原创 list of questions
points 淺談L0,L1,L2範數及其應用 - 簡書 http://www.jianshu.com/p/bf860ad177dd 搜索 卷積神經網絡 可視化
2020-02-25 08:30:41
原创 Ubuntu 16.04 基本安裝和美化
Ubuntu 16.04 安裝札記 - 昕昕の爸爸 - 博客園http://www.cnblogs.com/wadxy1314/p/6880264.
2020-02-25 08:30:41
原创 how to disable vimium for specific urls?
I use the extension vimium in my chrome to get easy control on the pages. But in the jupyter notebook pages, I need
2020-02-25 08:30:41
原创 smooth a curve in images
This is from a post in stackoverflow.com . I make a copy here so that it’s easy to access. #!/usr/bin/env python3 # -
2019-03-09 16:03:10
原创 how operating system locates the dll for an applicaton
when it’s implicit linking an dll (dynamic-link library) , the operating system will use the following algorithm for
2019-01-10 15:56:37
原创 why cross entropy loss works
cross entropy is measurement of probability distributions p and q over the same underlying random variable. H(p,q)=−∑
2019-01-06 16:15:48
原创 How to make TensorFlow employ multiple GPUs
The content of this essay may not be true. It’s just a short note. As far as I know, recent versions of TensorFlow do
2019-01-02 14:49:27
原创 機器學習領域的兩個名詞 ~~BP神經網絡~~ & ~~sotfmax loss~~
BP神經網絡 我聽人說過BP神經網絡 、一般的BP神經網絡，我還聽過前饋神經網絡。我感覺他們說的是同一個東西，也就是那種多層全連接的神經網絡，也就是MultiLayer Perceptron (MLP)。不過，不同的名字裏面，“向前”是他
2018-09-05 03:02:49
原创 tmux-cheatsheet.markdown
tmux shortcuts & cheatsheet start new: tmux start new with session name: tmux new -s myname attach: tmux a # (or at
2018-09-05 03:02:49
原创 如何讓奇異值分解(SVD)變得不“奇異”？
如何讓奇異值分解(SVD)變得不“奇異”？ 紅色石頭 發佈於 2018-08-29 分類：機器學習 閱讀(144) 評論(0) 如何讓奇異值分解(SVD)變得不“奇異”？-紅色石頭的個人博客 http://redstonewill
2018-09-05 03:02:49
原创 sklearn庫的學習 sklearn庫的學習
origin: sklearn庫的學習 - CSDN博客 https://blog.csdn.net/u014248127/article/details/78885180 sklearn庫的學習 網上有很多關於skle
2018-09-05 03:02:49
3
原创 fit a curve
scipy.interpolate.splprep # python - Interpolating a closed curve using scipy - Stack Overflow # https://stackoverflow.
2018-09-05 03:02:49
原创 'binary_crossentropy' & 'categorical_crossentropy' in keras
In model.compile(*) of keras, I met binary_crossentropy & categorical_crossentropy. These two kinds of loss somehow mad
2018-09-05 03:02:49
18
原创 5 easy steps to start editing python notebooks over SSH
ref: 5 easy steps to start editing python notebooks over SSH http://fizzylogic.nl/2017/11/06/edit-jupyt
2018-09-05 03:02:49
原创 nvidia errors in TensorFlow
Go to check GPU memory usage, when encountering nvidia or cuda error. I’ve been worked with tensorflow-gpu for a whil
2018-09-05 03:02:49