Name: TF.Learnで手書き文字を分類する - 機械学習レシピ #7 (Classifying Handwritten Digits with TF.Learn - Machine Learning Recipes #7)
Uploaded: 2021-01-14T06:58:28.000Z
Duration: 7 min 1 s
Description: VoiceTubeの動画で発音を聞きながら英語表現を覚えよう！学べる英語：

in Image Classifier using TensorFlow for Poets,

and this time, we'll write one using TF.Learn.

classifying handwritten digits from the MNIST dataset,

and writing a simple classifier for these is often

considered the Hello World of computer vision.

Now MNIST is a multi-class classification problem.

I wrote an IPython notebook for this episode,

and you can find a link to it in the description.

And to make it easier for you to configure your environment,

I'll start with a quick screencast of installing

First, here's an outline of what we'll cover.

I'll show you how to download the dataset

Next, we'll train a classifier, evaluate it,

and use it to make predictions on new images.

Then we'll visualize the weights the classifier learns

to gain intuition for how it works under the hood.

for Docker linked from the Getting Started page

on TensorFlow.org, and I'll start this screencast

assuming you've just finished downloading and installing

Docker itself but haven't started installing TensorFlow.

Starting from a fresh install of Docker, the first thing to do

And when this appears, you'll see an IP address just

and there's a link to that in the description.

The image contains TensorFlow with all its dependencies

properly configured, and here's the command

we'll use to download and launch the image.

But first, let's choose the version we want.

Now we can copy-paste the command into a terminal

If this is the first time you've run the image,

And on subsequent runs, it'll be cached locally.

The image starts automatically, and by default, it

All that's left for us to do is to open up a browser

and point it to the IP we jotted down earlier on port 8888.

that we can experiment with in our browser served

You can find the notebook for this episode in the description

I'll use matplotlib to display images, and, of course,

we'll use TF.Learn to train the classifier.

All of these are installed with the image.

The dataset contains thousands of labeled images

It's pre-divided into train, which is 55,000,

Let's visualize a few of these to get a feel.

This code displays an image along with its label,

and you might notice I'm reshaping the image,

The first image from the testing set is a seven,

and you can see the example index as well as the label.

but there's a variety of different handwriting

Here's an image that's harder to recognize.

That means each image contains exactly one digit.

Now let's talk about the features we'll use.

That's because extracting useful features

from images, like textures and shapes, is hard.

And here, we're using the flattened representation

To flatten an image means to convert it from a 2D array

to a 1D array by unstacking the rows and lining them up.

字幕リスト動画再生

TF.Learnで手書き文字を分類する - 機械学習レシピ #7 (Classifying Handwritten Digits with TF.Learn - Machine Learning Recipes #7)

episode

evidence

description

properly