Get Google Colab ready for use

Local side

Make sure Google Drive and local are in sync. Google backup and sync.app

Google Colab side

Mount the drive

Enable GPU

Install chainer

Install chainer. Just in case, make sure that the GPU is enabled.

Install python-shogi and pydlshogi

You are now ready to use Google Colab.

Use Google Colab

Local side

All editing of .py files is done locally.

Colab side

It is necessary to reflect the edits made on the local side. To make it take effect, restart the runtime.

Learning execution

The image is the image at the time of learning in Chapter 7. You may need to install pydlshogi every time (every runtime reboot?). python-shogi may need to be installed occasionally (?).

Experiment

CPU vs GPU Compare the learning speeds of CPU and GPU.

result GPU is 25 times faster

The learning of the evaluation interval 100 described in Chapter 7 was carried out, and the average time of one evaluation interval was measured.

CPU (iMac 3.1GHz 6-core 10th generation Intel Core i5 processor) 100 seconds on average GPU（Colab） 4 seconds on average

Recommended Posts

Learn with Shogi AI Deep Learning on Mac and Google Colab Use Google Colab

Deep Learning with Shogi AI on Mac and Google Colab

Deep Learning with Shogi AI on Mac and Google Colab Chapter 11

Deep Learning with Shogi AI on Mac and Google Colab Chapters 1-6

Deep Learning with Shogi AI on Mac and Google Colab Chapter 8

Deep Learning with Shogi AI on Mac and Google Colab Chapter 12 3

Deep Learning with Shogi AI on Mac and Google Colab Chapter 7

Deep Learning with Shogi AI on Mac and Google Colab Chapter 10 6-9

Deep Learning with Shogi AI on Mac and Google Colab Chapter 7 5-7

Deep Learning with Shogi AI on Mac and Google Colab Chapter 9

Deep Learning with Shogi AI on Mac and Google Colab Chapter 12 3

Deep Learning with Shogi AI on Mac and Google Colab Chapter 12 1-2

Deep Learning with Shogi AI on Mac and Google Colab Chapter 12 3

Deep Learning with Shogi AI on Mac and Google Colab Chapter 12 3 ~ 5

Deep Learning with Shogi AI on Mac and Google Colab Chapter 8 5-9

Deep Learning with Shogi AI on Mac and Google Colab Chapter 8 1-4

Deep Learning with Shogi AI on Mac and Google Colab Chapter 12 3

Deep Learning with Shogi AI on Mac and Google Colab Chapter 7 8

Deep Learning with Shogi AI on Mac and Google Colab Chapter 7 1-4

Deep Learning on Mac and Google Colab Words Learned with Shogi AI

Use MeCab and neologd with Google Colab

Machine learning with Pytorch on Google Colab

About learning with google colab

Steps to quickly create a deep learning environment on Mac with TensorFlow and OpenCV

Play with Turtle on Google Colab

The strongest way to use MeCab and CaboCha with Google Colab

Use TPU and Keras with Google Colaboratory

"Learning word2vec" and "Visualization with Tensorboard" on Colaboratory

Install selenium on Mac and try it with python

Deep learning image analysis starting with Kaggle and Keras

Ubuntu 20.04 on raspberry pi 4 with OpenCV and use with python

[AI] Deep Metric Learning

"Learn while making! Development deep learning by PyTorch" on Colaboratory.

[Google Colab] How to interrupt learning and then resume it

Recognize your boss and hide the screen with Deep Learning

Machine learning to learn with Nogizaka46 and Keyakizaka46 Part 1 Introduction

Machine learning environment settings based on Python 3 on Mac (coexistence with Python 2)

Reinforcement learning 23 Create and use your own module with Colaboratory

HIKAKIN and Max Murai with live game video and deep learning

Easy deep learning web app with NNC and Python + Flask

Deep Kernel Learning with Pyro

Plotly Dash on Google Colab

Try Deep Learning with FPGA

Use matplot libwidget on mac

Catalina on Mac and pyenv

Generate Pokemon with Deep Learning

Create AtCoder Contest appointments on Google Calendar with Python and GAS

Build a Python environment on your Mac with Anaconda and PyCharm

Error and solution when installing python3 with homebrew on mac (catalina 10.15)

PyPI package for super easy use of Cotoha on Google colab

Install lp_solve on Mac OS X and call it with python.