角轉換

https://www.cnblogs.com/kaituorensheng/p/3554571.htm

48.2.7中的zip和izip

https://blog.csdn.net/orangleliu/article/details/23737701

>>> a=[[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]]
>>> b=[[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]]
>>> d=list(zip(a,b))
>>> d
[([0, 1, 2], [0, 1, 2]), ([3, 4, 5], [3, 4, 5]), ([6, 7, 8], [6, 7, 8])]#第一個元祖包含a/b的第一個元素（list類型）

 49.linux中查看文件編碼格式

https://jingyan.baidu.com/article/36d6ed1f6fc8b71bcf48838e.html

50.tf中的參數初始化方法

https://blog.csdn.net/dcrmg/article/details/80034075