I read the Chainer reference (updated from time to time)

Learning notes from reading Chainer Tutorial

Core Functionalities

Function Functions that operate Variable

Parameters can be used to visualize the learned layer

Variable In short, a wrapper for arrays such as features?

import numpy as np
import chainer

a = np.random.rand(100, 50) * 100
→array([[ 73.79944963,  20.34729163,  17.8695034 , ...,  95.2588098 ,
         80.70607058,  72.77696887],
       [ 63.61317915,  52.34471719,   6.63279207, ...,  23.84326461,
         59.21347284,  99.79442349],
       [ 14.70947019,  73.28647468,  57.40101832, ...,   0.13991004,
          0.69580569,  35.80244434],
       ..., 
       [ 99.22098719,  50.55196297,  18.42562383, ...,  33.23917582,
         28.41971731,  95.31789821],
       [ 57.03728122,  37.14647991,  45.64473654, ...,  50.12747623,
         61.67733488,  33.88739351],
       [ 46.90448489,  89.0190541 ,  58.7650971 , ...,  71.94147691,
         88.81614863,  90.15044102]])

b = chainer.Variable(a)
→<chainer.variable.Variable object at 0x10b335e50>

#Get an array
b.data
→→array([[ 73.79944963,  20.34729163,  17.8695034 , ...,  95.2588098 ,
         80.70607058,  72.77696887],
       [ 63.61317915,  52.34471719,   6.63279207, ...,  23.84326461,
         59.21347284,  99.79442349],
       [ 14.70947019,  73.28647468,  57.40101832, ...,   0.13991004,
          0.69580569,  35.80244434],
       ..., 
       [ 99.22098719,  50.55196297,  18.42562383, ...,  33.23917582,
         28.41971731,  95.31789821],
       [ 57.03728122,  37.14647991,  45.64473654, ...,  50.12747623,
         61.67733488,  33.88739351],
       [ 46.90448489,  89.0190541 ,  58.7650971 , ...,  71.94147691,
         88.81614863,  90.15044102]])

#You can get the type of value etc.
b.label
→'(100, 50), float64'

#Get the full number of values
b.__len__()
→5000

FunctionSet

Function wrapper class. Used when sending an entire Function to the GPU or passing parameters and gradients to the Optimizer class.

We will update it from time to time.

Recommended Posts

I read the Chainer reference (updated from time to time)
vtkXMLUnstructuredGridReader Summary (updated from time to time)
vtkOpenFOAMReader Summary (Updated from time to time)
Tensorflow memo [updated from time to time]
[Introduction to matplotlib] Read the end time from COVID-19 data ♬
Private Python handbook (updated from time to time)
vtkClipPolyData / DataSet Summary (Updated from time to time)
[Updated from time to time] PostmarketOS related notes
Summary of vtkThreshold (updated from time to time)
For the first time in Numpy, I will update it from time to time
Summary of gcc options (updated from time to time)
Notes on machine learning (updated from time to time)
OpenFOAM post-processing cheat sheet (updated from time to time)
progate Python learning memo (updated from time to time)
Useful help sites, etc. (updated from time to time)
I tried to learn the sin function with chainer
I want to see the file name from DataLoader
I tried to detect the iris from the camera image
Machine learning python code summary (updated from time to time)
[Updated from time to time] Review of Let Code NumPy
I wanted to use the Python library from MATLAB
I tried to approximate the sin function using chainer
Migrating from Chainer v1 to Chainer v2
Anaconda updated from 4.2.0 to 4.3.0 (python3.5 updated to python3.6)
I tweeted from the terminal!
I read the SHAP paper
I want to move selenium for the time being [for mac]
[Updated from time to time] Summary of design patterns in Java
I want to calculate the allowable downtime from the operating rate
I tried to illustrate the time and time in C language
I tried to display the time and today's weather w
I tried changing the python script from 2.7.11 to 3.6.0 on windows10
I tried to get various information from the codeforces API
I tried to approximate the sin function using chainer (re-challenge)
I want to create a Dockerfile for the time being.
I want to record the execution time and keep a log.
I tried to describe the traffic in real time with WebSocket
I want to automatically find high-quality parts from the videos I shot
[Notes / Updated from time to time] This and that of Azure Functions
I want to read the html version of "OpenCV-Python Tutorials" OpenCV 3.1 version
[Updated as appropriate] I tried to organize the basic visualization methods
Read all the contents of proc / [pid] ~ From setgroups to wchan ~
Read all the contents of proc / [pid] ~ From cwd to loginuid ~
I tried to display the video playback time (OpenCV: Python version)
Read all the contents of proc / [pid] ~ From map_files to numa_maps ~
I calculated the stochastic integral (I to integral)
Python (from first time to execution)
Read all the contents of proc / [pid] ~ From oom_adj to sessionid ~
I tried to cut out a still image from the video
For the time being, I want to convert files with ffmpeg !!
Part 1 I wrote the answer to the reference problem of how to write offline in real time in Python
I read "Reinforcement Learning with Python: From Introduction to Practice" Chapter 2
[Note] AI / machine learning / python related websites [updated from time to time]
I tried to move the ball
Read all the contents of proc / [pid] ~ from attr to cpuset ~
I tried to estimate the interval.
I was able to print the thermal printer "PAPERANG" from Python (Windows10, Python3.6)
I want to separate the processing between test time and production environment
I want to send a signal only from the sub thread to the main thread
765 I tried to identify the three professional families by CNN (with Chainer 2.0.0)
Python: I want to measure the processing time of a function neatly