## python learning notes (2): numpy Foundation

Counter function can count the number of data in the list
Most common (10) can extract the top ten bits
from collections import Counter
a = ['q','q','w','w','w']
count = Counter(a)
count.most_common(1)
[('w', 3)]
count
Counter({'q': 2, 'w': 3})
The series object in panda has a value "counts method to count
The. fillna() function can rep ...

Posted on *Tue, 31 Mar 2020 16:48:30 -0700* by **ChrisF79**

## Python programming method

Python programming ideas
1. Top down design
2. Bottom up execution
For example: sports competition code
1. Top down design
#Games.py
from random import random
def printIntro():
print("Simulate two players A and B Some kind of competitive game")
print("Required for program operation A and B Capability val ...

Posted on *Mon, 30 Mar 2020 23:12:39 -0700* by **valoukh**

## How to use GAN to color Pokemon

In the previous Demo, we used the conditional GAN to generate a handwritten digital image. So what else can we do with neural networks besides generating digital images?
In this case, we use neural network to color the wireframe of Pokemon.
Step 1: import and use the library
from __future__ import absolute_import, division, print_function, uni ...

Posted on *Thu, 12 Mar 2020 20:37:02 -0700* by **tkmk**

## Tutorial of PyTorch generation countermeasure network (DCGAN)

To read the illustrated tutorial, go to http://studyai.com/pytorch-1.4/beginner/dcgan_faces_tutorial.html
This tutorial introduces DCGANs with an example. We will train a general adversarial network (GAN) to generate new celebrities after showing it many photos of celebrities. Most of the code here comes from the implementation of Python / exam ...

Posted on *Wed, 11 Mar 2020 04:32:32 -0700* by **atulkul**

## [machine learning] naive Bayesian text classification

Naive Bayes
1. Introduction to naive Bayesian algorithm
Naive Bayes is a classification algorithm based on Bayes. Naive Bayes classification algorithm calculates the prior probability of the target object, uses Bayes theorem to calculate the posterior probability, and then compares the posterior prob ...

Posted on *Tue, 03 Mar 2020 19:33:38 -0800* by **gukii**

## Python drawing normal curve: linespace combination Matplotlib (put into self write library, one line of code to realize complex drawing)

. Not much to say, given mu and sigma, a line of code to achieve complex drawing, all kinds of details of configuration are in silence.
PS: the specific usage of this figure is shown ...

Posted on *Sun, 23 Feb 2020 04:29:52 -0800* by **mega77**

## Python self study notes - Chapter 3 control structure and exceptions

1. Control structure
Python implements conditional branching through if statement and loop through while statement and for...in statement. There are other conditional expressions, like the ternary operators in Java or C.
1.1. Conditional branch
The most common syntax for Python conditional branch statements:
if boolean_expression1:
suite1
e ...

Posted on *Mon, 17 Feb 2020 00:32:07 -0800* by **lhaynes**

## Linear Regression &Softmax classification model & multi-layer perceptron

Linear regression after class questions
Full connection layer and I / O shape
If you are implementing a fully connected layer, the input shape of the fully connected layer is 7 × 8, and the output shape is 7 × 1, where 7 is the batch size, then the shape of the weight parameter w and th ...

Posted on *Fri, 14 Feb 2020 07:45:51 -0800* by **David-fethiye**

## Two solutions to over fitting

This paper mainly studies the book of dive into DL pytorch. So most of the content of this blog comes from this book. The framework uses pytorch, and the development tool is pycharm
Refer to hands-on deep learning
Reference link https://github.com/ShusenTang/Dive-into-DL-PyTorchhttps://github.com/zergta ...

Posted on *Wed, 12 Feb 2020 04:41:51 -0800* by **baw**

## Notes on knowledge points of softmax regression

The basic concept of softmax
Softmax regression, like linear regression, is also a single-layer neural network. The output layer of softmax regression is also a full connection layer.
The classification problem needs to get discrete prediction output. A simple way is to output the valueAs the predi ...

Posted on *Tue, 11 Feb 2020 22:14:50 -0800* by **mickey9801**