Google Colaboratory - python 실습하기

https://colab.research.google.com/

https://research.google.com/colaboratory/faq.html

자주 묻는 질문(FAQ)

기본 사항

Colab 사용하기

Google Colab Free GPU Tutorial

https://medium.com/deep-learning-turkey/google-colab-free-gpu-tutorial-e113627b9f5d

Hello! I will show you how to use Google Colab, Google’s free cloud service for AI developers. With Colab, you can develop deep learning applications on the GPU for free.

Thanks to KDnuggets!

I am happy to announce that this blog post was selected as KDnuggets Silver Blog for February 2018! Read this on KDnuggets.

What is Google Colab?

Google Colab is a free cloud service and now it supports free GPU!

You can;

• improve your Python programming language coding skills.
• develop deep learning applications using popular libraries such as Keras, TensorFlow, PyTorch, and OpenCV.

The most important feature that distinguishes Colab from other free cloud services is; Colab provides GPU and is totally free.

Detailed information about the service can be found on the faq page.

Getting Google Colab Ready to Use

Creating Folder on Google Drive

Since Colab is working on your own Google Drive, we first need to specify the folder we’ll work. I created a folder named “app” on my Google Drive. Of course, you can use a different name or choose the default Colab Notebooks folder instead of app folder.

I created an empty “app” folder

Creating New Colab Notebook

Create a new notebook via Right click > More > Colaboratory

Right click > More > Colaboratory

Rename notebook by means of clicking the file name.

Setting Free GPU

It is so simple to alter default hardware (CPU to GPU or vice versa); just follow Edit > Notebook settings or Runtime>Change runtime type and select GPU as Hardware accelerator.

Running Basic Python Codes with Google Colab

Now we can start using Google Colab.

I will run some Basic Data Types codes from Python Numpy Tutorial.

It works as expected :) If you do not know Python which is the most popular programming language for AI, I would recommend this simple and clean tutorial.

Running or Importing .py Files with Google Colab

Run these codes first in order to install the necessary libraries and perform authorization.

When you run the code above, you should see a result like this:

Click the link, copy verification code and paste it to text box.

After completion of the authorization process, you should see this:

Now you can reach you Google Drive with:

install Keras:

!pip install -q keras

upload mnist_cnn.py file to app folder which is located on your Google Drive.

mnist_cnn.py file

run the code below to train a simple convnet on the MNIST dataset.

!python3 "/content/drive/My Drive/app/mnist_cnn.py"

As you can see from the results, each epoch lasts only 11 seconds.

PyTorch로 시작하는 딥 러닝 입문

wikidocs.net/book/2788

파이토치 공식 문서 링크 : https://tutorials.pytorch.kr/beginner/blitz/tensor_tutorial.html